阅读说明：本技术 船舶动力设备监控方法、装置、设备及存储介质 (Ship power equipment monitoring method, device, equipment and storage medium ) 是由 李伟光 王梦驰 陈振宇 许正飞 钟昊 王家楠 于 2021-08-04 设计创作，主要内容包括：本申请涉及一种船舶动力设备监控方法、装置、设备及存储介质,涉及船舶监测技术领域,旨在解决船舶主机仅能够获取行驶过程中的动力设备状态参数,无法实时对动力设备的油耗进行预测的技术问题,方法包括：建立油耗初始模型；取动力设备在以往航程中的动力参数、船舶的环境参数以及船舶的实际油耗；将以往航程中的动力参数以及环境参数作为输入,实际油耗作为输出,以深度学习的方式对所述油耗初始模型进行训练,得到油耗预测模型；定期获取目标航段中的动力设备的动力参数和船舶的环境参数；在目标航段的起始点将所述动力参数和所述环境参数输入油耗预测模型,得到目标航段的油耗预测平均值。本申请具有能够对船舶的使用油耗进行预测的效果。(The application relates to a monitoring method, a monitoring device, equipment and a storage medium for ship power equipment, relates to the technical field of ship monitoring, and aims to solve the technical problem that a ship host machine can only obtain the state parameters of the power equipment in the driving process and cannot predict the oil consumption of the power equipment in real time, and the method comprises the following steps: establishing an oil consumption initial model; taking power parameters of power equipment in the past voyage, environmental parameters of a ship and actual oil consumption of the ship; taking power parameters and environment parameters in the past voyage as input, taking actual oil consumption as output, and training the oil consumption initial model in a deep learning manner to obtain an oil consumption prediction model; periodically acquiring power parameters of power equipment and environmental parameters of a ship in a target flight section; and inputting the power parameters and the environment parameters into an oil consumption prediction model at the initial point of the target flight segment to obtain the predicted average value of the oil consumption of the target flight segment. The application has the effect of predicting the use oil consumption of the ship.)

1. A method of monitoring a marine power plant, comprising:

establishing an oil consumption initial model;

acquiring power parameters of power equipment in a past voyage, environmental parameters of a ship and actual oil consumption of the ship; the power parameters at least comprise the rotating speed of an engine, the pitch of a propeller and the temperature of lubricating oil, and the environmental parameters of the ship at least comprise the wind speed, the wind direction, the water flow speed and the water flow direction;

taking power parameters and environment parameters in the past voyage as input, taking actual oil consumption as output, and training the oil consumption initial model in a deep learning manner to obtain an oil consumption prediction model;

periodically acquiring power parameters of power equipment and environmental parameters of a ship in a target flight section;

and inputting the power parameters and the environment parameters into an oil consumption prediction model at the initial point of the target flight segment to obtain the predicted average value of the oil consumption of the target flight segment.

2. The marine power plant monitoring method of claim 1, wherein: the method further comprises the following steps:

acquiring the actual speed and the actual oil consumption of the target flight segment periodically;

calculating power efficiency and a slip rate based on the power parameters of the target voyage section and the actual voyage speed;

and when the difference value between the actual oil consumption and the predicted average value of the oil consumption is greater than or equal to a fault preset value, comparing the slip rate with a slip rate warning value and outputting a navigation suggestion, wherein the navigation suggestion comprises return navigation maintenance and continuous navigation.

3. The marine power plant monitoring method of claim 2, wherein: when the difference value between the actual oil consumption and the predicted average value of the oil consumption is greater than or equal to a fault preset value, comparing the slip rate with a slip rate warning value and outputting a navigation suggestion, wherein the navigation suggestion comprises the following steps:

if the loss of slide is more than or equal to the loss of slide warning value, comparing the power parameter with the normal working range;

if the power parameters exceed the normal working range, displaying the fault of the power equipment and displaying the suggestion of return voyage maintenance;

if the power parameter is in the normal working range, displaying that the power equipment is normal and displaying a suggestion of continuing to sail;

and if the loss of slide is less than the loss of slide warning value, displaying to continue sailing.

4. The marine power plant monitoring method of claim 3, wherein: the suggestion that shows power equipment trouble and show return voyage maintenance includes:

acquiring the occupation ratio of the traveled voyage relative to the whole voyage, and if the occupation ratio exceeds the preset voyage ratio, determining the nearest maintenance point based on the satellite map and displaying the position of the maintenance point and the shortest path to the maintenance point;

and if the occupation ratio does not exceed the preset range ratio, calculating the return redundant time of the whole range, sending the fault information of the power equipment and the return redundant time to a data center and displaying the fault of the power equipment.

5. The marine power plant monitoring method of claim 3, wherein: the display power equipment is normal and displays the suggestion of continuing the navigation, and comprises the following steps:

detecting the bottom fouling degree of the ship;

if the degree of the dirty bottom exceeds a dirty bottom preset value, calculating an oil consumption increase value based on the current slip rate;

and sending the slip rate, the pollution information and the oil consumption increase value to a data center, and receiving and displaying a navigation instruction from the data center.

