阅读说明：本技术 一种基于机器学习的环路热管太阳能压力模式识别方法 (Loop heat pipe solar pressure pattern recognition method based on machine learning ) 是由 郭春生 许艳锋 李蒸 李言伟 江程 马军 薛于凡 谷潇潇 宁文婧 刘元帅 薛丽红 于 2020-05-19 设计创作，主要内容包括：本发明提供了一种基于机器学习的环路热管太阳能压力模式识别方法,所述集热装置包括反射镜和集热管箱,所述集热装置包括除垢阶段,所述采取如下方式运行：在除垢阶段,采取如下方式运行：所述压力感知元件与控制器进行数据连接,所述压力数据实时存储在数据库中,采用一维深度卷积神经网络提取数据特征,并进行模式识别,从而控制是否对集热管箱进行集热以进行除垢。本发明能够基于机器学习与模式识别的理论方法,根据集热装置不同的运行工况,利用集热装置实时监控系统中压力数据,设计出相应的集热运行模式,用大量的压力数据训练深度卷积神经网络,从而进行集热装置除垢,提高热利用效果和除垢效果。(The invention provides a loop heat pipe solar pressure mode identification method based on machine learning, wherein a heat collection device comprises a reflector and a heat collection pipe box, the heat collection device comprises a descaling stage, and the method comprises the following steps: in the descaling stage, the following modes are adopted for operation: the pressure sensing element is in data connection with the controller, the pressure data are stored in a database in real time, data features are extracted by adopting a one-dimensional depth convolution neural network, and pattern recognition is carried out, so that whether heat collection is carried out on the heat collection tube box or not is controlled to remove scale. According to the invention, based on a theoretical method of machine learning and pattern recognition, according to different operation conditions of the heat collecting device, the corresponding heat collecting operation mode is designed by utilizing pressure data in the real-time monitoring system of the heat collecting device, and a deep convolution neural network is trained by using a large amount of pressure data, so that the heat collecting device is descaled, and the heat utilization effect and the descaling effect are improved.)

1. A loop heat pipe solar pressure pattern recognition method based on machine learning is disclosed, wherein a heat collecting device comprises a reflector and a heat collecting pipe box, the heat collecting device comprises a descaling stage, and the method comprises the following steps: in the descaling stage, the following modes are adopted for operation:

the pressure sensing element is in data connection with the controller, the pressure data are stored in a database in real time, a one-dimensional depth convolution neural network is adopted to extract data characteristics, and pattern recognition is carried out, so that whether heat collection is carried out on the heat collection tube box or not is controlled to remove scale;

the pressure-based pattern recognition comprises the following steps:

1) preparing data: reexamining and verifying pressure data of the heat collecting devices in the database, correcting missing data, invalid data and inconsistent data, and ensuring the correctness and the logical consistency of the data;

2) generating a data set: dividing the prepared data into a training set/training set label and a detection set/detection set label;

3) network training: inputting the training set data into a convolution neural network, continuously performing convolution and pooling to obtain a characteristic vector, and sending the characteristic vector into a full-connection network. Obtaining a network error by calculating the output of the network and a training set label, and continuously correcting the network weight, the bias, the convolution coefficient and the pooling coefficient by using an error back propagation algorithm to enable the error to meet the set precision requirement, thereby completing network training;

4) network detection: inputting the data of the detection set into the trained network, and outputting a detection result;

5) the heat collector operates: and controlling whether to collect heat for the heat collecting tube box according to the detection result so as to remove scale.

2. The method for identifying the solar pressure pattern of the loop heat pipe based on the machine learning as claimed in claim 1, wherein the pressure sensing element is disposed in the heat collecting pipe box.

3. The utility model provides a heat transfer device, heat transfer device is including the thermal-arrest pipe case, upper left pipe, upper right pipe and the heat release nest of tubes that are located the lower part, and upper left pipe, upper right pipe are located the upper portion of thermal-arrest pipe case.

Technical Field

The invention belongs to the field of solar energy, and particularly relates to a solar heat collector system.

Background

With the rapid development of modern socioeconomic, the demand of human beings on energy is increasing. However, the continuous decrease and shortage of traditional energy reserves such as coal, oil, natural gas and the like causes the continuous increase of price, and the environmental pollution problem caused by the conventional fossil fuel is more serious, which greatly limits the development of society and the improvement of the life quality of human beings. Energy problems have become one of the most prominent problems in the modern world. Therefore, the search for new energy sources, especially clean energy sources without pollution, has become a hot spot of research.

Solar energy is inexhaustible clean energy and has huge resource amount, and the total amount of solar radiation energy collected on the surface of the earth every year is 1 multiplied by 10¹⁸kW.h, which is ten thousand times of the total energy consumed in the world year. The utilization of solar energy has been used as an important item for the development of new energy in all countries of the world. However, the solar radiation has a small energy density (about one kilowatt per square meter) and is discontinuous, which brings certain difficulties for large-scale exploitation and utilization. Therefore, in order to widely use solar energy, not only the technical problems should be solved, but also it is necessary to be economically competitive with conventional energy sources.

Aiming at the structure of a heat collector, the prior art has been researched and developed a lot, but the heat collecting capability is not enough on the whole, and the problem that the operation time is long and scaling is easy to happen, so that the heat collecting effect is influenced.

In any form and structure of solar collector, there is an absorption component for absorbing solar radiation, and the structure of the collector plays an important role in absorbing solar energy.

Aiming at the problems, the invention improves on the basis of the previous invention and provides a novel loop heat pipe solar heat collecting system, thereby solving the problems of low heat exchange amount of a heat pipe and uneven heat exchange.

In application, the continuous heat collection and heating of solar energy or no heating at night can cause the stability of internal fluid, namely the fluid does not flow any more or has little mobility, or the flow is stable, so that the vibration performance of the heat collection tube is greatly weakened, and the descaling and heating efficiency of the heat collection tube is influenced. There is therefore a need for improvements to the above-mentioned solar collectors. The applicant has already filed a relevant patent for this application.

However, in practice it has been found that adjusting the vibration of the tube bundle by varying the periodicity of the fixity and the parameters or parameter differences results in hysteresis and too long or too short a period. Therefore, the invention improves the previous application and intelligently controls the vibration, so that the fluid in the fluid can realize frequent vibration, and good descaling and heating effects can be realized.

Disclosure of Invention

Aiming at the defects in the prior art, the invention provides a heat collecting device with a novel structure. The heat collecting device can be based on a theoretical method of machine learning and pattern recognition, a corresponding heat collecting operation mode is designed by utilizing pressure data in a real-time monitoring system of the heat collecting device according to different operation working conditions of the heat collecting device, and a deep convolutional neural network is trained by using a large amount of pressure data, so that the heat collecting device is descaled, and the heat utilization effect and the descaling effect are improved.

In order to achieve the purpose, the invention adopts the following technical scheme:

a loop heat pipe solar pressure pattern recognition method based on machine learning is disclosed, wherein a heat collecting device comprises a reflector and a heat collecting pipe box, the heat collecting device comprises a descaling stage, and the method comprises the following steps: in the descaling stage, the following modes are adopted for operation:

the pressure sensing element is in data connection with the controller, the pressure data are stored in a database in real time, a one-dimensional depth convolution neural network is adopted to extract data characteristics, and pattern recognition is carried out, so that whether heat collection is carried out on the heat collection tube box or not is controlled to remove scale;

the pressure-based pattern recognition comprises the following steps:

1) preparing data: reexamining and verifying pressure data of the heat collecting devices in the database, correcting missing data, invalid data and inconsistent data, and ensuring the correctness and the logical consistency of the data;

2) generating a data set: dividing the prepared data into a training set/training set label and a detection set/detection set label;

3) network training: inputting the training set data into a convolution neural network, continuously performing convolution and pooling to obtain a characteristic vector, and sending the characteristic vector into a full-connection network. Obtaining a network error by calculating the output of the network and a training set label, and continuously correcting the network weight, the bias, the convolution coefficient and the pooling coefficient by using an error back propagation algorithm to enable the error to meet the set precision requirement, thereby completing network training;

4) network detection: inputting the data of the detection set into the trained network, and outputting a detection result;

5) the heat collector operates: and controlling whether to collect heat for the heat collecting tube box according to the detection result so as to remove scale.

