Control method, device, medium, equipment and program product of thermal power generating unit

Abstract

The present disclosure relates to a control method and device of a thermal power generating unit, a medium, equipment and a program product, and relates to the technical field of power generation. The method comprises: obtaining operation data of the thermal power generating unit, the operation data comprising actual values of first operation data and second operation data, the first operation data comprising historical power instruction values, grid frequency, active power actual values, boiler thermal efficiency, load response time, steam turbine heat rate, thermal power generating unit power generation coal consumption rate, power supply coal consumption rate, coal feeding system parameters, etc., and the second operation data comprising equipment operation data of the thermal power generating unit; inputting the first operation data into a trained prediction model to obtain predicted values of the second operation data; in the case that a difference between the actual values and the predicted values is less than a first preset threshold, determining a current power instruction value according to the actual values and the predicted values; and adjusting the coal feeding amount and the air supply amount according to the current power instruction value. The method can improve the response speed of power regulation of the thermal power generating unit.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of power generation, in particular to a control method and device of a thermal power unit, a medium, equipment and a program product. BACKGROUND

[0002] With the rapid development of renewable energy, the randomness and intermittency of wind and solar power generation have brought severe challenges to the safe operation of power grids. In order to balance the fluctuations of power grids, thermal power units need to be flexibly modified to improve the rapid response capability of power regulation.

[0003] The traditional "feedforward + PID feedback" control mode has been difficult to meet the needs of new power systems. In the process of deep peak shaving, this control method has a slow response speed, which can easily lead to problems such as imbalance of water-coal-wind ratio, abnormal fluctuations of furnace temperature, and even safety accidents in serious cases. SUMMARY

[0004] To overcome the problems in the related art, the present application provides a control method, device, medium, equipment and program product of a thermal power unit.

[0005] According to a first aspect of the present application, a control method of a thermal power unit is provided, the method comprising:

[0006] obtaining operation data of the thermal power unit, the operation data comprising actual values of first operation data and second operation data, the first operation data comprising one or any multiple of the following data: historical power instruction value, power grid frequency, active power actual value, boiler thermal efficiency, load response time, steam turbine heat rate, thermal power unit coal consumption rate, power supply coal consumption rate, coal feeding system parameters and air supply system parameters, the second operation data comprising device operation data of the thermal power unit;

[0007] inputting the first operation data into a trained prediction model to obtain predicted values of the second operation data;

[0008] in a case where a difference between the actual values and the predicted values is less than a first preset threshold, determining a current power instruction value according to the actual values and the predicted values;

[0009] adjusting the coal feeding amount and the air supply amount according to the current power instruction value.

[0010] Optionally, the operation data of the thermal power unit is obtained by:

[0011] obtaining the operation data collected by a distributed control system, wherein the distributed control system transmits the operation data to a data acquisition center through an electronic room server.

[0012] Optionally, the trained prediction model is obtained by the following steps:

[0013] obtaining historical operation data of the thermal power unit;

[0014] selecting, from the historical operation data, historical operation data in which a difference between an actual value of active power and a historical power instruction value is not more than a second preset threshold value, as training data;

[0015] determining, according to the training data, a training sample and a label, the training sample including one or any multiple of the following data: the historical power instruction value, a power grid frequency, the actual value of active power, a boiler thermal efficiency, a load response time, a steam turbine heat rate, a thermal power unit power generation coal consumption rate, a power supply coal consumption rate, a coal feeding system parameter, and an air supply system parameter, and the label including equipment operation data of the thermal power unit;

[0016] inputting the training sample into a neural network model to obtain a prediction value;

[0017] adjusting parameters of the neural network model according to a difference between the prediction value and the label;

[0018] returning to the step of inputting the training sample into the neural network model to obtain the prediction value until a difference between the prediction value and the label is less than a third preset threshold value or a cycle number reaches a preset number of times, to obtain the trained prediction model.