6. The marine power plant monitoring method of claim 1, wherein: if the loss of slide rate is less than the loss of slide rate warning value, then show to continue to navigate, include:

and re-inputting the power parameters and the environmental parameters in the current flight into the oil consumption prediction model to obtain the corrected predicted oil consumption.

7. The marine power plant monitoring method of claim 6, wherein: the step of inputting the power parameters and the environmental parameters under the current flight into the oil consumption prediction model again to obtain the corrected predicted oil consumption comprises the following steps:

when the difference value between the corrected predicted oil consumption and the actual oil consumption is still larger than the fault preset value, detecting the flow of the outlet of the oil tank;

and when the flow of the outlet of the oil tank is smaller than the actual oil consumption value, sending an alarm signal.

8. A marine power plant monitoring apparatus, the apparatus comprising:

the parameter detection module (301) is used for acquiring power parameters of the power equipment in the past voyage, environmental parameters of the ship and actual oil consumption of the ship and periodically acquiring the power parameters of the power equipment in a target voyage section and the environmental parameters of the ship;

the fuel consumption prediction module (302) is used for taking power parameters and environment parameters in the past voyage as input and taking actual fuel consumption as output, training the fuel consumption initial model in a deep learning mode to obtain a fuel consumption prediction model, and inputting the power parameters and the environment parameters into the fuel consumption prediction model at the starting point of a target voyage section to obtain a fuel consumption prediction average value of the target voyage section;

the power efficiency measuring and calculating module (303) is used for periodically acquiring the actual navigational speed and the actual oil consumption of the target navigation section, and measuring and calculating the engine efficiency and the slip loss rate based on the current engine parameters and the actual navigational speed of the ship;

the data analysis module (304) compares the slip rate with a slip rate warning value and outputs an operation suggestion when the difference value between the actual oil consumption value and the predicted oil consumption value is larger than or equal to a fault preset value;

the fouling detection module (305) is used for detecting the fouling degree of the bottom of the ship;

the oil consumption measuring and calculating module (306) is used for calculating an oil consumption increasing value based on the current loss rate;

and the oil quantity rechecking module (307) is used for detecting the flow of the outlet of the oil tank.

9. A computer device, characterized by: comprising a memory and a processor, said memory having stored thereon a computer program which can be loaded by the processor and which performs the method according to any of the claims 1-7.

10. A computer storage medium, characterized in that: a computer program which can be loaded by a processor and which performs the method according to any of claims 1-7.

Technical Field

The present disclosure relates to the field of ship monitoring, and in particular, to a method, an apparatus, a device and a storage medium for monitoring a ship power plant.

Background

The ship is a vehicle which can sail or berth in a water area for transportation or operation, and has different technical performance, operation equipment and structural types according to different use requirements; propulsion systems with external or self-contained energy sources are generally used as power plants, while in the power plants of ships propellers are generally used to propel the ship forward.

In the process of ship navigation, the main power of the ship is derived from a power device to drive the propeller to rotate, so that the water flow is moved to generate driving force, and the working efficiency of the propeller needs to be monitored in the process of propeller operation. Slip refers to the difference between the actual speed of the propeller to the water and the speed at which the propeller should theoretically move forward, and the ratio of slip to the speed at which the propeller should theoretically move forward is called the slip ratio, which is also called the slip rate. The loss rate is used for reflecting the working efficiency of the ship power device in the ship sailing process, and the influence of environmental factors on the actual sailing speed of the ship is reflected. Generally, in the process of sailing, a main engine of a ship only records power data and a loss rate, and the main engine of the ship is delivered to a ship company for analysis after the ship is landed.

In view of the above-mentioned related technologies, the inventor believes that the main engine of the ship can only obtain the state parameters of the power plant during the driving process, and cannot know whether the remaining fuel can maintain the sailing for completing the subsequent voyage.

Disclosure of Invention

In order to facilitate the prediction of oil consumption of a ship host in the sailing process, the application provides a monitoring method, a device, equipment and a storage medium for ship power equipment.

The technical scheme adopted by the monitoring method, the monitoring device, the monitoring equipment and the storage medium of the ship power equipment is as follows:

in a first aspect, the present application provides a method for monitoring a ship power plant, which adopts the following technical scheme:

a marine power plant monitoring method, comprising:

establishing an oil consumption initial model;

acquiring power parameters of power equipment in a past voyage, environmental parameters of a ship and actual oil consumption of the ship; the power parameters at least comprise the rotating speed of an engine, the pitch of a propeller and the temperature of lubricating oil, and the environmental parameters of the ship at least comprise the wind speed, the wind direction, the water flow speed and the water flow direction;

taking power parameters and environment parameters in the past voyage as input, taking actual oil consumption as output, and training the oil consumption initial model in a deep learning manner to obtain an oil consumption prediction model;

periodically acquiring power parameters of power equipment and environmental parameters of a ship in a target flight section;

and inputting the power parameters and the environment parameters into an oil consumption prediction model at the initial point of the target flight segment to obtain the predicted average value of the oil consumption of the target flight segment.