Preferably, the heat collecting device comprises a heat collecting pipe box, a left upper pipe, a right upper pipe and a heat releasing pipe group, wherein the heat collecting pipe box, the left upper pipe, the right upper pipe and the heat releasing pipe group are positioned at the lower part, the left upper pipe and the right upper pipe are positioned at the upper part of the heat collecting pipe box, the heat releasing pipe group comprises a left heat releasing pipe group and a right heat releasing pipe group, the left heat releasing pipe group is communicated with the left upper pipe and the heat collecting pipe box, the right heat releasing pipe group is communicated with the right upper pipe and the heat collecting pipe box, so that the heat collecting pipe box, the left upper pipe, the right upper pipe and the heat releasing pipe group form a closed heating fluid circulation, the heat releasing pipe groups are one or more, each heat releasing pipe group comprises a plurality of heat releasing pipes in an arc shape, the end parts of the adjacent heat releasing pipes are communicated, the plurality of heat releasing pipes form a series structure, and the end parts of the heat releasing pipes form a free end; the heat collecting pipe box comprises a first pipe orifice and a second pipe orifice, the first pipe orifice is connected with an inlet of a left heat releasing pipe group, the second pipe orifice is connected with an inlet of a right heat releasing pipe group, an outlet of the left heat releasing pipe group is connected with a left upper pipe, and an outlet of the right heat releasing pipe group is connected with a right upper pipe.

The invention has the following advantages:

1. according to the invention, based on a theoretical method of machine learning and pattern recognition, according to different operation conditions of the heat collecting device, the corresponding heat collecting operation mode is designed by utilizing pressure data in the real-time monitoring system of the heat collecting device, and a deep convolution neural network is trained by using a large amount of pressure data, so that the heat collecting device is descaled, and the heat utilization effect and the descaling effect are improved.

2. The invention provides a heat collecting device with a novel structure, which can improve the heat collecting effect, improve the heat releasing capacity of a heat collecting pipe and reduce the energy consumption.

3. The heat collecting device with new structure has more heat releasing pipe groups in limited space to increase the vibration range of the pipe bundle, strengthen heat transfer and eliminate scale.

4. The heat exchange efficiency can be further improved by the arrangement of the pipe diameters and the interval distribution of the heat release pipe groups in the fluid flowing direction.

5. The invention optimizes the optimal relation of the parameters of the heat collecting device through a large amount of experiments and numerical simulation, thereby realizing the optimal heating efficiency.

Description of the drawings:

FIG. 1 is a front view of a heat collecting device according to the present invention.

FIG. 2-1 is a front view of the heat collecting system of the present invention.

Fig. 2-2 is a front view of the heat collecting system of the present invention without collecting heat.

FIGS. 2 to 3 are front views illustrating heat collection of a preferred heat collecting device according to the present invention.

FIGS. 2 to 4 are front views of the preferred heat collecting apparatus of the present invention without collecting heat.

FIG. 3 is a left side view of the heat collecting device of FIG. 1 according to the present invention.

FIG. 4 is a bottom view of the heat collecting device of FIG. 1 according to the present invention.

FIG. 5 is a schematic view showing the staggered arrangement structure of the heat releasing tube sets of the heat collecting device of the present invention.

FIG. 6 is a schematic diagram of a heat collecting device.

FIG. 7 is a cross-sectional view of a preferred hydraulic pump.

In the figure: 1. the heat radiation pipe group comprises a left heat radiation pipe group 11, a right heat radiation pipe group 12, 21, a left upper pipe, 22, a right upper pipe, 3, a free end, 4, a free end, 5, a free end, 6, a free end, 7, a heat radiation pipe, 8, a heat collection pipe box, 9, a box body, 10 a first pipe orifice, 13 a second pipe orifice, a left return pipe 14, a right return pipe 15, 16 reflectors and 17 supporting pieces;

24. right hydraulic pump, 25, left hydraulic pump, 26, right hydraulic device, 27, left hydraulic device, 28, right telescopic rod, 29, left telescopic rod, 30, eccentric wheel, 31, check valve, 32, oil cylinder, 33, stop valve, 34 and plunger.

Detailed Description

The following detailed description of embodiments of the invention refers to the accompanying drawings.

In this document, "/" denotes division and "×", "denotes multiplication, referring to formulas, if not specifically stated.

As shown in fig. 1, a heat collecting device comprises a heat collecting pipe box 8, a left upper pipe 21, a right upper pipe 22 and a heat releasing pipe group 1, wherein the heat releasing pipe group 1 comprises a left heat releasing pipe group 11 and a right heat releasing pipe group 12, the left heat releasing pipe group 11 is communicated with the left upper pipe 21 and the heat collecting pipe box 8, the right heat releasing pipe group 12 is communicated with the right upper pipe 22 and the heat collecting pipe box 8, so that the heat collecting pipe box 8, the left upper pipe 21, the right upper pipe 22 and the heat releasing pipe group 1 form a closed circulation of heating fluid, the heat collecting pipe box 8 is filled with phase change fluid, each heat releasing pipe group 1 comprises a plurality of heat releasing pipes 7 in an arc shape, the end parts of the adjacent heat releasing pipes 7 are communicated, so that the plurality of heat releasing pipes 7 form a serial structure, and the end parts of the heat releasing pipes 7 form heat releasing pipe free ends 3-6; the heat collecting tube box comprises a first tube opening 10 and a second tube opening 13, the first tube opening 10 is connected with an inlet of a left heat-releasing tube group 11, the second tube opening 13 is connected with an inlet of a right heat-releasing tube group 12, an outlet of the left heat-releasing tube group 11 is connected with a left upper tube 21, and an outlet of the right heat-releasing tube group 12 is connected with a right upper tube 22; the first nozzle 10 and the second nozzle 13 are disposed at one side of the heat collecting tube box 8. Preferably, the left and right heat-releasing tube groups 11 and 12 are symmetrical along the middle of the heat collecting tube box.

Preferably, the upper left tube 21, the upper right tube 22 and the heat-releasing tube group 1 are provided in the tank 9, and a fluid, preferably air or water, is provided in the tank 9 to flow.

Preferably, the left upper tube 21, the right upper tube 22 and the heat collecting tube box 8 extend in a horizontal direction.

Preferably, the fluid flows in a horizontal direction.

Preferably, a plurality of heat radiation tube groups 1 are arranged along the horizontal direction of the left upper tube 21, the right upper tube 22 and the heat collecting tube box 8, and the heat radiation tube groups 1 are connected in parallel.

Preferably, a left return pipe 14 is disposed between the left upper pipe 21 and the heat collecting tube box 8, and a right return pipe 15 is disposed between the right upper pipe 22 and the heat collecting tube box 8. Preferably, the return pipes are provided at both ends of the heat collecting tube box 8.

The heat collecting tube box 8 is filled with phase-change fluid, preferably vapor-liquid phase-change fluid. The fluid heats and evaporates at the heat collecting tube box 8, flows along the heat release tube bundle to the upper left pipe 21 and the upper right pipe 22, and the fluid can produce volume expansion after being heated, thereby forming steam, and the volume of steam is far greater than water, and the steam that consequently forms can carry out the flow of quick impact formula in the coil pipe. Because of volume expansion and steam flow, the free end of the heat-radiating pipe can be induced to vibrate, the vibration is transmitted to the heat-exchanging fluid in the box body 9 by the free end of the heat-exchanging pipe in the vibrating process, and the fluid can also generate disturbance with each other, so that the surrounding heat-exchanging fluid forms disturbance flow, a boundary layer is damaged, and the purpose of enhancing heat transfer is realized. The fluid is condensed and released heat on the left upper pipe and the right upper pipe and then flows back to the heat collecting pipe box through the return pipe.