[0019] Optionally, the method further includes:

[0020] in a case where a difference between an actual value and a prediction value of the second operation data is greater than a first preset threshold value, outputting an abnormality prompt and obtaining a corrected value of the second operation data input by a user;

[0021] determining the current power instruction value according to the actual value and the corrected value;

[0022] updating the prediction model according to the first operation data and the corrected value of the second operation data.

[0023] Optionally, the method further includes:

[0024] sending the current power instruction value to an automatic generation control system, so that the automatic generation control system adjusts feedforward control parameters and feedback control parameters thereof according to the current power instruction value.

[0025] Optionally, the adjusting of the coal feeding amount and the air supply amount according to the current power instruction value includes:

[0026] send the current power instruction value to a decentralized control system, and control the coal feeding system to adjust the coal feeding amount and control the air supply system to adjust the air supply amount through the decentralized control system.

[0027] According to a second aspect of the present application, a control device of a thermal power generating unit is provided, comprising:

[0028] a data acquisition module configured to acquire operation data of the thermal power generating unit, wherein the operation data comprises actual values of first operation data and second operation data, the first operation data comprises one or any multiple of the following data: historical power instruction value, power grid frequency, actual value of active power, boiler thermal efficiency, load response time, steam turbine heat rate, thermal power generating unit power generation coal consumption rate, power supply coal consumption rate, coal feeding system parameter, and air supply system parameter, and the second operation data comprises equipment operation data of the thermal power generating unit;

[0029] a data prediction module configured to input the first operation data into a trained prediction model to obtain predicted values of the second operation data;

[0030] a power instruction module configured to determine a power instruction value according to the actual values and the predicted values when a difference between the actual values and the predicted values is less than a first preset threshold value;

[0031] a thermal power generating unit adjustment module configured to adjust the coal feeding amount and the air supply amount according to the current power instruction value.

[0032] According to a third aspect of the present application, a non-transitory computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of any one of the methods provided in the first aspect of the present application.

[0033] According to a fourth aspect of the present application, an electronic device is provided, comprising:

[0034] a memory storing a computer program;

[0035] a processor configured to execute the computer program in the memory to implement the steps of any one of the methods provided in the first aspect of the present application.

[0036] According to a fifth aspect of the present application, a computer program product is provided, comprising a computer program, and the computer program is executed by a processor to implement the steps of any one of the methods provided in the first aspect of the present application.

[0037] By the technical solution, firstly, the key operation data of the thermal power generating unit can be comprehensively collected, including power instruction, power grid frequency, active power and the like, reflecting the dynamic characteristics of the thermal power generating unit. Secondly, based on the trained prediction model, the deviation that may occur in the response process of the thermal power generating unit can be predicted. In addition, the method can compare the predicted value with the actual observation value in real time, and when the deviation between the two is less than a threshold value, the optimized power instruction can be determined. Finally, according to the optimized power instruction, the coal feeding and air supply can be accurately adjusted, so as to ensure the stability of the combustion process and avoid temperature fluctuation, thereby improving the load response speed of the thermal power generating unit.

[0038] Other features and advantages of the present disclosure will be described in detail in the following detailed description section. BRIEF DESCRIPTION OF DRAWINGS

[0039] The accompanying drawings are included to provide a further understanding of the present disclosure and constitute a part of the specification, and are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation on the present disclosure. In the drawings:

[0040] Figure 1 is a flow chart of a control method of a thermal power generating unit according to an exemplary embodiment;

[0041] Figure 2 is a block diagram of a control device of a thermal power generating unit according to an exemplary embodiment;

[0042] Figure 3 is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0043] The detailed description of the specific embodiments of the present disclosure is described below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present disclosure, and do not limit the present disclosure.

[0044] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in accordance with the corresponding data protection regulations and policies of the country where the device is located, and with the authorization of the corresponding device owner.

[0045] Herein, the terms "first", "second", and the like are only used to distinguish one element from another, without requiring or implying any actual relationship or order between the elements. In fact, the first element can also be referred to as the second element, and vice versa.

[0046] Figure 1 is a flow chart of a control method of a thermal power generating unit according to an exemplary embodiment, as shown in Figure 1 The method comprises the following steps.