By adopting the technical scheme, a large amount of historical data is input into the oil consumption initial model, the oil consumption prediction model for predicting the average value of oil consumption prediction aiming at the power parameters and the environmental parameters can be obtained after the oil consumption initial model is trained, the power parameters of the power equipment in the target voyage section and the environmental parameters of the ship are input into the oil consumption prediction model, and the predicted values of the power parameters and the oil consumption under the environmental parameters in the current voyage section can be calculated, so that the reference significance can be played for the navigation and the oil consumption prediction of the ship, and the planning on the fuel quantity of the whole voyage and the learning whether the navigation of the subsequent voyage can be maintained are facilitated.

Preferably, the method further comprises:

acquiring the actual speed and the actual oil consumption of the target flight segment periodically;

calculating power efficiency and a slip rate based on the power parameters of the target voyage section and the actual voyage speed;

and when the difference value between the actual oil consumption and the predicted average value of the oil consumption is greater than or equal to a fault preset value, comparing the slip rate with a slip rate warning value and outputting a navigation suggestion, wherein the navigation suggestion comprises return navigation maintenance and continuous navigation.

By adopting the technical scheme, the predicted average value of the oil consumption obtained by the prediction of the oil consumption prediction model can be used as one parameter for judging the working state of the ship, when the difference value between the actual oil consumption and the predicted average value of the oil consumption is more than or equal to the preset fault value, the abnormal condition is shown, and all factors for increasing the oil consumption need to be checked, so that whether the ship is in the abnormal state or not is verified, and the sailing state of the ship is conveniently monitored so as to ensure the stability of sailing and the stable operation of power equipment.

Preferably, when the difference between the actual oil consumption and the predicted average value of the oil consumption is greater than or equal to a preset fault value, the step of comparing the slip rate with a slip rate warning value and outputting a navigation recommendation includes:

if the loss of slide is more than or equal to the loss of slide warning value, comparing the power parameter with the normal working range;

if the power parameters exceed the normal working range, displaying the fault of the power equipment and displaying the suggestion of return voyage maintenance;

if the power parameter is in the normal working range, displaying that the power equipment is normal and displaying a suggestion of continuing to sail;

and if the loss of slide is less than the loss of slide warning value, displaying to continue sailing.

By adopting the technical scheme, when the difference value between the actual oil consumption and the predicted average value of the oil consumption is greater than or equal to the fault preset value, the loss rate is compared, and if the loss rate is greater than or equal to the loss rate warning value, the power equipment possibly has the risk of being in fault and needs to be overhauled; if the power parameter exceeds the normal working range, the power equipment is in a fault state, and if the power parameter is in the normal working range, the power equipment is normal, at the moment, the risk of ship breakdown does not exist, so that the ship still can sail, and the situation that the ship can sail continuously is displayed all the time, so that the shipman can discharge the fault state of the power equipment.

Preferably, the displaying of the power equipment failure and displaying of the return voyage repair recommendation includes:

acquiring the occupation ratio of the traveled voyage relative to the whole voyage, and if the occupation ratio exceeds the preset voyage ratio, determining the nearest maintenance point based on the satellite map and displaying the position of the maintenance point and the shortest path to the maintenance point;

and if the occupation ratio does not exceed the preset range ratio, calculating the return redundant time of the whole range, sending the fault information of the power equipment and the return redundant time to a data center and displaying the fault of the power equipment.

By adopting the technical scheme, in the process of return voyage maintenance, if the voyage exceeds the preset voyage ratio, the extra cost is increased if the voyage returns to the original port, the cost can be saved by selecting the nearest maintenance point for maintenance, and if the voyage does not exceed the preset voyage ratio, the cost increased by return voyage is smaller in an acceptable range, so that the original port is selected and the extra time is calculated, and the ship can be replaced to finish transportation.

Preferably, the displaying that the power plant is normal and displaying the suggestion of continuing the voyage includes:

detecting the bottom fouling degree of the ship;

if the degree of the dirty bottom exceeds a dirty bottom preset value, calculating an oil consumption increase value based on the current slip rate;

and sending the slip rate, the pollution information and the oil consumption increase value to a data center, and receiving and displaying a navigation instruction from the data center.

By adopting the technical scheme, if the power equipment of the ship is normal, and the other condition that the slip loss rate exceeds the slip loss rate warning value is that the ship possibly has a problem of fouling, the fouling condition of the ship needs to be verified, when the fouling degree exceeds the fouling preset value, extra oil consumption is calculated at the moment, and the slip loss rate, the fouling information and the oil consumption increase value are sent to the data center, so that the data center calculates the cost.

Preferably, if the loss of slip rate is less than the loss of slip rate warning value, displaying to continue the navigation includes:

and re-inputting the power parameters and the environmental parameters in the current flight into the oil consumption prediction model to obtain the corrected predicted oil consumption.

By adopting the technical scheme, if the loss of slip is less than the warning value, the oil consumption is still abnormal, at the moment, the power parameters and the environmental parameters of the current flight segment are input into the oil consumption prediction model again to obtain the corrected predicted oil consumption, and therefore the influence of the environmental factors on the oil consumption can be analyzed by comparing the corrected predicted oil consumption with the original predicted average value of the oil consumption.