According to the invention, the prior art is improved, and the upper pipe and the heat release pipe groups are respectively arranged into two groups distributed on the left side and the right side, so that the heat release pipe groups distributed on the left side and the right side can perform vibration heat exchange descaling, the heat exchange vibration area is enlarged, the vibration is more uniform, the heat exchange effect is more uniform, the heat exchange area is increased, and the heat exchange and descaling effects are enhanced.

The above-mentioned structure has carried out patent application, and this application is to above-mentioned structure further improves, reinforcing scale removal and heat transfer effect.

In the operation of the solar heat collector, although the structure has the elastic vibration descaling effect, the descaling effect needs to be further improved after long-term operation.

It has been found in research and practice that a sustained and stable heat collection results in a fluid-forming stability of the internal heat exchange components, i.e. no fluid flow or little fluid flow, or a steady flow rate, resulting in a greatly reduced vibration performance of the heat-emitting bank 1, which affects the efficiency of descaling and heating of the bank 1. For example, continuous heat collection in the day, or continuous no heat collection in the night, results in reduced descaling effect, and continuous heat collection in the day or electric heating descaling in the night is adopted in the prior application, which greatly improves the heat collection effect in the day. However, the above structure requires a separate electric heating device and complicated design of the assembly associated with the electric heating, resulting in a complicated structure, and thus the heat collecting device needs to be improved as follows.

In the prior application of the inventor, a heating mode with periodicity and parameters or parameter difference is provided, and the vibration of the coil is continuously promoted by the periodic heating mode, so that the heating efficiency and the descaling effect are improved. However, adjusting the vibration of the tube bundle by variation can lead to hysteresis and too long or too short a cycle. Therefore, the invention improves the previous application and intelligently controls the vibration, so that the fluid in the device can realize frequent vibration, and a good descaling effect is realized.

Aiming at the defects in the technology researched in the prior art, the invention provides a novel descaling heat collector capable of intelligently controlling vibration. This heat collector can realize fine scale removal effect.

The solar heat collector comprises a descaling stage, and the heat collector operates in the following mode in the descaling stage:

based on pressure pattern recognition

Preferably, a pressure sensing element is arranged in the heat collecting device and used for detecting the pressure in the heat collecting device, the pressure sensing element is in data connection with the controller, the pressure data are stored in a database in real time, a one-dimensional depth convolution neural network is adopted to extract data characteristics and perform mode identification, and therefore whether the heat collecting tube box is subjected to heat collection or not is controlled to remove scale.

The pressure-based pattern recognition comprises the following steps:

1. preparing data: and reexamining and verifying the pressure data of the heat collecting devices in the database, and correcting missing data, invalid data and inconsistent data to ensure the correctness and the logical consistency of the data.

2. Generating a data set: the prepared data is divided into training set/training set labels, detection set/detection set labels.

3. Network training: inputting the training set data into a convolution neural network, continuously performing convolution and pooling to obtain a characteristic vector, and sending the characteristic vector into a full-connection network. And obtaining a network error by calculating the output of the network and a training set label, and continuously correcting the network weight, the bias, the convolution coefficient and the pooling coefficient by using an error back propagation algorithm to enable the error to meet the set precision requirement, thereby finishing the network training.

4. Network detection: and inputting the detection set data into the trained network, and outputting a detection result label.

5. The heat collector operates: and controlling whether heat is collected for the heat collecting tube box or not according to the detection result label so as to remove the scale.

The invention provides a novel system for intelligently controlling vibration descaling of a heat collecting device, which is based on a theoretical method of machine learning and pattern recognition, utilizes pressure data with time correlation in a centralized heat collecting device real-time monitoring system according to different operating conditions of the heat collecting device, designs a corresponding working mode (heating mode/non-heating mode) of the heat collecting device, and trains a deep convolutional neural network by using a large amount of pressure data so as to control heat collection of the heat collecting device.

Preferably, the data preparation step specifically includes the following processing:

1) processing missing data: missing values in the database may occur due to a failure of the network transmission. For the missing data value, adopting an estimation method and replacing the missing value with the sample mean value;

2) processing invalid data: the pressure data in the database may have invalid values, such as negative values or values exceeding a theoretical maximum value, due to a failure of the sensor, and these values are deleted from the database;

3) processing inconsistent data: the inconsistent data is checked by means of an integrity constraint mechanism of the database management system, and then corrected by referring to corresponding data values in the database. Preferably, in the heat collecting device, the heat collecting pressure with high outdoor temperature is higher than the heat collecting pressure with low outdoor temperature, if the heat collecting pressure with high outdoor temperature in the database is lower than the heat collecting pressure with low outdoor temperature, a user error prompt can be given by means of a check constraint mechanism in an integrity constraint of the database management system, and the user replaces the pressure data value of the inconsistent data with the predicted data or the critical pressure data value of the corresponding temperature according to the error prompt.

Preferably, the step of generating a data set comprises the steps of:

1) generating training set data and labels: and reading the pressure data values of the corresponding working conditions from the database according to different operating conditions of the heat collecting device, and generating training set data and working condition labels under various working condition states. Preferably, in a specific application, the operating condition is divided into 1 for heat collection by the heat collection device, and 2 for no heat collection by the heat collection device. Automatically generating working condition labels by a program according to different working conditions;

preferably, the data includes data indicating that the evaporation of the fluid inside the heat collecting device is substantially saturated under different operating conditions. The working condition comprises at least one of season, weather, time and the like.

2) Generating detection set data and labels: and reading the pressure data values of the corresponding working conditions from the database according to different operating conditions of the heat collecting device, and generating detection set data and working condition labels under various working condition states. The working condition labels are the same as the working condition labels of the training set and are automatically generated by a program according to the running working conditions.

As the optimization, whether the evaporation of the fluid in the heat collecting device reaches the saturation or not can be judged, the label is 1, the saturation is reached, and the label is 2.

The network training comprises the following specific steps:

1) reading a group of training set data d, wherein the size of the training set data d is [ Mx 1 xN ], M represents the size of a training batch, and 1 xN represents one-dimensional training data;

2) and performing a first convolution operation on the read training data to obtain a feature map t. Initializing coefficients of a convolution kernel g, and setting the size of g as [ P × 1 × Q ], wherein P represents the number of convolution kernels, [1 × Q ] represents the size of the convolution kernels, the obtained convolution result is t ═ Σ (d × g), and the size of a feature map is [ M × 1 × N × Q ];

3) and performing maximum pooling operation on the feature map t obtained by the convolution operation to obtain a feature map z. Initializing a pooling coefficient, wherein the given pooling step length is p, the size of a pooling window is k, the size of a finally obtained feature map z is [ Mx1 x (N/p). times.Q ], and the data dimensionality is reduced in a pooling process;

4) repeating the steps 2) -3), repeatedly performing convolution and pooling operation to obtain a feature vector x, and finishing the feature extraction process of the convolutional neural network;

5) initializing a weight matrix w and an offset b of the full-connection network, sending the extracted eigenvector x into the full-connection network, and calculating with the weight matrix w and the offset b to obtain a network output y ═ sigma (wxx + b);

6) subtracting the training set label l from the output y obtained by the network to obtain a network error e which is y-l, carrying out derivation on the network error, and sequentially correcting the weight w, the bias b, the pooling coefficients of each layer and the convolution coefficients of each layer of the fully-connected network by utilizing the derivative back propagation;

7) and repeating the process until the network error e meets the precision requirement, finishing the network training process, and generating a convolutional neural network model.

The network detection steps are as follows:

1) loading the trained convolutional neural network model, wherein the convolutional kernel coefficient, the pooling coefficient, the network weight w and the bias b of the convolutional neural network are trained;

2) and inputting the detection data set into the trained convolutional neural network, and outputting a detection result. The type of run can be determined, for example, based on the output tag. For example, 1 represents collector hot, 2 represents collector hot, etc.

