阅读说明：本技术 水轮发电机组预警方法以及预警装置 (Early warning method and early warning device for hydroelectric generating set ) 是由 张培 赵训新 何葵东 王卫玉 李崇仕 侯凯 罗立军 胡蝶 姜晓峰 莫凡 金艳 于 2021-01-15 设计创作，主要内容包括：本申请实施例提供一种水轮发电机组预警方法以及预警装置,方法包括：获取机组的工况数据；获取所述工况数据下振摆监测数据最近M天的历史数据；对M天的所述历史数据进行曲线拟合,通过拟合曲线获得第1天拟合结果和第N天拟合结果；根据所述第N天拟合结果和所述第1天拟合结果的比值,判断机组振摆变化量是否显著；其中,M和N均为大于2的正整数,且N不大于M。在上述水轮发电机组预警方法的实施例中,通过对相同工况下的历史数据进行曲线拟合,得到历史变化趋势曲线,而历史变化趋势曲线表明了历史数据整体的变化趋势,避免了单点数据波动造成的影响,相较于固定的检测限值,对振摆变化的预警更为准确,从而有效提高趋势预警的准确性。(The embodiment of the application provides a hydroelectric generating set early warning method and an early warning device, wherein the method comprises the following steps: acquiring working condition data of the unit; acquiring historical data of the last M days of the vibration and oscillation monitoring data under the working condition data; performing curve fitting on the historical data of M days, and obtaining a fitting result of the 1 st day and a fitting result of the N day through fitting a curve; judging whether the unit runout variation is obvious or not according to the ratio of the fitting result on the Nth day and the fitting result on the 1 st day; wherein M and N are both positive integers greater than 2, and N is not greater than M. In the embodiment of the hydro-turbo generator set early warning method, the historical data under the same working condition are subjected to curve fitting to obtain the historical change trend curve, the historical change trend curve shows the overall change trend of the historical data, the influence caused by single-point data fluctuation is avoided, and compared with a fixed detection limit value, the early warning on the oscillation change is more accurate, so that the accuracy of the trend early warning is effectively improved.)

1. The early warning method for the hydroelectric generating set is characterized by comprising the following steps:

acquiring working condition data of the unit;

acquiring historical data of the last M days of the vibration and oscillation monitoring data under the working condition data;

performing curve fitting on the historical data of M days, and obtaining a fitting result of the 1 st day and a fitting result of the N day through fitting a curve;

judging whether the unit runout variation is obvious or not according to the ratio of the fitting result on the Nth day and the fitting result on the 1 st day;

wherein M and N are both positive integers greater than 2, and N is not greater than M.

2. The hydroelectric generating set early warning method according to claim 1, further comprising:

acquiring the vibration monitoring data of the last P days;

processing the vibration and oscillation monitoring data in P days by adopting a Mann-Kendall trend judgment algorithm;

when the trend changes and exceeds a confidence coefficient threshold value, judging that the trend changes obviously;

when the unit runout variation is judged to be obvious and the trend variation is judged to be obvious simultaneously, early warning is carried out;

wherein P is a positive integer greater than 2.

3. The hydroelectric generating set early warning method according to claim 2, wherein: the confidence threshold is greater than 1 and less than 3.

4. The hydroelectric generating set early warning method according to claim 1, wherein the determining whether the unit runout variation is significant according to the ratio of the fitting result on the nth day to the fitting result on the 1 st day comprises:

calculating a ratio a by the following formula;

a＝μ1/μn

wherein, mu 1 is the fitting result of the day 1, and mu N is the fitting result of the day N;

when the ratio a is larger than a first threshold value, performing primary early warning;

when the ratio a is larger than a second threshold value, performing secondary early warning;

the second threshold is greater than the first threshold.

5. The hydroelectric generating set early warning method according to claim 4, wherein: the first threshold value is 1.25, and the second threshold value is 1.5.

6. The hydroelectric generating set early warning method according to any one of claims 1 to 5, comprising the following steps:

acquiring the vibration monitoring data and the working condition data of the past days;

screening the steady-state working condition of the vibration monitoring data;

and after screening, calculating the daily average value of the vibration monitoring data corresponding to the working condition data.

7. The hydroelectric generating set early warning method according to claim 6, wherein the screening of the steady state operating conditions comprises:

acquiring the vibration monitoring data and the working condition data;

calculating data in a set time interval from the moment that the pointer points to the first piece of active power data;

searching a maximum power value and a minimum power value in the set time interval, and calculating power amplitudes of the maximum power value and the minimum power value;

if the power amplitude is larger than a power threshold value, screening out the data in the time interval;

if the power amplitude is not larger than the power threshold, reserving the data in the time interval;

and calculating the data of the next active power pointed by the pointer, and repeating the steps.