Preferably, the step of inputting the power parameters and the environmental parameters under the current flight into the oil consumption prediction model again to obtain the corrected predicted oil consumption includes:

when the difference value between the corrected predicted oil consumption and the actual oil consumption is still larger than the fault preset value, detecting the flow of the outlet of the oil tank;

and when the flow of the outlet of the oil tank is smaller than the actual oil consumption value, sending an alarm signal.

By adopting the technical scheme, when the difference value between the corrected predicted oil consumption and the actual oil consumption is still larger than the fault preset value, the fact that the actual oil consumption is influenced by environmental factors is small is shown at the moment, so that some artificial factors such as oil stealing may exist, the flow of the outlet of the oil tank is compared with the actual oil consumption, if the actual oil consumption is consistent with the flow of the outlet of the oil tank, other reasons may exist, if the actual oil consumption is inconsistent with the flow of the outlet of the oil tank, the situation of oil stealing is proved to exist at the moment, an alarm needs to be given out, and crews are checked one by one.

In a second aspect, the present application provides a monitoring device for a ship power equipment, which adopts the following technical scheme:

a marine power plant monitoring apparatus, the apparatus comprising:

the parameter detection module is used for acquiring power parameters of the power equipment in the past voyage, environmental parameters of the ship and actual oil consumption of the ship and periodically acquiring the power parameters of the power equipment in a target voyage section and the environmental parameters of the ship;

the fuel consumption prediction module is used for taking power parameters and environment parameters in the past voyage as input, taking actual fuel consumption as output, training the fuel consumption initial model in a deep learning mode to obtain a fuel consumption prediction model, and inputting the power parameters and the environment parameters into the fuel consumption prediction model at the starting point of a target voyage section to obtain a fuel consumption prediction average value of the target voyage section;

the power efficiency measuring and calculating module is used for periodically obtaining the actual navigational speed and the actual oil consumption of the target navigation section and measuring and calculating the engine efficiency and the slip loss rate based on the current engine parameters and the actual navigational speed of the ship;

the data transceiving module is used for sending the engine parameters, the actual navigational speed, the periodic oil consumption, the engine efficiency and the slip rate to a data center and receiving instructions from the data center;

the data analysis module is used for comparing the loss rate with a loss rate warning value and outputting an operation suggestion when the difference value between the actual oil consumption value and the predicted oil consumption value is larger than or equal to a fault preset value;

the fouling detection module is used for detecting the fouling degree of the bottom of the ship;

the oil consumption measuring and calculating module is used for calculating an oil consumption increasing value based on the current slip rate;

and the oil quantity rechecking module is used for detecting the flow of the outlet of the oil tank.

By adopting the technical scheme, a large amount of historical data is input into the oil consumption initial model, the oil consumption prediction model for predicting the average value of oil consumption prediction aiming at the power parameters and the environmental parameters can be obtained after the oil consumption initial model is trained, the power parameters of the power equipment in the target voyage section and the environmental parameters of the ship are input into the oil consumption prediction model, and the predicted values of the power parameters and the oil consumption under the environmental parameters in the current voyage section can be calculated, so that the reference significance can be played for the navigation and the oil consumption prediction of the ship, and the planning on the fuel quantity of the whole voyage and the learning whether the navigation of the subsequent voyage can be maintained are facilitated.

In a third aspect, the present application provides a computer device, which adopts the following technical solution:

a computer apparatus comprising a memory and a processor, the memory having stored thereon a computer program that can be loaded by the processor and executed to perform any of the marine power plant monitoring methods described above.

By adopting the technical scheme, a large amount of historical data is input into the oil consumption initial model, the oil consumption prediction model for predicting the average value of oil consumption prediction aiming at the power parameters and the environmental parameters can be obtained after the oil consumption initial model is trained, the power parameters of the power equipment in the target voyage section and the environmental parameters of the ship are input into the oil consumption prediction model, and the predicted values of the power parameters and the oil consumption under the environmental parameters in the current voyage section can be calculated, so that the reference significance can be played for the navigation and the oil consumption prediction of the ship, and the planning on the fuel quantity of the whole voyage and the learning whether the navigation of the subsequent voyage can be maintained are facilitated.

In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solutions:

a computer storage medium storing a computer program that can be loaded by a processor and that implements any of the marine power plant monitoring methods described above.

By adopting the technical scheme, a large amount of historical data is input into the oil consumption initial model, the oil consumption prediction model for predicting the average value of oil consumption prediction aiming at the power parameters and the environmental parameters can be obtained after the oil consumption initial model is trained, the power parameters of the power equipment in the target voyage section and the environmental parameters of the ship are input into the oil consumption prediction model, and the predicted values of the power parameters and the oil consumption under the environmental parameters in the current voyage section can be calculated, so that the reference significance can be played for the navigation and the oil consumption prediction of the ship, and the planning on the fuel quantity of the whole voyage and the learning whether the navigation of the subsequent voyage can be maintained are facilitated.