The invention provides a new method for controlling the heat collection of the heat collection device, which makes full use of the online monitoring data of the concentrated heat collection device, and has the advantages of high detection speed and low cost.

The invention organically integrates the data processing technology, machine learning and pattern recognition theory, and can improve the accuracy of the operation of the heat collecting device.

The working process of the specific convolutional neural network is as follows:

1) inputting a group of training set data d, wherein the size of the training set data d is [ M multiplied by 1 multiplied by N ], M represents the size of the training batch, and 1 multiplied by N represents one-dimensional training data;

2) and performing a first convolution operation on the read training data to obtain a feature map t. Initializing coefficients of a convolution kernel g, and setting the size of g as [ P × 1 × Q ], wherein P represents the number of convolution kernels, [1 × Q ] represents the size of the convolution kernels, the obtained convolution result is t ═ Σ (d × g), and the size of a feature map is [ M × 1 × N × Q ];

3) and performing maximum pooling operation on the feature map t obtained by the convolution operation to obtain a feature map z. Initializing a pooling coefficient, setting a pooling step length as p, setting a pooling window size as k, and reducing data dimensionality in a pooling process, wherein the size of a finally obtained feature map z is [ MX 1X (N/p) XQ ];

4) repeating the steps 2) -3), and repeatedly performing convolution and pooling operation to obtain a feature vector;

through the mode recognition of the pressure detected by the pressure sensing element, the evaporation of the fluid in the interior is basically saturated, and the volume of the fluid in the interior is not changed greatly. So that the fluid undergoes volume reduction to thereby realize vibration. When the pressure is reduced to a certain degree, the internal fluid starts to enter a stable state again, and the fluid needs to be heated to evaporate and expand again, so that the heat collection tube box needs to be started to heat.

The data is more accurate relative to the previous parameters and parameter differences.

Preferably, the pressure sensing element is disposed within the heat collecting channel 8.

Preferably, the pressure sensing element is disposed at the free end. Through setting up at the free end, can perceive the pressure variation of free end to realize better control and regulation.

Recognizing patterns based on temperature

Preferably, a temperature sensing element is arranged in the heat collecting device and used for detecting the temperature in the heat collecting device, the temperature sensing element is in data connection with the controller, the temperature data are stored in a database in real time, a one-dimensional depth convolution neural network is adopted to extract data characteristics and perform mode identification, and therefore whether the heat collecting tube box is subjected to heat collection or not is controlled to remove scale.

The temperature-based pattern recognition comprises the following steps:

1. preparing data: and rechecking and checking the temperature data of the heat collecting devices in the database, and correcting missing data, invalid data and inconsistent data to ensure the correctness and the logical consistency of the data.

2. Generating a data set: the prepared data is divided into training set/training set labels, detection set/detection set labels.

3. Network training: inputting the training set data into a convolution neural network, continuously performing convolution and pooling to obtain a characteristic vector, and sending the characteristic vector into a full-connection network. And obtaining a network error by calculating the output of the network and a training set label, and continuously correcting the network weight, the bias, the convolution coefficient and the pooling coefficient by using an error back propagation algorithm to enable the error to meet the set precision requirement, thereby finishing the network training.

4. Network detection: and inputting the detection set data into the trained network, and outputting a detection result label.

5. The heat collector operates: and controlling whether heat is collected for the heat collecting tube box or not according to the detection result label so as to remove the scale.

The invention provides a novel system for intelligently controlling vibration descaling of a heat collecting device, which is based on a theoretical method of machine learning and pattern recognition, utilizes temperature data with time correlation in a centralized heat collecting device real-time monitoring system according to different operating conditions of the heat collecting device, designs a corresponding working mode (heating mode/non-heating mode) of the heat collecting device, and trains a deep convolutional neural network by using a large amount of temperature data so as to carry out heat collecting control on the heat collecting device.

Preferably, the data preparation step specifically includes the following processing:

1) processing missing data: missing values in the database may occur due to a failure of the network transmission. For the missing data value, adopting an estimation method and replacing the missing value with the sample mean value;

2) processing invalid data: the temperature data in the database may have invalid values, such as negative values or values exceeding a theoretical maximum value, due to a failure of the sensor, and these values are deleted from the database;

3) processing inconsistent data: the inconsistent data is checked by means of an integrity constraint mechanism of the database management system, and then corrected by referring to corresponding data values in the database. Preferably, in the heat collecting device, the heat collecting temperature with high outdoor temperature is higher than the heat collecting temperature with low outdoor temperature, if the heat collecting temperature with high outdoor temperature in the database is lower than the heat collecting temperature with low outdoor temperature, a user error prompt can be given by means of a check constraint mechanism in an integrity constraint of the database management system, and the user replaces the temperature data value of the inconsistent data with the pre-estimated data or the critical temperature data value of the corresponding temperature according to the error prompt.

Preferably, the step of generating a data set comprises the steps of:

1) generating training set data and labels: and reading the temperature data values of the corresponding working conditions from the database according to different operating conditions of the heat collecting device, and generating training set data and working condition labels under various working condition states. Preferably, in a specific application, the operating condition is divided into 1 for heat collection by the heat collection device, and 2 for no heat collection by the heat collection device. Automatically generating working condition labels by a program according to different working conditions;

preferably, the data includes data indicating that the evaporation of the fluid inside the heat collecting device is substantially saturated under different operating conditions. The working condition comprises at least one of season, weather, time and the like.

2) Generating detection set data and labels: and reading the temperature data values of the corresponding working conditions from the database according to different operating conditions of the heat collecting device, and generating detection set data and working condition labels under various working condition states. The working condition labels are the same as the working condition labels of the training set and are automatically generated by a program according to the running working conditions.

As the optimization, whether the evaporation of the fluid in the heat collecting device reaches the saturation or not can be judged, the label is 1, the saturation is reached, and the label is 2.

The network training comprises the following specific steps:

1) reading a group of training set data d, wherein the size of the training set data d is [ Mx 1 xN ], M represents the size of a training batch, and 1 xN represents one-dimensional training data;

2) and performing a first convolution operation on the read training data to obtain a feature map t. Initializing coefficients of a convolution kernel g, and setting the size of g as [ P × 1 × Q ], wherein P represents the number of convolution kernels, [1 × Q ] represents the size of the convolution kernels, the obtained convolution result is t ═ Σ (d × g), and the size of a feature map is [ M × 1 × N × Q ];

3) and performing maximum pooling operation on the feature map i obtained by the convolution operation to obtain a feature map z. Initializing a pooling coefficient, wherein the given pooling step length is p, the size of a pooling window is k, the size of a finally obtained feature map z is [ Mx1 x (N/p). times.Q ], and the data dimensionality is reduced in a pooling process;

4) repeating the steps 2) -3), repeatedly performing convolution and pooling operation to obtain a feature vector x, and finishing the feature extraction process of the convolutional neural network;

5) initializing a weight matrix w and an offset b of the full-connection network, sending the extracted eigenvector x into the full-connection network, and calculating with the weight matrix w and the offset b to obtain a network output y ═ sigma (wxx + b);

6) subtracting the training set label l from the output y obtained by the network to obtain a network error e which is y-l, carrying out derivation on the network error, and sequentially correcting the weight w, the bias b, the pooling coefficients of each layer and the convolution coefficients of each layer of the fully-connected network by utilizing the derivative back propagation;

7) and repeating the process until the network error e meets the precision requirement, finishing the network training process, and generating a convolutional neural network model.

The network detection steps are as follows:

1) loading the trained convolutional neural network model, wherein the convolutional kernel coefficient, the pooling coefficient, the network weight w and the bias b of the convolutional neural network are trained;

2) and inputting the detection data set into the trained convolutional neural network, and outputting a detection result. The type of run can be determined, for example, based on the output tag. For example, 1 represents collector hot, 2 represents collector hot, etc.

