Primary frequency modulation control method of thermal power generating unit and related device

Abstract

The invention discloses a primary frequency modulation control method and related device for a thermal power generating unit, and the method comprises the steps: obtaining unit operation data, steam turbine related data and integral electric quantity during the operation of a historical station unit, and the steam turbine related data comprises a steam turbine main control instruction; determining an operation data sample and a correction coefficient label of primary frequency modulation in a normal operation stage of the unit according to the unit operation data, the steam turbine related data and the integral electric quantity, and generating a primary frequency modulation data set; performing correction prediction training on the initial neural network model through the primary frequency modulation data set to obtain an optimized neural network model; performing correction prediction according to real-time related data of unit operation by adopting the optimized neural network model to obtain a primary frequency modulation correction coefficient; and performing primary frequency modulation control on the thermal power generating unit based on the primary frequency modulation correction coefficient. The technical problem that the primary frequency modulation quality is poor due to the fact that the existing primary frequency modulation action cannot meet different working condition requirements in an actual scene can be solved.

Description

Technical Field

[0001] This application relates to the technical field of thermal power generation control, and particularly to a primary frequency modulation control method and related device for a thermal power unit. Background Art

[0002] At present, the primary frequency modulation method of a thermal power unit is that the load instruction is superimposed with the main steam pressure deviation correction value and the frequency difference signal correction value as the set value of the regulator, and the turbine master control instruction is sent to the electro-hydraulic control system DEH to adjust the opening of the turbine control valve. Due to the transformation of the energy structure, in order to ensure the safe and stable operation of the power grid, the requirements for the frequency modulation ability of thermal power units are getting higher and higher.

[0003] During the actual operation of thermal power units, the actual action amount of primary frequency modulation of some units cannot meet the actual needs under different working conditions, which has a negative impact on the stability of the power grid, that is, the traditional frequency difference function and main steam pressure correction function are difficult to meet the primary frequency modulation quality requirements under different working conditions. Summary of the Invention

[0004] This application provides a primary frequency modulation control method and related device for a thermal power unit, which are used to solve the technical problem that the existing primary frequency modulation actions cannot meet the requirements of different working conditions in the actual scenario, resulting in poor primary frequency modulation quality.

[0005] In view of this, the first aspect of this application provides a primary frequency modulation control method for a thermal power unit, including:

[0006] Obtain the unit operation data, turbine-related data, and integrated power during the operation of the historical station unit, where the turbine-related data includes the turbine master control instruction;

[0007] Determine the operation data sample and correction coefficient label of primary frequency modulation during the normal operation stage of the unit according to the unit operation data, the turbine-related data, and the integrated power, and generate a primary frequency modulation data set;

[0008] Correct and predictively train the initial neural network model through the primary frequency modulation data set to obtain an optimized neural network model;

[0009] Use the optimized neural network model to perform correction and prediction according to the real-time relevant data of the unit operation to obtain a primary frequency modulation correction coefficient;

[0010] Perform primary frequency modulation control of the thermal power unit based on the primary frequency modulation correction coefficient.

[0011] Preferably, the obtaining the unit operation data, turbine-related data, and integrated power during the operation of the historical station unit, where the turbine-related data includes the turbine master control instruction, includes:

[0012] When the unit at the historical station is operating and triggers a primary frequency regulation action, collect the unit operation data and steam turbine-related data;

[0013] Calculate the actual integral power and the theoretical integral power through the preset control system logic in the system to obtain the integral power.

[0014] Preferably, for obtaining the unit operation data, steam turbine-related data and integral power when the unit at the historical station is operating, the steam turbine-related data includes the steam turbine master control command, and then further includes:

[0015] Perform data preprocessing operations on the unit operation data, the steam turbine-related data and the integral power, and the data preprocessing operations include data cleaning and normalization processing.

[0016] Preferably, the primary frequency regulation control of the thermal power unit based on the primary frequency regulation correction coefficient includes:

[0017] Multiply the primary frequency regulation correction coefficient by the current steam turbine master control output result to obtain a corrected control output value;

[0018] Perform speed limit processing on the corrected control output value to obtain a speed limit output value;

[0019] Superimpose the speed limit output value onto the feedforward signal of the PID regulator in the steam turbine master control loop to generate a steam turbine master control command;

[0020] Control the steam turbine valve opening through the steam turbine master control command.

[0021] The second aspect of the present application provides a primary frequency regulation control device for a thermal power unit, including:

[0022] A data acquisition unit for acquiring the unit operation data, steam turbine-related data and integral power when the unit at the historical station is operating, and the steam turbine-related data includes the steam turbine master control command;

[0023] A data set generation unit for determining the operation data sample and correction coefficient label of primary frequency regulation during the normal operation stage of the unit according to the unit operation data, the steam turbine-related data and the integral power, and generating a primary frequency regulation data set;

[0024] A model training unit for performing correction prediction training on the initial neural network model through the primary frequency regulation data set to obtain an optimized neural network model;

[0025] A correction prediction unit for performing correction prediction according to the real-time relevant data of the unit operation by using the optimized neural network model to obtain a primary frequency regulation correction coefficient;

[0026] A frequency regulation control unit for performing primary frequency regulation control on the thermal power unit based on the primary frequency regulation correction coefficient.