In summary, the present application includes at least one of the following beneficial technical effects:

the method has the advantages that a large amount of historical data are input into the oil consumption initial model, the oil consumption prediction model for predicting the average value of oil consumption prediction aiming at the power parameters and the environmental parameters can be obtained after the oil consumption initial model is trained, the power parameters of the current power equipment and the environmental parameters of the ship are input into the oil consumption prediction model, the predicted values of the power parameters and the oil consumption under the current navigation section and the environmental parameters can be calculated, the reference significance can be achieved for navigation and oil consumption prediction of the ship, planning on the fuel quantity of the whole navigation range is facilitated, the running state of the ship is detected aiming at abnormal oil consumption, and therefore the abnormal state of the ship can be found in time.

Drawings

FIG. 1 is a flow chart of a method of monitoring a marine power plant in an embodiment of the present application;

FIG. 2 is a flowchart illustrating the sub-steps of step S108 in the embodiment of the present application;

fig. 3 is a block diagram of a monitoring device for a ship power plant in the embodiment of the present application.

Description of reference numerals: 301. a parameter detection module; 302. a fuel consumption prediction module; 303. a power efficiency measuring and calculating module; 304. a data analysis module; 305. a dirty bottom detection module; 306. a fuel consumption measuring module; 307. and an oil quantity rechecking module.

Detailed Description

The present application is described in further detail below with reference to figures 1-3.

The embodiment of the application discloses a monitoring method of ship power equipment, which is used for monitoring power parameters of the ship power equipment and environmental parameters of a ship and forming historical data by combining actual oil consumption of the ship; and training a deep learning model based on the historical data obtained by monitoring, and predicting the average value of the oil consumption of a certain flight section in the whole flight through the trained model. The method can be applied to a ship host of a large-scale offshore cargo ship, and oil consumption is predicted aiming at ocean navigation of the cargo ship. In the actual sailing process, the captain divides the whole voyage into different voyage sections according to the hydrological characteristics, and predicts each voyage section.

The process flow shown in fig. 1 will be described in detail below with reference to specific embodiments, and the contents may be as follows:

step 101, establishing an oil consumption initial model.

In implementation, the ship host computer migrates the features in the same ship fuel consumption prediction model in a feature migration manner to obtain a fuel consumption initial model in a migration learning manner at the initial stage of sailing, and trains the fuel consumption initial model based on the past historical data of the ship. The initial model of fuel consumption uses a multi-factor predictive model, such as LSTM (long short term memory network). The multi-factor prediction model can calculate and output a prediction result based on the input influence factors, and can predict the fuel consumption when applied to the fuel prediction model.

And 102, acquiring power parameters of the power equipment in the past voyage, environmental parameters of the ship and actual oil consumption of the ship.

The power parameters at least comprise the rotating speed of an engine, the pitch of a propeller and the temperature of lubricating oil, and the environmental parameters of the ship at least comprise the wind speed, the wind direction, the water flow speed and the water flow direction.

In the implementation, at the beginning of the target voyage, the ship host acquires the power parameters of the power equipment in the past voyage, the environmental parameters of the ship and the actual oil consumption of the ship, and trains by taking the power parameters of the power equipment in the past voyage, the environmental parameters of the ship and the actual oil consumption of the ship as training samples. The ship main engine tests the engine rotating speed in the ship power parameters through the rotating speed sensor, reads the propeller pitch of the ship through acquiring ship delivery parameters, and acquires the temperature of lubricating oil through the temperature sensor at the power equipment. In addition, the power parameters of the power equipment also comprise lubricating oil pressure, and the marine main engine can also obtain the lubricating oil pressure of the power equipment through a pressure sensor. The environmental parameters of the ship comprise wind speed, wind direction, water flow speed and water flow direction, and the wind speed and the wind direction are acquired by an anemorumbometer arranged on the ship; the water flow velocity and the water flow direction are measured by an ultrasonic time difference and flow velocity meter arranged on a ship through the propagation velocity difference of ultrasonic waves in different directions of water flow, and the actual oil consumption of the ship is the average value of the fuel consumption of each section obtained by dividing the volume difference of fuel of each section by the distance of each section.

And 103, taking the power parameters and the environmental parameters in the past voyage as input and the actual oil consumption as output, and training the oil consumption initial model in a deep learning manner to obtain an oil consumption prediction model.

In implementation, the past voyage includes the whole historical voyage of the ship and the voyage of the ship in the voyage, the historical whole voyage can reflect the historical data of the ship in the voyage process, and the voyage which the voyage has voyage can reflect the power parameters of the power equipment of the ship in the voyage process. The power parameters and the environmental parameters in the past voyage are used as input, the actual oil consumption is used as output, the input is input into an oil consumption initial model, and the features in the oil consumption model are fixed through ten thousand-order training. In addition, the marine main engine extracts 10% of data from the historical data as a verification set, and the 10% verification set is used for verification, so that a prediction model of the fuel consumption can be obtained. In the process of sailing of the ship, each time the ship sails for one section of sailing, the main engine of the ship trains the power parameters, the environmental parameters and the actual oil consumption of the ship as a part of the previous sailing, namely after each section of sailing is finished, the main engine of the ship trains the oil consumption prediction model again, and therefore a new oil consumption prediction model is obtained.

And step 104, periodically acquiring power parameters of power equipment in the target navigation section and environmental parameters of the ship.