The invention provides a new method for controlling the heat collection of the heat collection device, which makes full use of the online monitoring data of the concentrated heat collection device, and has the advantages of high detection speed and low cost.

The invention organically integrates the data processing technology, machine learning and pattern recognition theory, and can improve the accuracy of the operation of the heat collecting device.

The working process of the specific convolutional neural network is as follows:

1) inputting a group of training set data d, wherein the size of the training set data d is [ M multiplied by 1 multiplied by N ], M represents the size of the training batch, and 1 multiplied by N represents one-dimensional training data;

2) and performing a first convolution operation on the read training data to obtain a feature map t. Initializing coefficients of a convolution kernel g, and setting the size of g as [ P × 1 × Q ], wherein P represents the number of convolution kernels, [1 × Q ] represents the size of the convolution kernels, the obtained convolution result is t ═ Σ (d × g), and the size of a feature map is [ M × 1 × N × Q ];

3) and performing maximum pooling operation on the feature map t obtained by the convolution operation to obtain a feature map z. Initializing a pooling coefficient, setting a pooling step length as p, setting a pooling window size as k, and setting the size of a finally obtained feature map z as [ MX 1X (N/p)/Q ], wherein the pooling process reduces the dimensionality of data;

4) repeating the steps 2) -3), and repeatedly performing convolution and pooling operation to obtain a feature vector;

in this case, the internal fluid is relatively stable, and the tube bundle is deteriorated in vibration at this time, and therefore, it is necessary to adjust the internal fluid so as to vibrate the internal fluid for descaling. So that the fluid undergoes volume reduction to thereby realize vibration. When the temperature is reduced to a certain degree, the internal fluid starts to enter a stable state again, and the fluid needs to be heated to be evaporated and expanded again, so that the heat collection tube box needs to be started to heat.

Preferably, the temperature sensing element is disposed within the heat collecting channel 8.

Preferably, the temperature sensing element is disposed at the free end. Through setting up at the free end, can perceive the temperature variation of free end to realize better control and regulation.

Thirdly, automatically adjusting vibration based on liquid level

Preferably, a liquid level sensing element is arranged in the heat collection tube box 8 and used for detecting the liquid level in the heat collection tube box 8, the liquid level sensing element is in data connection with the controller, the liquid level data are stored in the database in real time, a one-dimensional depth convolution neural network is adopted for extracting data characteristics and performing mode identification, and therefore whether the heat collection tube box is subjected to heat collection or not is controlled so as to remove scale.

The liquid level pattern-based identification comprises the following steps:

1. preparing data: and reexamining and verifying the liquid level data of the heat collecting tube box 8 in the database, and correcting missing data, invalid data and inconsistent data to ensure the correctness and the logical consistency of the data.

2. Generating a data set: the prepared data is divided into training set/training set labels, detection set/detection set labels.

3. Network training: inputting the training set data into a convolution neural network, continuously performing convolution and pooling to obtain a characteristic vector, and sending the characteristic vector into a full-connection network. And obtaining a network error by calculating the output of the network and a training set label, and continuously correcting the network weight, the bias, the convolution coefficient and the pooling coefficient by using an error back propagation algorithm to enable the error to meet the set precision requirement, thereby finishing the network training.

4. Network detection: and inputting the detection set data into the trained network, and outputting a detection result label.

5. The heat collector operates: and controlling whether heat is collected for the heat collecting tube box or not according to the detection result label so as to remove the scale.

The invention provides a novel system for intelligently controlling vibration descaling of a heat collecting device, which is based on a theoretical method of machine learning and pattern recognition, utilizes liquid level data with time correlation in a centralized heat collecting device real-time monitoring system according to different operating conditions of the heat collecting device, designs a corresponding working mode (heating mode/non-heating mode) of the heat collecting device, and trains a deep convolutional neural network by using a large amount of liquid level data, thereby carrying out heat collecting control on the heat collecting device.

Preferably, the data preparation step specifically includes the following processing:

1) processing missing data: missing values in the database may occur due to a failure of the network transmission. For the missing data value, adopting an estimation method and replacing the missing value with the sample mean value;

2) processing invalid data: due to a failure of the sensor, the liquid level data in the database has invalid values, such as negative values or values exceeding a theoretical maximum value, and the values are deleted from the database;

3) processing inconsistent data: the inconsistent data is checked by means of an integrity constraint mechanism of the database management system, and then corrected by referring to corresponding data values in the database. Preferably, in the heat collecting device, the heat collecting liquid level with high outdoor temperature is always higher than the heat collecting liquid level with low outdoor temperature, if the heat collecting liquid level with high outdoor temperature in the database is lower than the heat collecting liquid level with low outdoor temperature, a user error prompt can be given by means of a check constraint mechanism in an integrity constraint of the database management system, and the user replaces the liquid level data value of the inconsistent data with the pre-estimated data or the critical liquid level data value of the corresponding liquid level according to the error prompt.

Preferably, the step of generating a data set comprises the steps of:

1) generating training set data and labels: and reading the liquid level data values of the corresponding working conditions from the database according to different operating conditions of the heat collecting device, and generating training set data and working condition labels under various working condition states. Preferably, in a specific application, the operating condition is divided into 1, the heat collection device collects heat, the label is 2, and the heat collection device does not collect heat. Automatically generating working condition labels by a program according to different working conditions;

preferably, the data includes data indicating that the evaporation of the fluid inside the heat collecting device is substantially saturated under different operating conditions. The working condition comprises at least one of season, weather, time and the like.

2) Generating detection set data and labels: and reading the liquid level data values of the corresponding working conditions from the database according to different operating conditions of the heat collecting device, and generating detection set data and working condition labels under various working condition states. The working condition labels are the same as the working condition labels of the training set and are automatically generated by a program according to the running working conditions.

As the optimization, whether the evaporation of the fluid in the heat collecting device reaches the saturation or not can be judged, the label is 1, the saturation is reached, and the label is 2.

The network training comprises the following specific steps:

1) reading a group of training set data d, wherein the size of the training set data d is [ Mx 1 xN ], M represents the size of a training batch, and 1 xN represents one-dimensional training data;

2) and performing a first convolution operation on the read training data to obtain a feature map t. Initializing coefficients of a convolution kernel g, and setting the size of g as { P × 1 × Q ], wherein P represents the number of convolution kernels, [1 × Q ] represents the size of the convolution kernels, the obtained convolution result is t ═ Σ (d × g), and the size of a feature map is [ M × 1 × N × Q ];

3) and performing maximum pooling operation on the feature map iota obtained by the convolution operation to obtain a feature map z. Initializing a pooling coefficient, wherein the given pooling step length is p, the size of a pooling window is k, the size of a finally obtained feature map z is [ Mx1 x (N/p). times.Q ], and the data dimensionality is reduced in a pooling process;

4) repeating the steps 2) -3), repeatedly performing convolution and pooling operation to obtain a feature vector x, and finishing the feature extraction process of the convolutional neural network;

5) initializing a weight matrix w and an offset b of the fully-connected network, sending the extracted eigenvector x into the fully-connected network, and calculating with the weight matrix w and the offset b to obtain a network output y ═ Σ (w × x + b);

6) subtracting the training set label l from the output y obtained by the network to obtain a network error e which is y-l, carrying out derivation on the network error, and sequentially correcting the weight w, the bias b, the pooling coefficients of each layer and the convolution coefficients of each layer of the fully-connected network by utilizing the derivative back propagation;

7) and repeating the process until the network error e meets the precision requirement, finishing the network training process, and generating a convolutional neural network model.

The network detection steps are as follows:

1) loading the trained convolutional neural network model, wherein the convolutional kernel coefficient, the pooling coefficient, the network weight w and the bias b of the convolutional neural network are trained;

2) and inputting the detection data set into the trained convolutional neural network, and outputting a detection result. The type of run can be determined, for example, based on the output tag. For example, 1 represents collector hot, 2 represents collector hot, etc.