[0047] In step 110, operation data of the thermal power unit is acquired, the operation data including actual values of first operation data and second operation data, the first operation data including one or any multiple of the following data: historical power instruction value, grid frequency, active power actual value, boiler thermal efficiency, load response time, steam turbine heat rate, thermal power unit power generation coal consumption rate, power supply coal consumption rate, coal feeding system parameters, and air supply system parameters, and the second operation data including equipment operation data of the thermal power unit.

[0048] In step 120, the first operation data is input into the trained prediction model to obtain predicted values of the second operation data.

[0049] In step 130, in a case where a difference between the actual values and the predicted values is less than a first preset threshold, a power instruction value is determined according to the actual values and the predicted values.

[0050] In step 140, the coal feeding amount and the air supply amount are adjusted according to the current power instruction value.

[0051] Here, the first operation data can include single data or any combination data set of the current power instruction value, the grid frequency, the active power actual value, the boiler thermal efficiency, the load response time, the steam turbine heat rate, the thermal power unit power generation coal consumption rate, the power supply coal consumption rate, the coal feeding system parameters, and the air supply system parameters. The first operation data can represent the dynamic operation performance and efficiency characteristics of the thermal power unit, and is an object that needs to be quickly responded by the thermal power unit.

[0052] The second operation data can include equipment operation data of the thermal power unit, and specifically can include power generation thermal power unit output parameters, boiler operation data, steam turbine operation data, and auxiliary system parameters. The second operation data can reflect the equipment operation state inside the thermal power unit, and directly determines the actual response capability and operation state of the thermal power unit.

[0053] The first preset threshold can set a reasonable prediction value and actual value difference threshold according to the actual situation of the thermal power unit, which should be as small as possible to improve the control precision. The historical power instruction value is acquired from an automatic generation control (AGC) system, and the automatic generation control system issues a power generation power adjustment instruction to the thermal power unit according to the grid load change situation to maintain the grid frequency and power balance.

[0054] It should be understood that step 110 provides basic data input for subsequent prediction and optimization control by obtaining the operation data of the thermal power unit. There is an inherent correlation between the first operation data and the second operation data. Changes in demand on the grid side will drive the fuel supply and combustion process inside the thermal power unit to make corresponding adjustments. The actual response inside the thermal power unit will in turn affect the power supply on the grid side. This mutual coupling dynamic characteristic means that the relationship between the first operation data and the second operation data can be fully utilized to ultimately achieve coordination between the grid and the thermal power unit according to the current power instruction value.

[0055] Step 120 uses the trained prediction model to predict the theoretical value of the second operation data according to the obtained first operation data. The prediction model can be a model obtained by learning the inherent relationship between the first operation data and the second operation data of the thermal power unit through historical operation data using a neural network model training method. By predicting the theoretical value of the second parameter, deviations that may occur during the response process of the thermal power unit can be identified in a timely manner, laying a foundation for subsequent control optimization.

[0056] Step 130 compares the predicted value of the second parameter with the actual value in real time. When the difference between the two is less than a first preset threshold, it means that the prediction is not abnormal. There is no large fluctuation between the predicted value and the actual value of the second parameter, and the current power instruction value can be determined accordingly. Specifically, the power instruction value can be adjusted to be the current power instruction value, so that the predicted value of the second parameter and the actual value tend to be consistent.

[0057] Step 140 adjusts the coal supply and air supply according to the current power instruction value determined in the foregoing. Specifically, the coal supply and air supply can be adjusted in real time according to the current power instruction value, so that the former and the latter change in direct proportion. When the current power instruction value rises, the coal supply and air supply are increased, and when the current power instruction value decreases, the coal supply and air supply are correspondingly reduced. This can stabilize the combustion process and avoid temperature fluctuations caused by supply-demand imbalance, thereby improving the load response speed of the thermal power unit.