8. The hydroelectric generating set early warning method according to claim 6, wherein the calculating the daily average of the oscillation monitoring data corresponding to the operating condition data comprises:

grouping the vibration monitoring data in the same day according to the working condition data;

under the same working condition data, calculating a daily average value through the following formula;

xi: ith runout monitoring data; n: the number of the numerical values participating in the calculation.

9. The hydroelectric generating set early warning method according to claim 6, further comprising:

dividing a water head interval according to the water head value, and dividing a power interval according to the load power;

creating a data set corresponding to the head interval and the power interval;

and filling the vibration monitoring data into the corresponding data set.

10. The utility model provides a hydroelectric set early warning device which characterized in that includes:

the system comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is configured to acquire working condition data of a unit;

the second acquisition module is configured to acquire historical data of the last M days of the oscillation monitoring data under the working condition data;

the fitting module is configured to perform curve fitting on the historical data of M days, and obtain a day 1 fitting result and a day N fitting result through a fitting curve;

the judging module is configured to judge whether the unit runout variation is obvious or not according to the ratio of the fitting result of the Nth day and the fitting result of the 1 st day;

wherein M and N are both positive integers greater than 2, and N is not greater than M.

Technical Field

The embodiment of the application relates to the technical field of hydroelectric power generation equipment, in particular to a hydroelectric generating set early warning method and early warning device.

Background

The water turbine generator set comprises a water turbine and a generator, wherein the water turbine is power equipment for converting water flow energy into rotary mechanical energy and drives the generator to rotate to generate electric energy. In the hydroelectric generating set, the main shaft swing and the frame vibration affect the normal operation of the hydroelectric generating set, however, the vibration and the swing are caused by the aspects of design, installation, operation and the like, and cannot be completely avoided or eliminated, so the vibration and the swing need to be monitored.

In view of this, the hydroelectric generating set is generally installed with a vibration monitoring device at each monitoring point, and the purpose is to monitor the vibration data such as the main shaft throw and the frame vibration in real time during the operation of the hydroelectric generating set, and then monitor and early warn the operation state of the hydroelectric generating set according to the vibration data obtained by the vibration monitoring device. However, the main method for early warning the equipment abnormality based on the oscillation monitoring data is an out-of-limit warning method, that is, by configuring a detection limit value, when the oscillation monitoring data exceeds the detection limit value, early warning information is output to guide the water-turbine generator set to avoid the abnormal operation, so that sudden accidents are prevented, and the safe operation of the water-turbine generator set is ensured.

However, the vibration monitoring data is obviously changed under the influence of factors such as unit characteristics, unit transition process, operation conditions and environment, and therefore the early warning error is very large by using a fixed detection limit value.

Disclosure of Invention

An object of the embodiment of the application is to provide a hydroelectric generating set early warning method and an early warning device, so that the problem that early warning errors are large due to the fact that fixed detection limit values are adopted in the prior art is solved.

Based on the above purpose, in a first aspect, an embodiment of the present application provides a method for early warning of a hydroelectric generating set, including:

acquiring working condition data of the unit;

acquiring historical data of the last M days of the vibration and oscillation monitoring data under the working condition data;

performing curve fitting on the historical data of M days, and obtaining a fitting result of the 1 st day and a fitting result of the N day through fitting a curve;

judging whether the unit runout variation is obvious or not according to the ratio of the fitting result on the Nth day and the fitting result on the 1 st day;

wherein M and N are both positive integers greater than 2, and N is not greater than M.

In the embodiment of the hydro-turbo generator set early warning method, the historical data under the same working condition are subjected to curve fitting to obtain the historical change trend curve, the historical change trend curve shows the overall change trend of the historical data, the influence caused by single-point data fluctuation is avoided, and compared with a fixed detection limit value, the early warning on the oscillation change is more accurate, so that the accuracy of the trend early warning is effectively improved.

In one possible embodiment, the method further comprises:

acquiring the vibration monitoring data of the last P days;

processing the vibration and oscillation monitoring data in P days by adopting a Mann-Kendall trend judgment algorithm;

when the trend changes and exceeds a confidence coefficient threshold value, judging that the trend changes obviously;

when the unit runout variation is judged to be obvious and the trend variation is judged to be obvious simultaneously, early warning is carried out;

wherein P is a positive integer greater than 2.

In one possible embodiment, the confidence threshold is greater than 1 and less than 3.