The invention provides a new method for controlling the heat collection of the heat collection device, which makes full use of the online monitoring data of the concentrated heat collection device, and has the advantages of high detection speed and low cost.

The invention organically integrates the data processing technology, machine learning and pattern recognition theory, and can improve the accuracy of the operation of the heat collecting device.

The working process of the specific convolutional neural network is as follows:

1) inputting a group of training set data d, wherein the size of the training set data d is [ M multiplied by 1 multiplied by N ], M represents the size of the training batch, and 1 multiplied by N represents one-dimensional training data;

2) and performing a first convolution operation on the read training data to obtain a feature map t. Initializing coefficients of a convolution kernel g, and setting the size of g as [ P × 1 × Q ], wherein P represents the number of convolution kernels, [1 × Q ] represents the size of the convolution kernels, the obtained convolution result is t ═ Σ (d × g), and the size of a feature map is [ M × 1 × N × Q ];

3) and performing maximum pooling operation on the feature map t obtained by the convolution operation to obtain a feature map z. Initializing a pooling coefficient, setting a pooling step length as p, setting a pooling window size as k, and reducing data dimensionality in a pooling process, wherein the size of a finally obtained feature map z is [ MX 1X (N/p) XQ ];

4) repeating the steps 2) -3), and repeatedly performing convolution and pooling operation to obtain a feature vector;

through the mode recognition of the liquid level detected by the liquid level sensing element, the evaporation of the fluid in the interior is basically saturated, and the volume of the fluid in the interior is not changed greatly basically. So that the fluid undergoes volume reduction to thereby realize vibration. When the liquid level is reduced to a certain degree, the internal fluid starts to enter a stable state again, and the fluid needs to be heated to evaporate and expand again, so that the heat collection tube box needs to be started to heat.

Fourthly, automatically adjusting vibration based on speed

Preferably, a speed sensing element is arranged in the free end of the tube bundle and used for detecting the flow speed of fluid in the free end of the tube bundle, the speed sensing element is in data connection with the controller, the speed data are stored in a database in real time, a one-dimensional deep convolutional neural network is adopted to extract data characteristics and perform mode identification, and therefore whether the heat collection tube box is subjected to heat collection or not is controlled so as to remove scale.

The speed-based pattern recognition comprises the following steps:

1. preparing data: and rechecking and checking the speed data of the heat collection tube box 8 in the database, and correcting missing data, invalid data and inconsistent data to ensure the correctness and the logical consistency of the data.

2. Generating a data set: the prepared data is divided into training set/training set labels, detection set/detection set labels.

3. Network training: inputting the training set data into a convolution neural network, continuously performing convolution and pooling to obtain a characteristic vector, and sending the characteristic vector into a full-connection network. And obtaining a network error by calculating the output of the network and a training set label, and continuously correcting the network weight, the bias, the convolution coefficient and the pooling coefficient by using an error back propagation algorithm to enable the error to meet the set precision requirement, thereby finishing the network training.

4. Network detection: and inputting the detection set data into the trained network, and outputting a detection result label.

5. The heat collector operates: and controlling whether heat is collected for the heat collecting tube box or not according to the detection result label so as to remove the scale.

The invention provides a novel system for intelligently controlling vibration descaling of a heat collecting device, which is based on a theoretical method of machine learning and pattern recognition, utilizes speed data with time correlation in a centralized heat collecting device real-time monitoring system according to different operating conditions of the heat collecting device, designs a corresponding working mode (heating mode/non-heating mode) of the heat collecting device, and trains a deep convolutional neural network by using a large amount of speed data so as to control heat collection of the heat collecting device.

Preferably, the data preparation step specifically includes the following processing:

1) processing missing data: missing values in the database may occur due to a failure of the network transmission. For the missing data value, adopting an estimation method and replacing the missing value with the sample mean value;

2) processing invalid data: the speed data in the database is invalid due to a failure of the sensor, such as negative values or exceeding a theoretical maximum value, and the values are deleted from the database;

3) processing inconsistent data: the inconsistent data is checked by means of an integrity constraint mechanism of the database management system, and then corrected by referring to corresponding data values in the database. Preferably, in the heat collecting device, the heat collecting speed with high outdoor temperature is higher than the heat collecting speed with low outdoor temperature, if the heat collecting speed with high outdoor temperature in the database is lower than the heat collecting speed with low outdoor temperature, a user error prompt can be given by means of a check constraint mechanism in an integrity constraint of the database management system, and the user replaces the speed data value of the inconsistent data with the estimated data or the critical speed data value of the corresponding speed according to the error prompt.

Preferably, the step of generating a data set comprises the steps of:

1) generating training set data and labels: and reading speed data values of corresponding working conditions from the database according to different operating conditions of the heat collecting device, and generating training set data and working condition labels under various working condition states. Preferably, in a specific application, the operating condition is divided into 1 for heat collection by the heat collection device, and 2 for no heat collection by the heat collection device. Automatically generating working condition labels by a program according to different working conditions;

preferably, the data includes data indicating that the evaporation of the fluid inside the heat collecting device is substantially saturated under different operating conditions. The working condition comprises at least one of season, weather, time and the like.

2) Generating detection set data and labels: and reading speed data values of corresponding working conditions from the database according to different operating conditions of the heat collecting device, and generating detection set data and working condition labels under various working condition states. The working condition labels are the same as the working condition labels of the training set and are automatically generated by a program according to the running working conditions.

As the optimization, whether the evaporation of the fluid in the heat collecting device reaches the saturation or not can be judged, the label is 1, the saturation is reached, and the label is 2.

The network training comprises the following specific steps:

1) reading a group of training set data d, wherein the size of the training set data d is [ Mx 1 xN ], M represents the size of a training batch, and 1 xN represents one-dimensional training data;

2) and performing a first convolution operation on the read training data to obtain a feature map t. Initializing coefficients of a convolution kernel g, and setting the size of g as [ P × 1 × Q ], wherein P represents the number of convolution kernels, [1 × Q ] represents the size of the convolution kernels, the obtained convolution result is t ═ Σ (d × g), and the size of a feature map is [ M × 1 × N × Q ];

3) and performing maximum pooling operation on the feature map t obtained by the convolution operation to obtain a feature map z. Initializing a pooling coefficient, wherein the given pooling step length is p, the size of a pooling window is k, the size of a finally obtained feature map z is [ Mx1 x (N/p). times.Q ], and the data dimensionality is reduced in a pooling process;

4) repeating the steps 2) -3), repeatedly performing convolution and pooling operation to obtain a feature vector x, and finishing the feature extraction process of the convolutional neural network;

5) initializing a weight matrix w and a bias b of the fully-connected network, sending the extracted eigenvector x into the fully-connected network, and calculating with the weight matrix w and the bias b to obtain a network output y-sigma (wxx + b);

6) subtracting the training set label l from the output y obtained by the network to obtain a network error e which is y-l, carrying out derivation on the network error, and sequentially correcting the weight w, the bias b, the pooling coefficients of each layer and the convolution coefficients of each layer of the fully-connected network by utilizing the derivative back propagation;

7) and repeating the process until the network error e meets the precision requirement, finishing the network training process, and generating a convolutional neural network model.

The network detection steps are as follows:

1) loading the trained convolutional neural network model, wherein the convolutional kernel coefficient, the pooling coefficient, the network weight w and the bias b of the convolutional neural network are trained;

2) and inputting the detection data set into the trained convolutional neural network, and outputting a detection result. The type of run can be determined, for example, based on the output tag. For example, 1 represents collector hot, 2 represents collector hot, etc.

The invention provides a new method for controlling the heat collection of the heat collection device, which makes full use of the online monitoring data of the concentrated heat collection device, and has the advantages of high detection speed and low cost.