[0058] Through the above technical solution, first, key operation data of the thermal power unit can be comprehensively collected, including power instruction, grid frequency, active power, etc., reflecting the dynamic characteristics of the thermal power unit. Second, based on the trained prediction model, deviations that may occur during the response process of the thermal power unit can be predicted. In addition, the method can compare the predicted value with the actual observed value in real time, and when the deviation between the two is less than a threshold, the optimized power instruction can be determined. Finally, according to the optimized power instruction, the coal supply and air supply are accurately adjusted to ensure the stability of the combustion process, avoid temperature fluctuations, and thereby improve the load response speed of the thermal power unit.

[0059] In an embodiment, the operation data of the thermal power generating unit is acquired by acquiring the operation data collected by the distributed control system, wherein the distributed control system transmits the operation data to the data collection center through the electronic room server.

[0060] Here, the distributed control system (DCS) is composed of multiple distributed control units, each of which controls a certain subsystem or device of the thermal power generating unit. Each control unit of the distributed control system can collect first operation data and second operation data of the thermal power generating unit in real time through the sensors connected thereto. Each control unit of the distributed control system transmits the collected operation data to the electronic room server through an electronic data bus. The electronic room server then transmits the data to a higher-level data collection center.

[0061] The electronic room server is located between the distributed control system and the data collection center, and can centrally receive operation data from each distributed control unit, and concentrate the distributed data stream to a unified data platform, i.e. the data collection center. The electronic room server also has the function of data caching. Some key operation data can be temporarily stored to prevent data loss caused by communication interruption.

[0062] The data collection center can be an Internet gateway (IGate) data collection center. The data collection center receives various operation data from the electronic room server, and centrally manages and stores the operation data. The data collection center can filter and process the massive data collected. Specifically, the data collection center can remove some redundant or noise data to improve the quality and effectiveness of the data. The data collection center distributes the filtered operation data to the execution subject of the method. The execution subject of the method can be an advanced integrated intelligent computing system (AICS).

[0063] This hierarchical data collection and transmission through the distributed control system, the electronic room server and the data collection center can comprehensively, in real time and with high quality, acquire the operation data of the thermal power generating unit.

[0064] In an embodiment, the trained prediction model is obtained by the following steps: obtaining historical operation data of the thermal power unit; screening, from the historical operation data, historical operation data in which a difference between an actual active power value and a historical power instruction value is not more than a second preset threshold value, as training data; determining, according to the training data, a training sample and a label, the training sample including one or any multiple of the following data: the historical power instruction value, a power grid frequency, the actual active power value, a boiler thermal efficiency, a load response time, a steam turbine heat rate, a thermal power unit power generation coal consumption rate, a power supply coal consumption rate, a coal feeding system parameter, and an air supply system parameter, the label including equipment operation data of the thermal power unit; inputting the training sample into a neural network model to obtain a prediction value; adjusting parameters of the neural network model according to a difference between the prediction value and the label; returning to perform the inputting the training sample into the neural network model to obtain the prediction value until the difference between the prediction value and the label is less than a third preset threshold value or a cycle number reaches a preset number of times, to obtain the trained prediction model.

[0065] Here, the historical operation data refers to operation data of the thermal power unit in a past period of time.

[0066] The second preset threshold value refers to a maximum allowed value of the difference between the actual active power value and the historical power instruction value. Only the historical data in which the difference between the actual value and the instruction value is within the threshold value range is selected as the training data. The second preset threshold value can be set in combination with the response characteristics and control requirements of the actual thermal power unit. The second preset threshold value is often set to a relatively small value, so that the actual response of the thermal power unit can better match the instruction value.

[0067] The training sample contains data elements consistent with the first operation parameter. The label contains data elements consistent with the second operation parameter. Each training sample has a corresponding label. The label can reflect the actual operation state of each device of the thermal power unit under the given training sample condition.

[0068] A common neural network model, such as a deep neural network (DNN) model, can be selected as an initial model of the prediction model. The neural network model is composed of multiple hidden layers and can learn complex nonlinear relationships.

[0069] The input layer of the neural network model accepts the training sample. The hidden layer learns the complex mapping relationship between the input features and the output through the nonlinear transformation of multiple neurons. The output layer gives the predicted equipment operation data. Using an optimization algorithm such as gradient descent, the parameters of each layer of the model are adjusted according to the difference between the predicted output and the label. The goal is to minimize the error between the prediction value and the label, so that the model learns a more accurate mapping relationship.