In a possible implementation manner, the determining whether the variation of the unit runout is significant according to the ratio of the fitting result of the nth day to the fitting result of the 1 st day includes:

calculating a ratio a by the following formula;

a＝μ1/μn

wherein, mu 1 is the fitting result of the day 1, and mu N is the fitting result of the day N;

when the ratio a is larger than a first threshold value, performing primary early warning;

when the ratio a is larger than a second threshold value, performing secondary early warning;

the second threshold is greater than the first threshold.

In one possible embodiment, the first threshold is 1.25 and the second threshold is 1.5.

In one possible embodiment, the method comprises the following steps:

acquiring the vibration monitoring data and the working condition data of the past days;

screening the steady-state working condition of the vibration monitoring data;

and after screening, calculating the daily average value of the vibration monitoring data corresponding to the working condition data.

In one possible embodiment, the steady state condition screening includes:

acquiring the vibration monitoring data and the working condition data;

calculating data in a set time interval from the moment that the pointer points to the first piece of active power data;

searching a maximum power value and a minimum power value in the set time interval, and calculating power amplitudes of the maximum power value and the minimum power value;

if the power amplitude is larger than a power threshold value, screening out the data in the time interval;

if the power amplitude is not larger than the power threshold, reserving the data in the time interval;

and calculating the data of the next active power pointed by the pointer, and repeating the steps.

In one possible embodiment, the calculating the daily average of the oscillation monitoring data according to the operating condition data includes:

grouping the vibration monitoring data in the same day according to the working condition data;

under the same working condition data, calculating a daily average value through the following formula;

xi: ith runout monitoring data; n: the number of the numerical values participating in the calculation.

In one possible embodiment, the method further comprises:

dividing a water head interval according to the water head value, and dividing a power interval according to the load power;

creating a data set corresponding to the head interval and the power interval;

and filling the vibration monitoring data into the corresponding data set.

In a second aspect, an embodiment of the present application provides a hydroelectric set early warning device, include:

the system comprises a first acquisition module, a second acquisition module and a control module, wherein the first acquisition module is configured to acquire working condition data of a unit;

the second acquisition module is configured to acquire historical data of the last M days of the oscillation monitoring data under the working condition data;

the early warning module is configured to perform curve fitting on the historical data of M days, and obtain a fitting result of the 1 st day and a fitting result of the N day through a fitting curve;

the judging module is configured to judge whether the unit runout variation is obvious or not according to the ratio of the fitting result of the Nth day and the fitting result of the 1 st day;

wherein M and N are both positive integers greater than 2, and N is not greater than M.

The apparatus of this embodiment may be configured to implement the technical solution of the first aspect, and the implementation principle and the technical effect are similar, which are not described herein again.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only the embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a first flowchart of an early warning method for a hydroelectric generating set according to an embodiment of the present application;

FIG. 2 is a flow chart II of a hydroelectric generating set early warning method provided by the embodiment of the present application

Fig. 3 is a third flowchart of an early warning method for a hydroelectric generating set according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of a hydroelectric generating set early warning device provided by the embodiment of the application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The embodiment of the application provides a hydroelectric generating set early warning method, as shown in fig. 1, the method comprises the following steps:

step S10: acquiring working condition data of the unit;

the working condition data of the unit usually comprises load power and a water head value, and can be obtained through a monitoring system of the hydroelectric generating set. The unit runout change under different working conditions has different characteristics, the historical runout data under the same working conditions has higher referential performance, and the early warning accuracy of the unit runout change is higher, so that the working condition data should be obtained firstly in the early warning method, and the historical data can be conveniently and specifically obtained in the subsequent process.

Step S20: acquiring historical data of the last M days of the oscillation monitoring data under the working condition data;

according to the above description, the unit runout changes under different working conditions have different characteristics, the historical runout data under the same working conditions have higher referential property, and the warning accuracy for the unit runout changes is higher.

M is a positive integer greater than 2, for example, M can be 7, and the larger M is, the more historical data is acquired, and the more historical data can make the early warning result more accurate.

Step S30: performing curve fitting on the historical data of M days, and obtaining a fitting result of the 1 st day and a fitting result of the N day through fitting a curve;

after the historical data of M days are obtained, curve fitting can be carried out on the historical data of M days, a historical change trend curve related to unit runout monitoring data is obtained after curve fitting, and a day 1 fitting result and a day N fitting result can be obtained according to the historical change trend curve. The fitting result of the 1 st day and the fitting result of the N th day are obtained through the historical change trend curve, so that the influence caused by data fluctuation can be reduced, and the change trend of the historical data is reflected integrally. Wherein N is a positive integer greater than 2, and N is not greater than M. In this embodiment, when M is 7, N also takes 7.