[0027] Preferably, the data acquisition unit is specifically configured to:

[0028] When the historical unit set is in operation and triggers a primary frequency regulation action, collect the unit operation data and turbine-related data;

[0029] Calculate the actual integral power and the theoretical integral power through the preset control system logic in the system to obtain the integral power.

[0030] Preferably, it further includes:

[0031] A preprocessing unit for performing data preprocessing operations on the unit operation data, the turbine-related data, and the integral power, where the data preprocessing operations include data cleaning and normalization processing.

[0032] Preferably, the frequency regulation control unit is specifically configured to:

[0033] Multiply the primary frequency regulation correction coefficient by the current turbine main control output result to obtain a corrected control output value;

[0034] Perform speed limit processing on the corrected control output value to obtain a speed limit output value;

[0035] Superimpose the speed limit output value on the feedforward signal of the PID regulator in the turbine main control loop to generate a turbine main control command;

[0036] Control the opening of the turbine valve through the turbine main control command.

[0037] The third aspect of the present application provides a primary frequency regulation control device for a thermal power unit, and the device includes a processor and a memory;

[0038] The memory is used to store program codes and transmit the program codes to the processor;

[0039] The processor is used to execute the primary frequency regulation control method for the thermal power unit described in the first aspect according to the instructions in the program codes.

[0040] The fourth aspect of the present application provides a computer-readable storage medium, and the computer-readable storage medium is used to store program codes, and the program codes are used to execute the primary frequency regulation control method for the thermal power unit described in the first aspect.

[0041] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0042] In this application, a primary frequency regulation control method for a thermal power unit is provided, including: obtaining the unit operation data, turbine-related data, and integrated power consumption during the operation of the historical unit, where the turbine-related data includes the turbine main control command; determining the operation data sample and correction coefficient label for primary frequency regulation in the normal operation stage of the unit based on the unit operation data, turbine-related data, and integrated power consumption, and generating a primary frequency regulation data set; correcting and predicting the training of the initial neural network model through the primary frequency regulation data set to obtain an optimized neural network model; using the optimized neural network model to perform correction and prediction based on the real-time relevant data of the unit operation to obtain a primary frequency regulation correction coefficient; and performing primary frequency regulation control on the thermal power unit based on the primary frequency regulation correction coefficient.

[0043] The primary frequency regulation control method for a thermal power unit provided in this application obtains various data at different levels such as the unit operation data, turbine-related data, and integrated power consumption during the unit operation. Then, based on the primary frequency regulation data set composed of these data, the initial neural network model is corrected and predicted for training, enabling the model to learn the correlation between the actual operation data and the correction coefficient. Subsequently, the optimized neural network model can be used to achieve correction and prediction in real-time scenarios, obtaining accurate and reliable primary frequency regulation correction coefficients. This process is not limited by the application scenario and working conditions, so it can meet the primary frequency regulation requirements under all working conditions of the thermal power unit and ensure better frequency regulation quality. Therefore, this application can solve the technical problem that the existing primary frequency regulation actions cannot meet the requirements of different working conditions in the actual scenario, resulting in poor primary frequency regulation quality. Description of the Drawings

[0044] Figure 1 It is a schematic flow chart of a primary frequency regulation control method for a thermal power unit provided in an embodiment of this application;

[0045] Figure 2 It is a schematic structural diagram of a primary frequency regulation control device for a thermal power unit provided in an embodiment of this application;

[0046] Figure 3 It is a schematic diagram of the model training and correction prediction process based on a neural network model provided in an embodiment of this application;

[0047] Figure 4 It is a schematic diagram of the overall control process of the turbine main control in a thermal power unit provided in an embodiment of this application. Detailed Embodiments

[0048] To enable those skilled in the art to better understand the solution of this application, the following will clearly and completely describe the technical solution in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts belong to the scope of protection of this application.

[0049] For ease of understanding, please refer to Figure 1 , an embodiment of a primary frequency regulation control method for a thermal power unit provided by this application, includes:

[0050] Step 101: Obtain the unit operation data, turbine-related data, and integral power when the historical station unit is operating. The turbine-related data includes the turbine master control command.

[0051] Further, step 101 includes:

[0052] When the historical station unit is operating and triggers a primary frequency regulation action, collect the unit operation data and turbine-related data;

[0053] Calculate the actual integral power and the theoretical integral power through the preset control system logic in the system to obtain the integral power.