[0070] Specifically, a back propagation algorithm can be used to propagate the prediction error of the output layer to each hidden layer. According to the error gradient, an optimization algorithm such as Adam optimizer is used to update the weight and bias parameters of each layer. The adjusted model is applied to the training samples again to obtain a new prediction output. The difference between the predicted value and the label is continuously calculated, and the above parameter adjustment process is repeated. Until the difference between the predicted value and the label is less than a third preset threshold, or the number of iterations reaches a preset number, the model training is completed. By continuously iterating and adjusting the parameters, the prediction result gradually approaches the label.

[0071] The preset number is the maximum number of iterations to prevent overfitting of the prediction model. The third preset threshold refers to the maximum allowed difference between the predicted value and the label. When the difference between the predicted value and the label is less than this threshold, it is considered that the model training is completed.

[0072] By screening historical operation data, constructing a prediction model based on a neural network, and continuously optimizing the training, a model can be established that can accurately predict the operating parameters of each device of a thermal power generating unit.

[0073] In an embodiment, the method further comprises: in the case where the difference between the actual value and the predicted value of the second operating data is greater than a first preset threshold, outputting an abnormal prompt and obtaining a user-input corrected value of the second operating data; determining the current power instruction value according to the actual value and the corrected value; and updating the prediction model according to the first operating data and the corrected value of the second operating data.

[0074] Here, the case where the difference between the actual value and the predicted value of the second operating data is greater than the first preset threshold means that the prediction result given by the prediction model has a large deviation from the actual second operating data. In this case, if the current power instruction value is determined according to the predicted value, the final adjusted air supply amount and coal supply amount will have a large fluctuation, which will reduce the service life of the thermal power generating unit. In the case of a large prediction deviation, the user needs to be reminded. At the same time, the user is prompted to manually correct the predicted value of the second operating data. By comparing the actual value and the corrected value of the second operating data, a more accurate current power instruction value can be obtained. The first operating data and the corrected second operating data are used together to update the prediction model. This can make the model adapt to changes in actual working conditions and improve the accuracy and reliability of the prediction.

[0075] By manually correcting the prediction deviation and using the corrected data to continuously optimize the prediction model, the prediction accuracy of the model in actual operation can be continuously improved.

[0076] In an embodiment, the method further comprises: sending the current power instruction value to an automatic generation control system, so that the automatic generation control system adjusts its feedforward control parameters and feedback control parameters according to the current power instruction value.

[0077] It should be understood that, although the historical power instruction value in the first operation data is obtained from the automatic generation control system, a more accurate current power instruction value is obtained through the foregoing prediction model optimization. Therefore, it is necessary to feed back this optimized more accurate current power instruction value to the automatic generation control system.

[0078] The feedforward control parameters are parameters by which the automatic generation control system adjusts the power instruction value in advance according to the predicted power grid load information, and the feedback control parameters are parameters by which the automatic generation control system adjusts the power instruction value according to the deviation between the actual active power value and the power instruction value. After receiving the optimized current power instruction value, the automatic generation control system can adjust the two types of control parameters accordingly, so as to achieve more accurate power output control. By optimizing the current power instruction value through the prediction model and feeding it back to the automatic generation control system, the automatic generation control system can perform feedforward and feedback control according to the more accurate instruction value. Finally, the power output control accuracy of the entire thermal power generating unit is improved.

[0079] In an embodiment, the adjusting the coal supply amount and the air supply amount according to the current power instruction value comprises:

[0080] The current power instruction value is sent to a distributed control system, and the distributed control system is used to control the coal supply system to adjust the coal supply amount and control the air supply system to adjust the air supply amount.