In the implementation, in the process of each section of the voyage, the main engine of the ship measures and calculates the power parameters of the power equipment and the environmental parameters of the ship at intervals. The marine main engine obtains the period values of the power parameters and the environmental parameters through setting, the period value can be 2h, namely the power parameters and the environmental parameters are sampled once every 2h, and the periodic monitoring of the power parameters and the environmental parameters is guaranteed.

And 105, inputting the power parameters and the environmental parameters into the oil consumption prediction model at the initial point of the target flight segment to obtain the predicted average value of the oil consumption of the target flight segment.

In implementation, at the starting point of each flight segment, which is also the ending point of the previous flight segment, the ship host trains the oil consumption prediction model again to obtain a new oil consumption prediction model. And then the ship host inputs the power parameters and the environmental parameters of the starting point into the oil consumption prediction model, the oil consumption prediction model automatically predicts and outputs an oil consumption prediction average value, and the oil consumption prediction average value is the average oil consumption of every hundred miles, namely the oil consumption prediction average value in the process of the next section of navigation, so as to be used as the oil consumption prediction reference in the navigation process.

Optionally, in order to facilitate comparison of the difference between the predicted oil consumption and the actual oil consumption, and analyze and compare the navigation state of the ship with respect to the difference between the predicted oil consumption and the actual oil consumption, correspondingly, after the step 105, the method further includes:

and step 106, regularly acquiring the actual speed and the actual oil consumption of the target flight segment.

In implementation, at certain intervals, the ship main engine can measure the speed of the ship relative to water through a relative range instrument installed on the ship, can measure the speed of the ship relative to the ground through an absolute range instrument, and can measure the actual oil consumption in the current period through the liquid level height difference in the oil tank, the volume of the oil tank and the division of the volume of the oil tank by the mileage of a target range. The period value for obtaining the actual navigational speed and the actual oil consumption of the target navigation segment can be consistent with the period value of the navigation segment, can also be consistent with the detection period values of the power parameters and the environmental parameters, and certainly, an independent period value can also be set for monitoring. In this embodiment, in order to facilitate the statistical timing consistency, a method consistent with the detection period values of the dynamic parameters and the environmental parameters is adopted.

And step 107, calculating the power efficiency and the slip rate based on the power parameters of the target navigation section and the actual navigation speed.

In implementation, after the actual oil consumption is obtained, the main engine of the ship measures and calculates the power efficiency and the slip rate based on the power parameters of the target voyage section and the actual voyage speed so as to detect the working state of the power equipment. The value calculation mode of the power efficiency is that the distance to the ground of the actual sailing of the ship in every hundred circles of rotating speed of an engine in the power equipment, namely the distance to the ground multiplied by 100/(rotating speed multiplied by sailing time), the unit of the distance to the ground is converted into meter, the unit of the rotating speed is converted into r/s, and the unit of the sailing time is converted into s; the slip loss rate is calculated by the ratio of the difference between the actual and theoretical speeds to the theoretical speed, i.e., (engine speed x propeller pitch-relative odometer reading)/(engine speed x propeller pitch). The working efficiency of the engine can be obtained through measuring and calculating the power efficiency, and the influence of environmental factors on ship navigation can be reflected through measuring and calculating the slip loss rate.

Specifically, in order to ensure real-time monitoring of the data center on ship data, the ship host can periodically send power parameters, environmental parameters, actual navigational speed, actual oil consumption, power efficiency and slip rate to the data center in real time.

In implementation, send all data packets to shore-based data center through wireless transceiver device after, the mode of wireless transceiver can adopt ocean satellite communication, also can adopt other remote transmission modes to be convenient for data center in time to record and keep all data.

And 108, comparing the slip rate with a slip rate warning value and outputting a navigation suggestion when the difference value of the actual oil consumption and the predicted average value of the oil consumption is larger than or equal to a fault preset value.

Wherein the navigation advice comprises return voyage maintenance and continuous voyage.

In implementation, when the ship host detects that the difference value between the actual oil consumption and the predicted average value of the oil consumption is larger than or equal to the preset fault value, the loss rate and the loss rate warning value are compared, and a navigation suggestion is output. The standard value of the fault preset value can be defined according to the attributes of different freight ships, and is generally positively correlated according to the engine power of the ship power plant. When the difference value between the actual oil consumption and the predicted average value of the oil consumption is greater than or equal to the preset fault value, the power equipment fault or serious ship fouling may be represented at the moment, and at the moment, the slip rate needs to be compared with the slip rate warning value to give a navigation suggestion so as to be convenient for the captain to refer.

Optionally, for different comparison results, an additional analysis logic needs to be executed, and correspondingly, different measures are taken to deal with the current increase in oil consumption, and accordingly, the specific processing flow of step 109 is as follows:

and step 201, if the loss of slide is greater than or equal to the loss of slide warning value, comparing the power parameter with the normal working range.

In implementation, when the loss of slip is greater than or equal to the loss of slip warning value, the marine main engine compares the power parameter with the normal working range to judge whether the power equipment fails. The slip rate warning value is set by the captain according to different types of cargo ships, for example 25%. If the slip rate is too high, it indicates that the power output by the power plant of the marine vessel is not responding to speed, and there may be a possibility of engine failure or other loss of power.