It should be noted that the curve here also includes the special case of a straight line, i.e. the fitting result may also be a straight line.

Step S40: and judging whether the unit runout variation is obvious or not according to the ratio of the fitting result of the Nth day to the fitting result of the 1 st day.

After the day 1 fitting result and the day N fitting result are obtained through step S30, comparative analysis may be performed, and a ratio of the day N fitting result to the day 1 fitting result is set as a, where a may be calculated according to the following formula (1):

a＝μ1/μn (1)

wherein, mu 1 is the fitting result of the 1 st day, and mu N is the fitting result of the Nth day.

And setting a significant threshold representing 'significant', judging that the unit runout variation is significant when a is greater than the significant threshold, and judging that the unit runout variation is normal when a is not greater than the significant threshold. The significance threshold may be set according to the specific hydroelectric generating set and may also be set with reference to relevant standards, for example, in the assessment of mechanical vibration of the hydroelectric power plant and the energy storage pump station set in GB/T32584-2016, the "25% change in vibration amplitude, whether increasing or decreasing, relative to a reference value should be considered significant", so that the significance threshold may be set with reference to "25%".

In the embodiment of the hydro-turbo generator set early warning method, the historical data under the same working condition are subjected to curve fitting to obtain the historical change trend curve, the historical change trend curve shows the overall change trend of the historical data, the influence caused by single-point data fluctuation is avoided, and compared with a fixed detection limit value, the early warning on the oscillation change is more accurate, so that the accuracy of the trend early warning is effectively improved.

Optionally, in order to further refine the early warning result, the condition that the unit runout variation is significant is further subdivided, that is, the ratio a is subjected to segment early warning, and when the ratio a is greater than a first threshold, the first-stage early warning is defined; and when the ratio a is larger than a second threshold value, defining the second-level early warning, wherein the second threshold value is larger than the second threshold value.

According to the ratio a calculated by the formula (1), whether the ratio a is in the first-stage early warning and the second-stage early warning can be judged, and when the ratio a is in the first-stage early warning or the second-stage early warning, a judgment result is output. Illustratively, the first threshold may be set to 1.25 and the second threshold may be set to 1.5.

In one possible embodiment, as shown in fig. 2, the method further comprises:

step S50: acquiring the vibration monitoring data of the last P days;

the vibration monitoring data is obtained by vibration monitoring devices configured at monitoring points of the unit, and comprises vibration parameters such as main shaft throw and frame vibration. The P day is a positive integer greater than 2, for example, P may be 3, and the larger P is, the more the acquired runout monitoring data is, and the more the runout monitoring data makes the early warning result more accurate.

Step S60: processing the vibration and oscillation monitoring data of the P day by adopting a Mann-Kendall trend judgment algorithm;

the Mann-Kendall trend determination algorithm is a non-parametric test, which does not require data to obey a specific distribution (such as gaussian distribution and the like), allows data to be missing, and is a very common and practical trend test method. And the pendulum monitoring data of P days are processed by adopting a Mann-Kendall trend judgment algorithm, so that monotonous trend verification can be realized.

Step S70: when the trend changes and exceeds a confidence coefficient threshold value, judging that the trend changes obviously;

when the trend changes beyond the confidence threshold, the oscillation monitoring data of day P shows a clear ascending trend. The confidence threshold may refer to a value in a range of 1-3, for example, in the present embodiment, the confidence threshold is set to 2.

Step S80: and when the unit runout variation is judged to be obvious and the trend variation is judged to be obvious simultaneously, early warning is carried out.

Namely, the early warning judgment is carried out simultaneously by two different methods, and when the early warning is judged to occur by the two methods (the unit runout variation is obvious and the trend variation is obvious), the early warning output is carried out, so that the false warning rate is reduced, and the accuracy of the trend early warning is effectively improved.

According to the steps, the early warning of the water-turbine generator set early warning method depends on the corresponding relation between the working condition data and the runout monitoring data, and for convenience of data processing and early warning, as shown in fig. 3, the water-turbine generator set early warning method provided by the embodiment of the application further comprises the following steps:

step S100: acquiring vibration oscillation monitoring data and working condition data of a plurality of days in the past;

the obtaining of the oscillation monitoring data and the operating condition data may refer to the above description, and is not described herein again.