[0081] Here, the optimized current power instruction value is sent to the distributed control system, so that the distributed control system adjusts the parameters of the related subsystems according to this instruction value. The coal supply system controls the fuel supply amount of the boiler, which directly affects the power output of the thermal power generating unit. The distributed control system will adjust the related parameters of the coal supply system, such as the speed of the coal feeder, the coal supply amount, and the like, according to the current power instruction value, so as to meet the power demand. The air supply system controls the air supply amount to the boiler, which also affects the power output of the thermal power generating unit. The distributed control system will adjust the speed of the air supply fan, the air supply amount, and the like, according to the current power instruction value, so as to cooperate with the adjustment of the coal supply system and jointly ensure the accurate power output of the thermal power generating unit.

[0082] Figure 2 is a block diagram of a control device 200 of a thermal power generating unit according to an exemplary embodiment, as shown in Figure 2 The control device 200 of the thermal power generating unit comprises:

[0083] The data acquisition module 210 is configured to acquire operation data of the thermal power unit, wherein the operation data comprises actual values of first operation data and second operation data, and the first operation data comprises one or any multiple of historical power instruction values, grid frequencies, active power actual values, boiler thermal efficiencies, load response times, steam turbine heat rates, thermal power unit power generation coal consumption rates, power supply coal consumption rates, coal feeding system parameters and air supply system parameters, and the second operation data comprises device operation data of the thermal power unit.

[0084] The data prediction module 220 is configured to input the first operation data into a trained prediction model to obtain predicted values of the second operation data.

[0085] The power instruction module 230 is configured to determine a current power instruction value according to the actual values and the predicted values when a difference between the actual values and the predicted values is less than a first preset threshold.

[0086] The thermal power unit adjustment module 240 is configured to adjust coal feeding amounts and air supply amounts according to the current power instruction value.

[0087] Optionally, the data prediction module 220 is specifically configured to:

[0088] The operation data collected by a distributed control system is acquired, wherein the distributed control system transmits the operation data to a data acquisition center through an electronic room server.

[0089] Optionally, the device comprises a prediction model training module configured to:

[0090] The historical operation data of the thermal power unit is acquired.

[0091] The historical operation data in which a difference between an active power actual value and a historical power instruction value is not more than a second preset threshold is screened from the historical operation data as training data.

[0092] According to the training data, a training sample and a label are determined, wherein the training sample comprises one or any multiple of historical power instruction values, grid frequencies, active power actual values, boiler thermal efficiencies, load response times, steam turbine heat rates, thermal power unit power generation coal consumption rates, power supply coal consumption rates, coal feeding system parameters and air supply system parameters, and the label comprises device operation data of the thermal power unit.

[0093] The training sample is input into a neural network model to obtain predicted values.

[0094] According to a difference between the predicted values and the label, parameters of the neural network model are adjusted.

[0095] Return to execute the training sample input to the neural network model, get the predicted value, until the difference between the predicted value and the label is less than a third preset threshold or the number of cycles reaches a preset number, to obtain the trained prediction model.

[0096] Optionally, the apparatus further comprises a correction module configured to:

[0097] In the case where the difference between the actual value and the predicted value of the second running data is greater than a first preset threshold, output an abnormal prompt and obtain a correction value of the second running data input by a user;

[0098] Determine the current power instruction value according to the actual value and the correction value;

[0099] Update the prediction model according to the first running data and the correction value of the second running data.

[0100] Optionally, the apparatus further comprises an output module configured to:

[0101] Send the current power instruction value to an automatic generation control system, so that the automatic generation control system adjusts its feedforward control parameters and feedback control parameters according to the current power instruction value.

[0102] Optionally, the thermal power unit adjustment module 240 is specifically configured to:

[0103] Send the current power instruction value to a distributed control system, and control the coal feeding system to adjust the coal feeding amount and control the air supply system to adjust the air supply amount through the distributed control system.

[0104] As to the apparatus in the above-mentioned embodiments, the specific manners in which various modules perform operations have been described in detail in the embodiments related to the method, and thus will not be described here in detail.

[0105] Figure 3 is a block diagram of an electronic device 300 according to an exemplary embodiment. As shown in Figure 3 The electronic device 300 can include a processor 301 and a memory 302. The electronic device 300 can also include one or more of a multimedia component 303, an input / output (I / O) interface 304, and a communication component 305.