The invention organically integrates the data processing technology, machine learning and pattern recognition theory, and can improve the accuracy of the operation of the heat collecting device.

The working process of the specific convolutional neural network is as follows:

1) inputting a group of training set data d, wherein the size of the training set data d is [ M multiplied by 1 multiplied by N ], M represents the size of the training batch, and 1 multiplied by N represents one-dimensional training data;

2) and performing a first convolution operation on the read training data to obtain a feature map t. Initializing coefficients of a convolution kernel g, and setting the size of g as [ P × 1 × Q ], wherein P represents the number of convolution kernels, [1 × Q ] represents the size of the convolution kernels, the obtained convolution result is t ═ Σ (d × g), and the size of a feature map is [ M × 1 × N × Q ];

3) and performing maximum pooling operation on the feature map t obtained by the convolution operation to obtain a feature map z. Initializing a pooling coefficient, setting a pooling step length as p, setting a pooling window size as k, and reducing data dimensionality in a pooling process, wherein the size of a finally obtained feature map z is [ MX 1X (N/p) XQ ];

4) repeating the steps 2) -3), and repeatedly performing convolution and pooling operation to obtain a feature vector;

in this case, the internal fluid is relatively stable, and the tube bundle is deteriorated in vibration at this time, and therefore, it is necessary to adjust the internal fluid so as to vibrate the internal fluid for descaling. So that the fluid undergoes volume reduction to thereby realize vibration. When the speed is reduced to a certain degree, the internal fluid starts to enter a stable state again, and the fluid needs to be heated to be evaporated and expanded again, so that the heat collection tube box needs to be started to heat. Preferably, the heat collecting tube box is heated or not heated by rotating the reflector. When heat collection is required, the reflecting surface of the reflector faces the sun, and when heat collection is not required, the reflecting surface of the reflector does not face the sun. This can be achieved by means of a rotating mirror of a conventional solar tracking system, which need not be described in detail here.

Preferably, another embodiment may be adopted, in which the operation of whether to collect heat or not to collect heat is performed on the heat collecting tube box in a manner of whether the heat collecting tube box is located at the focal point of the reflector. When heat collection is required, the heat collection tube box is positioned at the focus of the reflector, and when heat collection is not required, the heat collection tube box is not positioned at the focus of the reflector.

As shown in fig. 1, the reflector 16 is divided into two parts along the middle, a first part 161 and a second part 162, and a first part 161 and a second part 162, as shown in fig. 2. The support member 17 is a support column disposed at a lower portion of the heat collecting tube box 8, and the hydraulic telescopic rods 171 and 172 extend from the support column and are connected to the first and second portions 161 and 162, respectively. For driving the first and second parts apart or together. When the first part and the second part are combined together, the reflector 16 forms a complete reflector, and the heat collecting tube box is located at the focal position of the reflector 16 for collecting heat from the heat collecting tube box. When the first and second parts are separated, the heat collecting tube box is not located at the focus of the first and second parts, and is not heated.

Preferably, the hydraulic telescopic rod is connected with an actuator, the actuator drives the hydraulic telescopic rod to extend and retract, and the telescopic rod extends and retracts to change the position of the focal point of the reflecting mirror.

The hydraulic telescopic rod is connected to the support 17 in a pivoting manner.

As a modified example, as shown in fig. 2-3 and 2-4. The heat collecting device comprises a right hydraulic pump 24, a left hydraulic pump 25, a right hydraulic device 26 and a left hydraulic device 27, telescopic rods 35 and 36 are arranged at the upper parts of the right hydraulic device 26 and the left hydraulic device 27 and are connected to the lower parts of a second part 162 and a first part 161 in a pivoting mode, and the right hydraulic pump 24 and the left hydraulic pump 25 respectively drive the right hydraulic device 26 and the left hydraulic device 27 to ascend and descend.

Preferably, the device further comprises a right support bar 28 and a left support bar 29, the right support bar 28 and the left support bar 29 comprising a first part and a second part, the first part being located at the lower part, the lower end of the first part being pivotally connected to the support bar 17, the second part being a telescopic bar, the upper end of the telescopic bar being pivotally connected to the first part 162 and the second part 162. The telescoping rod may telescope within the first member. The right and left support bars 28 and 29 serve to support the mirror so that the mirror is maintained at a lower corresponding position. For example, when the first and second portions of the reflector are combined, the first and second portions are supported by the right and left support rods 28 and 29 to be maintained at corresponding positions, so that the heat collecting tube box 8 is located at the focal point of the reflector.

Preferably, the first member is a rod having an opening in the middle thereof, such that the telescopic rod is able to telescope within the first member.

Preferably, the right support rod 28 and the left support rod 29 are also hydraulically operated, and hydraulic pumps are separately provided, and the first component is a hydraulic device that drives the telescopic rods to extend and retract. The specific structure is similar to the right hydraulic device 26 and the left hydraulic device 27.

Fig. 7 shows a specific structure of the hydraulic pump. As shown in fig. 7, the hydraulic pump includes an eccentric 30, a check valve 31, a cylinder 32, a stop valve 33, and a plunger 34, wherein the eccentric 30 is connected with the plunger 34. The plunger 34 is disposed within a plunger cavity 38, the plunger cavity 38 being in communication with the hydraulic pump. The hydraulic pump comprises a cavity, a telescopic rod is arranged on the upper portion of the cavity, a plate-shaped structure 39 with the same inner diameter as the cavity of the hydraulic pump is arranged at the lower end of the telescopic rod, a rod-shaped structure 40 extends out of the middle of the plate-shaped structure, and the rod-shaped structure 40 extends out of the cavity of the hydraulic pump and is connected with a reflector.

The lower part of the cavity is provided with an oil cylinder 32, two one-way valves 31 are arranged between the oil cylinder and the telescopic rod, and liquid enters the upper part from the oil cylinder at the lower part to push the telescopic rod to move upwards; the two one-way valves are respectively arranged at the upper part and the lower part of the position where the plunger cavity is communicated with the hydraulic pump; a partition wall 37 is arranged on one side (far away from the position where the plunger cavity is communicated with the hydraulic pump) of the two check valves 31, a certain distance is reserved between the partition wall 37 and one side wall of the cavity opposite to the position where the plunger cavity is communicated with the hydraulic pump, and a stop valve 33 is arranged. By opening of the shut-off valve for liquid to flow from above into the lower cylinder 32.

When the reflector is lifted to stop the device from collecting heat, the right hydraulic pump 24 and the left hydraulic pump 25 can be driven, and the eccentric wheel 30 drives the plunger 34 to reciprocate. When the plunger 34 moves to the right, vacuum is generated in the cylinder body, and oil is sucked through the one-way valve, so that the oil suction process is completed. When the plunger 34 moves to the left, the oil in the cylinder is input into the hydraulic system through the check valve 31. The cam is continuously rotated to raise the mirror.

When the reflector is lowered to start heat collection, the stop valve 33 can be opened, oil on the upper part of the hydraulic system flows back to the oil cylinder, and then the reflector returns to the original position under the action of gravity.

Of course, hydraulic pumps are also a well-established prior art, and the embodiment of fig. 7 is presented for simplicity only and is not intended to be limiting. All hydraulic pumps of the prior art can be used.

The descaling time may preferably be performed after the solar collector is operated for a certain period of time. Preferably when the heat collecting effect is deteriorated.

Preferably, the heat release pipes of the left heat release pipe group are distributed around the axis of the left upper pipe, and the heat release pipes of the right heat release pipe group are distributed around the axis of the right upper pipe. The left upper pipe and the right upper pipe are arranged as circle centers, so that the distribution of the heat release pipes can be better ensured, and the vibration and the heating are uniform.

Preferably, the left heat-releasing tube group and the right heat-releasing tube group are both plural.

Preferably, the left heat-releasing tube group and the right heat-releasing tube group are mirror-symmetrical along a plane on which a vertical axis of the heat collecting tube box is located. Through such setting, can make the heat release pipe distribution of heat transfer more reasonable even, improve the heat transfer effect.