Step S200: screening steady-state working conditions of the vibration and oscillation monitoring data;

the water-turbine generator set comprises a stable working condition state and an unstable working state in the working process, under the stable working condition state, the working condition data of the water-turbine generator set are in the stable state, and the load power fluctuates within a preset range. Under the unsteady operating mode state, for example start-up stage and load adjustment transition stage etc. the operating mode data of hydroelectric set is in the unsteady state, and load power fluctuation range is great, and the runout monitoring data change is great under this kind of circumstances, leads to the wrong report of trend early warning easily, consequently need carry out steady state screening, will be in the runout monitoring data deletion of unsteady operating mode state, only remain the data that the unit produced under the steady operating mode state to reduce the false alarm rate.

Optionally, the step of screening the steady-state operating condition includes:

acquiring all data in a calculation time period, calculating that a pointer points to a first piece of active power data, taking 10min of active power data backwards, searching a maximum power value and a minimum power value, and calculating power amplitudes of the maximum power value and the minimum power value; if the power amplitude is greater than 10MW, the data is screened out within 10 minutes. If the MW is less than 10MW, the data in the time interval is reserved. And the calculation pointer points to the next active moment, and the calculation screening is repeated until the data screening in the time period is finished.

Wherein, 10min is the setting time interval, and 10MW is the power threshold value, and setting time interval and power threshold value are not limited to this, can confirm according to hydroelectric set's actual conditions.

Step S300: and after screening, calculating the daily average value of the vibration monitoring data according to the working condition data.

Grouping the vibration monitoring data in the same day according to working condition data, and calculating a daily average value through the following formula (2) under the same working condition data;

xi: ith runout monitoring data. N: the number of the numerical values participating in the calculation.

Further, the hydro-turbo generator set early warning method further comprises the step of constructing a working condition grid, and the step comprises the following steps:

dividing a water head interval according to the water head value, and dividing a power interval according to the load power;

creating a data set corresponding to a head interval and a power interval;

and filling the vibration monitoring data into the corresponding data set.

According to the description, the unit runout change under different working conditions has different characteristics, the historical runout data under the same working conditions is more referential, and the early warning accuracy of the unit runout change is higher. The working condition data of the unit comprises load power and a water head value, however, the specific value of the working condition data is less in historical data, and therefore the referential performance is reduced.

When the working condition data of the unit is in a certain range, the vibration and swing change characteristics of the unit tend to be the same. Therefore, data grouping is carried out in the embodiment of the application in a mode of constructing the working condition grids so as to facilitate data management and trend early warning, each data set in the steps corresponds to the working condition grids of a certain water head interval and a certain power interval, and the requirement that the data of the water head interval and the power interval corresponding to the data set are stored in the data set is met.

The power interval may be defined according to the power range or rated power in the operating condition data, and may be, for example, 4% of the rated power, that is, 4% Pe.

In one example, the specific dividing method is that the water head is divided into one grid every 1 meter between the minimum water head value and the maximum water head value; dividing the load power into one lattice in a vibration area, dividing the non-vibration area into one lattice at intervals of 10MW from the minimum power to the maximum power, and creating a working condition grid corresponding to a water head lattice and a power lattice; and filling the oscillation monitoring data into the corresponding working condition grids according to the corresponding water head values and the load power.

Under the condition of having the working condition grids, acquiring historical data under the working condition data becomes acquiring historical data in a data set corresponding to the working condition data.

It should be noted that the construction of the working condition grid is not all in the early warning process of each hydro-generator set early warning method, and can be completed in the data generation process generally, so that the later calling in the subsequent early warning process is completed.

It should be noted that the method of the embodiment of the present application may be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiment, and the multiple devices interact with each other to complete the method.

In addition, specific embodiments of the present specification have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

Fig. 4 is a schematic structural diagram of a hydroelectric set early warning device that this application embodiment provided, as shown in fig. 4, the device of this embodiment can include:

the system comprises a first acquisition module 100, a second acquisition module and a control module, wherein the first acquisition module is configured to acquire working condition data of a unit;

a second obtaining module 200, configured to obtain historical data of the last M days of the oscillation monitoring data under the working condition data;

a fitting module 300 configured to perform curve fitting on the historical data for M days, and obtain a day 1 fitting result and a day N fitting result by fitting a curve;

a judging module 400 configured to judge whether the unit runout variation is significant according to a ratio of the fitting result on the nth day and the fitting result on the 1 st day;

wherein M and N are both positive integers greater than 2.

The apparatus of this embodiment may be used to implement the technical solution of the method embodiment shown in fig. 1, and the implementation principle and the technical effect are similar, which are not described herein again.

For convenience of description, the above devices are described as being functionally divided into various modules, respectively. Of course, the functions of the modules may be implemented in the same or multiple software and/or hardware when implementing the embodiments of the present application.

Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.

Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.