[0106] The processor 301 is configured to control overall operations of the electronic device 300 to complete all or part of the steps of the method for controlling a thermal power generating unit described above. The memory 302 is configured to store various types of data to support operations of the electronic device 300, which can include, for example, instructions for operating any application or method on the electronic device 300, and application-related data, such as contact data, sent and received messages, pictures, audio, video, and the like. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage, a flash memory, a magnetic disk, or an optical disk. The multimedia component 303 can include a screen and an audio component. The screen can be, for example, a touch screen, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 302 or transmitted through the communication component 305. The audio component also includes at least one speaker configured to output audio signals. The I / O interface 304 provides an interface between the processor 301 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 305 is configured to perform wired or wireless communication between the electronic device 300 and other devices. The wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, and the like, or a combination of one or more of them, is not limited herein. Therefore, the corresponding communication component 305 can include a Wi-Fi module, a Bluetooth module, an NFC module, and the like.

[0107] In an exemplary embodiment, the electronic device 300 can be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the above-mentioned method for controlling a thermal power generating unit.

[0108] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the above-mentioned method for controlling a thermal power generating unit. For example, the computer-readable storage medium can be the above-mentioned memory 302 including program instructions, which can be executed by the processor 301 of the electronic device 300 to complete the above-mentioned method for controlling a thermal power generating unit.

[0109] In another exemplary embodiment, a computer program product is also provided, which contains a computer program that can be executed by a programmable device, and the computer program has code portions for executing the above-mentioned method for controlling a thermal power generating unit when executed by the programmable device.

[0110] The preferred embodiments of the present disclosure are described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details in the above-described embodiments. Within the technical concept scope of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and all these simple modifications shall fall within the protection scope of the present disclosure.

[0111] In addition, it should be noted that each specific technical feature described in the above-described specific embodiments can be combined in any appropriate manner without contradiction, and in order to avoid unnecessary repetition, the present disclosure will not make further descriptions on various possible combination manners.

[0112] In addition, any combination of various different embodiments of the present disclosure can also be made, as long as it does not deviate from the idea of the present disclosure, and it shall be considered as the disclosed content of the present disclosure.

Claims

1. A control method of a thermal power generating unit, characterized by, The method comprises: obtaining operation data of a thermal power unit, the operation data comprising actual values of first operation data and second operation data, the first operation data comprising one or any multiple of the following data: historical power instruction value, power grid frequency, active power actual value, boiler thermal efficiency, load response time, steam turbine heat rate, thermal power unit power generation coal consumption rate, power supply coal consumption rate, coal feeding system parameters and air supply system parameters, and the second operation data comprising equipment operation data of the thermal power unit; inputting the first operation data into a trained prediction model to obtain predicted values of the second operation data; in a case where a difference between the actual values and the predicted values is less than a first preset threshold, determining a current power instruction value according to the actual values and the predicted values; adjusting coal feeding amount and air supply amount according to the current power instruction value; the trained prediction model is obtained through the following steps: obtaining historical operation data of a thermal power unit; screening, from the historical operation data, historical operation data in which a difference between an active power actual value and a historical power instruction value is not more than a second preset threshold, as training data; determining training samples and labels according to the training data, the training samples comprising one or any multiple of the following data: historical power instruction value, power grid frequency, active power actual value, boiler thermal efficiency, load response time, steam turbine heat rate, thermal power unit power generation coal consumption rate, power supply coal consumption rate, coal feeding system parameters and air supply system parameters, and the labels comprising equipment operation data of the thermal power unit; inputting the training samples into a neural network model to obtain predicted values; adjusting parameters of the neural network model according to a difference between the predicted values and the labels; returning to performing the inputting of the training samples into the neural network model to obtain predicted values until a difference between the predicted values and the labels is less than a third preset threshold or a cycle number reaches a preset number, to obtain the trained prediction model; in a case where a difference between actual values and predicted values of the second operation data is greater than the first preset threshold, outputting an abnormal prompt and obtaining a corrected value of the second operation data input by a user; determining the current power instruction value according to the actual values and the corrected values; updating the prediction model according to the first operation data and the corrected values of the second operation data; sending the current power instruction value to an automatic generation control system, so that the automatic generation control system adjusts feedforward control parameters and feedback control parameters thereof according to the current power instruction value, wherein the feedforward control parameters are parameters by which the automatic generation control system adjusts the power instruction value in advance according to predicted power grid load information thereof, and the feedback control parameters are parameters by which the automatic generation control system adjusts the power instruction value according to a deviation between the active power actual value and the power instruction value.