Step 202, if the power parameters exceed the normal working range, displaying the fault of the power equipment and displaying the suggestion of return flight maintenance.

In implementation, when the power parameters of the marine main engine exceed the normal working range, the fault of the power equipment is displayed, and the suggestion of return voyage maintenance is displayed. And when the actual oil consumption is greater than the predicted oil consumption and the slip rate is greater than or equal to the slip rate warning value, comparing the power parameters corresponding to the actual oil consumption at the moment with the normal working range of the power equipment to obtain whether the working state of the engine is normal or not. For example, when the engine is in fault, the engine is stopped at the moment, the slip rate tends to be infinite, the slip rate must exceed the slip rate warning value at the moment, and if the power parameters of the engine, such as the temperature and the pressure of lubricating oil, also exceed the normal working range at the moment, the fault of the engine can be known, so that the engine can be timely returned for maintenance.

Optionally, in the return trip maintenance process, the actual cost and the influence on the timeliness of the freight transportation need to be considered, and accordingly, the specific processing flow in step 202 includes:

and acquiring the occupation ratio of the traveled voyage relative to the whole voyage, and if the occupation ratio exceeds the preset voyage ratio, determining the nearest maintenance point based on the satellite map and displaying the position of the maintenance point and the shortest path to the maintenance point.

In practice, if the ratio of the traveled voyage to the whole voyage exceeds the preset voyage ratio, it indicates that returning to the original port causes higher additional cost, and therefore, it is the optimal choice to select the nearest maintenance point for maintenance. Based on the shortest path determined by the satellite map, the ship host can select the shortest path to reach a maintenance point, so that the ship can be maintained fastest, and delayed freight time is reduced. The preset voyage ratio is determined according to the unit price, profit and freight time of each single freight.

And if the occupation ratio does not exceed the preset range ratio, calculating the return redundant time of the whole range, wherein the return redundant time is the extra time required to be added after the return, and sending the fault information of the power equipment and the return redundant time to a data center and displaying the fault of the power equipment.

In implementation, if the occupation ratio does not exceed the preset voyage ratio, the ship returns to the initial port more cost-effectively, and the ship host calculates the return time, calculates the sum of the unloading time and the reloading time based on the unloading speed and the loading amount of the initial port, and sends the sum to the data center.

And step 203, if the power parameter is in the normal working range, displaying that the power equipment is normal and displaying a suggestion of continuing the navigation.

In implementation, if the power parameter is in the normal working range, the power parameter of the power equipment is normal, and the working state of the power equipment is normal. Other reasons may be that the slip rate is too high, such as fouling. If the non-power equipment fails, the ship can keep a state of continuous navigation, and the oil consumption is increased only in the navigation process, so that the continuous navigation is displayed.

Optionally, in consideration of the effect of eliminating the power equipment fault, the loss rate of the ship may be increased due to fouling, and accordingly, the specific process in step 203 includes:

detecting the bottom fouling degree of the ship;

in the implementation, when the dynamic parameter is located normal operating range, the ship host detects the dirty degree of the bottom of the ship to obtain the dirty degree of the bottom of the ship. The underwater camera shoots the image of the bottom of the ship and reflects the image by calculating the area and thickness of the polluted bottom.

If the degree of the dirty bottom exceeds a dirty bottom preset value, calculating an oil consumption increase value based on the current slip rate;

in the implementation, if dirty volume exceedes dirty default, then indicate that the dirty degree of boats and ships is high, the resistance increase of boats and ships bottom, the fuel is extravagant to be increased, needs to scrape the end to the diapire of boats and ships and handles. The preset value of the fouling is derived from the measured value in the actual sailing process, and the fouling degree is represented based on the proportion of the surface area of the fouling to the ship bottom and the average thickness of the fouling, for example, the surface area is more than 80 percent, and the average thickness is more than 10 cm. The measuring and calculating mode of the oil consumption increment is that the current predicted oil consumption average value is multiplied by the voyage minus the oil consumption value corresponding to the theoretical ship speed.

In order to monitor the ship state in real time by the shore-based data center, correspondingly, the loss rate, the pollution information and the oil consumption increase value are sent to the data center, and the navigation instruction from the data center is received and displayed.

In implementation, the loss rate, the pollution information and the oil consumption increase value are used as important factors of the calculation cost and need to be sent to a data center, so that the calculation cost of the data center is facilitated; if the cost calculated by the data center is increased, the data center sends a navigation instruction, and the navigation instruction comprises the adoption of low-speed navigation or the increase of the navigation speed to guarantee that the vehicle arrives at the destination in due time. The data center can also in time remind the captain of boats and ships to go to the ship repair shop and scrape the end and spray paint the processing after boats and ships arrive in port to alleviate the dirty degree of boats and ships, reduce the oil consumption waste that dirty end leads to.

And step 204, if the loss of slide is less than the loss of slide alert value, displaying to continue navigation.

In implementation, if the slip rate is less than the slip rate warning value, and the power equipment fault and the dirty bottom are eliminated, there may be environmental factor influence and oil stealing factor, and accordingly, the specific process is as follows:

and re-inputting the power parameters and the environmental parameters in the current flight into the oil consumption prediction model to obtain the corrected predicted oil consumption.