Preferably, the heat collecting tube box 8 has a flat tube structure. The heat absorption area is increased by arranging the flat tube structure. So that the heat collecting tube box 8 can be ensured to be positioned at the focal point of the reflector even if the installation position is a little remote.

Preferably, the left heat-releasing tube group 11 and the right heat-releasing tube group 12 are arranged in a staggered manner in the horizontal extending direction, as shown in fig. 5. Through the staggered distribution, can make to vibrate on different length and release heat and scale removal for the vibration is more even, strengthens heat transfer and scale removal effect.

Preferably, a reflecting mirror 16 is provided at a lower portion of the heat collecting device, the heat collecting tube box is located at a focal position of the reflecting mirror 16, and the left and right heat releasing tube groups are located in the fluid passage. Thereby forming a solar energy collection system.

Preferably, a support 17 is included, and the support 17 supports the heat collecting device.

Preferably, a fluid channel is included within which fluid flows. As shown in fig. 2, the heat collecting tube box 8 is located at a lower end of the fluid passage, as shown in fig. 2. The upper left tube 21, the upper right tube 22, the left heat-releasing tube group 11, and the right heat-releasing tube group 12 are provided in the fluid passage, and heat the fluid in the fluid passage by releasing heat.

Preferably, the flow direction of the fluid is the same as the direction in which the left and right upper tubes 21 and 22 and the heat collecting tube box 8 extend. Through such arrangement, the fluid scours the heat release pipe set when flowing, especially the free end of the heat release pipe set, so that the free end vibrates, heat transfer is enhanced, and the descaling effect is achieved.

Preferably, the heat release tube group 1 is provided in plural (for example, on the same side (left side or right side)) along the flow direction of the fluid in the fluid passage, and the tube diameter of the heat release tube group 1 (for example, on the same side (left side or right side)) along the flow direction of the fluid in the fluid passage becomes larger.

Along the flowing direction of the fluid, the temperature of the fluid is continuously increased, so that the heat exchange temperature difference is continuously reduced, and the heat exchange capacity is increased more and more. Through the pipe diameter grow of heat release nest of tubes, can guarantee that more steam passes through upper portion and gets into heat release nest of tubes, guarantee along fluid flow direction because the steam volume is big and the vibration is effectual to make whole heat transfer even. The distribution of steam in all heat release pipe groups is even, further strengthens heat transfer effect for the whole vibration effect is even, and the heat transfer effect increases, further improves heat transfer effect and scale removal effect.

Preferably, the heat release pipe diameter of the heat release pipe group (for example, the same side (left side or right side)) is increased along the flowing direction of the fluid in the fluid passage.

Through so setting up, avoid the fluid all to carry out the heat transfer at front, and the heat transfer of messenger increases to the rear portion as far as possible to form the heat transfer effect of similar countercurrent. Experiments show that better heat exchange effect and descaling effect can be achieved by adopting the structural design.

Preferably, the heat release pipe groups on the same side (left side or right side) are arranged in plurality along the flowing direction of the fluid in the fluid channel, and the interval between the adjacent heat release pipe groups on the same side (left side or right side) is gradually reduced from the top to the bottom. The specific effect is similar to the effect of the previous pipe diameter change.

Preferably, the spacing between the heat release pipe groups on the same side (left side or right side) along the flowing direction of the fluid in the fluid channel is increased in a decreasing amplitude. The specific effect is similar to the effect of the previous pipe diameter change.

In tests it was found that the volume, the distance of the upper left tube 21 and the upper right tube 22 and the volume of the collection tank can have an influence on the heat exchange efficiency and the homogeneity. If the volume undersize of thermal-arrest case, lead to the steam overheated, the heat can't in time be transmitted to exothermic pipe and upper left pipe upper right side, the volume is too big, lead to the steam condensation too fast, also can't transmit, upper left pipe 21 with the reason, upper right pipe 22's volume must be suitable for with thermal-arrest case volume collocation mutually, otherwise can lead to the steam condensation too fast or too slow, all can lead to the heat transfer condition to worsen, upper left pipe 21, distance also can lead to heat exchange efficiency too poor between the upper right pipe 22, the distance is too little, then exothermic pipe distributes too closely, also can influence heat exchange efficiency, upper left pipe 21, distance also need and thermal-arrest distance collocation between the case be suitable for between the upper right pipe 22 mutually, otherwise distance between them can influence the volume of the liquid or the steam that holds, then can exert an influence to the vibration of free end, thereby influence the heat transfer. The volumes of the upper left tube 21 and the upper right tube 22, the distance and the volume of the heat collecting tank have a certain relation.

The invention provides an optimal size relation summarized by numerical simulation and test data of a plurality of heat pipes with different sizes. Starting from the maximum heat exchange amount in the heat exchange effect, nearly 200 forms are calculated. The dimensional relationship is as follows:

the volumes of the upper left tube 21 and the upper right tube 22 are respectively V1 and V2, the volume of the heat collection box is V3, and the included angle formed between the midpoint of the bottom of the heat collection box body and the circle centers of the upper left tube 21 and the upper right tube 22 is A, so that the following requirements are met:

(V1+V2)/V3＝a-b*sin(A/2)²-c sin (a/2); where a, b, c are parameters, sin is a triangular sine function,

0.8490< a <0.8492, 0.1302< b <0.1304, 0.0020< c < 0.0022; preferably, a is 0.8491, b is 0.1303, and c is 0.0021.

Preferably, an included angle A formed between the midpoint of the bottom of the heat collection box and the circle centers of the upper left tube 21 and the upper right tube 22 is 40-120 degrees (angle), and preferably 80-100 degrees (angle). Preferably, 0.72< (V1+ V2)/V3< 0.85;

the distance between the center of the upper left tube 21 and the center of the upper right tube 22 is M, the tube diameter of the upper left tube 21 and the radius of the upper right tube 22 are the same, B is B, the radius of the axis of the innermost heat radiation tube in the heat radiation tubes is N1, the radius of the axis of the outermost heat radiation tube is W2,

preferably, 35< B <61 mm; 230< M <385 mm; 69< N1<121mm, 119< W2<201 mm. Preferably, the number of the heat release pipes of the heat release pipe group is 3 to 5, preferably 3 or 4. Preferably, the radius of the heat-radiating pipe is preferably 10-40 mm; preferably 15 to 35mm, more preferably 20 to 30 mm.

Preferably, the arc between the ends of the free ends 3, 4, centered on the central axis of the left header, is 95-130 degrees, preferably 120 degrees. The same applies to the curvature of the free ends 5, 6 and the free ends 3, 4. Through the design of the preferable included angle, the vibration of the free end is optimal, and therefore the heating efficiency is optimal.

Preferably, V1 ═ V2.

In the prior application, only by considering that the distance between the center of the upper left tube 21 and the center of the upper right tube 22 is M, the tube diameters of the upper left tube 21 and the upper right tube 22 are the same, and B is B, the radius of the axis of the innermost heat radiation tube in the heat radiation tubes is N1, and the radius of the axis of the outermost heat radiation tube is W2, the volumes and the distances of the upper left tube 21 and the upper right tube 22 and the volume of the heat collection box are firstly related through an optimized relational expression, and an optimal dimensional relation is obtained. The above relation formula of the present application is a further improvement of the relation formula of the previous application, and belongs to the original invention point of the present invention through the relation formula of the volume and the included angle.

Preferably, the tube bundle of the heat-releasing tube group 1 is an elastic tube bundle. The heat exchange coefficient can be further improved by arranging the tube bundle of the heat release tube group 1 with an elastic tube bundle.

The number of the heat release pipe groups 1 is plural, and the plurality of the heat release pipe groups 1 are in a parallel structure.

Although the present invention has been described with reference to the preferred embodiments, it is not limited thereto. Various changes and modifications may be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.