2. The method of claim 1, wherein, The obtaining of the operation data of the thermal power unit comprises: obtaining the operation data collected by a distributed control system, wherein the distributed control system transmits the operation data to a data collection center through an electronic room server.

3. The method of claim 1, wherein, The adjusting of the coal feeding amount and the air supply amount according to the current power instruction value comprises: The current power instruction value is sent to a decentralized control system, and the decentralized control system is used to control the coal feeding system to adjust the coal feeding amount and control the air supply system to adjust the air supply amount.

4. A control device for a thermal power generating unit, characterized by comprising: The method comprises the following steps: The data acquisition module is configured to acquire operation data of the thermal power unit, wherein the operation data comprises actual values of first operation data and second operation data, and the first operation data comprises one or any multiple of the following data: historical power instruction value, power grid frequency, active power actual value, boiler thermal efficiency, load response time, steam turbine heat consumption rate, thermal power unit power generation coal consumption rate, power supply coal consumption rate, coal feeding system parameter, and air supply system parameter, and the second operation data comprises equipment operation data of the thermal power unit; The data prediction module is configured to input the first operation data into a trained prediction model to obtain predicted values of the second operation data; The power instruction module is configured to determine a current power instruction value according to the actual values and the predicted values when the difference between the actual values and the predicted values is less than a first preset threshold value; The thermal power unit adjustment module is configured to adjust the coal feeding amount and the air supply amount according to the current power instruction value; The prediction model training module is configured to acquire historical operation data of the thermal power unit; The historical operation data in which the difference between the active power actual value and the historical power instruction value is not more than a second preset threshold value is selected from the historical operation data as training data; The training sample comprises one or any multiple of the following data: historical power instruction value, power grid frequency, active power actual value, boiler thermal efficiency, load response time, steam turbine heat consumption rate, thermal power unit power generation coal consumption rate, power supply coal consumption rate, coal feeding system parameter, and air supply system parameter, and the label comprises the equipment operation data of the thermal power unit; The training sample is input into a neural network model to obtain predicted values; The parameters of the neural network model are adjusted according to the difference between the predicted values and the label; The process of inputting the training sample into the neural network model to obtain predicted values is repeated until the difference between the predicted values and the label is less than a third preset threshold value or the number of cycles reaches a preset number, thereby obtaining the trained prediction model; The correction module is configured to output an abnormal prompt and acquire a correction value of the second operation data when the difference between the actual values and the predicted values of the second operation data is greater than the first preset threshold value; The current power instruction value is determined according to the actual values and the correction values; The prediction model is updated according to the first operation data and the correction values of the second operation data; The output module is configured to send the current power instruction value to an automatic generation control system, so that the automatic generation control system adjusts its feedforward control parameter and feedback control parameter according to the current power instruction value, wherein the feedforward control parameter is a parameter used by the automatic generation control system to adjust the power instruction value in advance according to the predicted power grid load information, and the feedback control parameter is a parameter used by the automatic generation control system to adjust the power instruction value according to the deviation between the active power actual value and the power instruction value.

5. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, which is executed by the processor, implements the steps of the method according to any one of claims 1-3.

6. An electronic device, comprising: comprises: a memory having stored thereon a computer program; a processor configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1-3.

7. A computer program product comprising a computer program, characterized in that, The computer program, which is executed by the processor, implements the steps of the method according to any one of claims 1-3. comprises: a memory having stored thereon a computer program; a processor configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1-3.

Images