In implementation, when the loss of slip is smaller than the loss of slip warning value, the ship host inputs the power parameters and the environmental parameters under the current flight segment into the oil consumption prediction model again to obtain the corrected predicted oil consumption. And re-inputting the power parameters and the environmental parameters into the oil consumption prediction model when the difference value between the actual oil consumption and the predicted average value of the oil consumption is greater than or equal to the preset value of the fault, wherein the obtained oil consumption prediction is the oil consumption prediction under the current environmental parameters, and if the environmental factors influence the oil consumption, the oil consumption is inevitably predicted to be increased.

Optionally, the correcting and predicting the oil consumption reflects the influence of environmental changes on the actual oil consumption, and correspondingly, the power parameters and the environmental parameters under the current flight segment are input into the oil consumption prediction model again, and the method further includes the following steps after the corrected and predicted oil consumption is obtained:

when the difference value between the corrected predicted oil consumption and the actual oil consumption is still larger than the fault preset value, detecting the flow of the outlet of the oil tank;

in implementation, when the difference between the corrected predicted oil consumption and the actual oil consumption is less than or equal to the fault preset value, it is proved that the environmental factors affect the actual oil consumption, and the actual oil consumption is increased. If the difference value between the corrected predicted oil consumption and the actual oil consumption is still larger than the fault preset value, the oil stealing condition may exist at the moment, and the flow of the oil tank needs to be detected.

And when the flow of the outlet of the oil tank is smaller than the actual oil consumption value, sending an alarm signal to the data center for alarming.

In the implementation, when the flow of the outlet of the fuel tank is smaller than the actual fuel consumption value, the fact that other fuel outlets possibly exist in the fuel tank is indicated, and the situation that the fuel is stolen by a crew is existed. The ship host sends an alarm signal to the captain and the data center for inspection, and possible oil stealing personnel are investigated through video monitoring on the ship.

When the flow of the outlet of the oil tank is equal to the actual oil consumption value, no alarm is needed, and the actual oil consumption value may be increased due to driving reasons, such as the need of steering or sudden increase of the power consumption of the ship. At the moment, the ship sails normally without alarming.

In implementation, when the difference between the actual oil consumption and the predicted average value of the oil consumption is smaller than the preset fault value, the ship is in a normal state at the moment, and the ship is possibly influenced by environmental factors, such as sudden change of a downwind state into an upwind state or increase of the slip rate in the process of steering of the ship, and the ship normally runs without monitoring.

Based on the same technical concept, the embodiment of the present application further provides a monitoring device for a ship power plant, as shown in fig. 3, the monitoring device includes:

the parameter detection module 301 is configured to obtain a power parameter of the power equipment in a past voyage, an environmental parameter of the ship, and an actual oil consumption of the ship, and periodically obtain the power parameter of the power equipment and the environmental parameter of the ship in a target voyage.

The oil consumption prediction module 302 is configured to take a power parameter and an environmental parameter in a previous voyage as inputs and an actual oil consumption as an output, train the oil consumption initial model in a deep learning manner, obtain an oil consumption prediction model, and input the power parameter and the environmental parameter into the oil consumption prediction model at a starting point of a target voyage segment to obtain an oil consumption prediction average value of the target voyage segment.

Optionally, the apparatus further comprises:

the power efficiency measuring and calculating module 303 is configured to periodically obtain an actual speed and an actual oil consumption of the target flight segment, and measure and calculate engine efficiency and a slip rate based on the current engine parameter and the actual speed of the ship.

And the data analysis module 304 compares the slip rate with a slip rate warning value and outputs an operation suggestion when the difference value between the actual oil consumption value and the predicted oil consumption value is greater than or equal to the fault preset value.

And the fouling detection module 305 is used for detecting the fouling degree of the bottom of the ship.

The oil consumption measuring and calculating module 306 is configured to calculate an oil consumption increase value based on the current loss rate.

And the oil quantity rechecking module 307 is used for detecting the flow of the outlet of the oil tank.

It should be noted that: when the monitoring device for the ship power equipment provided by the embodiment performs fuel consumption prediction based on machine learning, the division of the functional modules is only used for illustration, and in practical application, the function distribution can be completed by different functional modules according to needs, that is, the internal structure of the monitoring device is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the apparatus for cultivating the formation-based game role based on machine learning and the method for cultivating the formation-based game role based on machine learning provided by the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.

Based on the same inventive concept, the embodiment of the application also discloses a computer device, and specifically, the computer device comprises a memory and a processor, wherein the memory stores a computer program which can be loaded by the processor and used for executing the monitoring method of the ship power equipment.

Based on the same inventive concept, the embodiment of the application also discloses a computer readable storage medium.

Specifically, the computer-readable storage medium stores a computer program that can be loaded by a processor and executes the ship power plant monitoring method as described above, and includes, for example: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only memory (ROM 0, a Random Access Memory (RAM)), a magnetic disk, and an optical disk.

The above embodiments are preferred embodiments of the present application, and the protection scope of the present application is not limited by the above embodiments, so: all equivalent changes made according to the structure, shape and principle of the present application shall be covered by the protection scope of the present application.