[0054] It should be noted that since a large amount of historical data is required for model training, obtaining data when the historical station unit is operating and triggers a primary frequency regulation action may refer to the state at the nth trigger. At this time, the unit operation data and turbine-related data can be obtained; among them, the unit operation data includes but is not limited to the main steam pressure, actual load, frequency difference signal, feed water flow, coal feed amount, and total air volume of the unit; and the turbine-related data includes but is not limited to the turbine master control command, regulating stage pressure, and main steam temperature; where the turbine master control command refers to the command sent to the digital electro-hydraulic control system (DEH).

[0055] After the historical station unit is operating and the primary frequency regulation action is triggered and ended, the integral power change rate can be calculated according to the actual integral power and the theoretical integral power calculated based on the preset control system logic. The specific calculation process is as follows:

[0056]

[0057] Further, after step 101, it also includes:

[0058] Perform data preprocessing operations on the unit operation data, turbine-related data, and integral power. The data preprocessing operations include data cleaning and normalization processing.

[0059] To ensure the accuracy and reliability of model training, this embodiment also preprocesses the acquired data to improve data quality. It can be understood that the data preprocessing operations in this embodiment include but are not limited to data cleaning and normalization processing; if it is beneficial to improve data quality, an appropriate preprocessing scheme can be selected or designed by oneself. The data cleaning in this embodiment can eliminate the relevant data generated under abnormal working conditions; while the normalization operation can unify the data with different dimensions into the same data range, facilitating data analysis.

[0060] Step 102: Determine the operation data samples and correction coefficient labels of primary frequency modulation during the normal operation stage of the unit according to the unit operation data, turbine-related data, and integrated power consumption, and generate a primary frequency modulation data set.

[0061] In this embodiment, the unit operation data and turbine-related data after the preprocessing operation are used as the operation data sample Pk, and the integrated power consumption change rate calculated according to the integrated power consumption is used as the correction coefficient label Ck. Combining the operation data sample Pk and the correction coefficient label Ck can generate a primary frequency modulation data set. In this embodiment, the primary frequency modulation data set is divided according to the ratio of 8:2, and a primary frequency modulation training data set and a test data set can be obtained. It can be understood that the data division ratio can be set according to the actual situation, and only an example is given here without limitation.

[0062] Step 103: Perform correction prediction training on the initial neural network model through the primary frequency modulation data set to obtain an optimized neural network model.

[0063] The initial neural network model can be constructed based on neural network frameworks similar to CNN, etc., as long as the model has good prediction performance, low model parameter complexity, and is simple and easy to operate. This embodiment does not limit the selected neural network framework.

[0064] The operation data sample Pk in the primary frequency modulation data set is used as the input of the initial neural network model, while the correction coefficient label Ck is used as the model output; the initial rate of the model is set to 1.0; the activation function is the tanh function; the Dropout parameter is set to 0.8; the mean square error loss function is selected as the loss function; the RMSprop method is selected for parameter update. In addition, the input neurons of the model are set to 9, the hidden layer is set to 80, and the output neurons are set to 1.

[0065] During model training, the model is trained with the training dataset in the primary frequency regulation dataset until the convergence condition is met; then the test dataset is input into the model, and the prediction results are compared with the test samples of the primary frequency regulation correction coefficient to obtain the accuracy of the model. The basis for judging whether the test results are accurate is: (model output correction coefficient - test sample correction coefficient) / model output correction coefficient < 5%; if the accuracy of the model is lower than 98%, the prediction accuracy of the model can be improved by adjusting the number of neurons in the hidden layer. It can be understood that the configuration selections of the training parameters, functions, and methods in the model training stage are all examples, and other selections and designs can also be made according to needs, as long as the model correction prediction training can be achieved.

[0066] Step 104: Use the optimized neural network model to perform correction prediction based on the real-time relevant data of the unit operation to obtain the primary frequency regulation correction coefficient.

[0067] Obtain the real-time relevant data during the unit operation. The real-time relevant data is the same as the historical data obtained, and also includes main steam pressure, actual load, frequency difference signal, turbine master control instruction, regulating stage pressure, main steam temperature, feed water flow, coal feed amount, total air volume, etc. Similar to the historical data, the same preprocessing operations can be performed on the real-time relevant data to ensure the unity of the data type input into the model, and the specific details are not elaborated. Input the real-time relevant data into the optimized neural network model, and the primary frequency regulation correction coefficient can be predicted. For the entire process of predicting the primary frequency regulation correction coefficient based on the neural network model in this embodiment, please refer to Figure 3 , including model training and real-time prediction.

[0068] Step 105: Perform primary frequency regulation control on the thermal power unit based on the primary frequency regulation correction coefficient.

[0069] Further, step 105 includes:

[0070] Multiply the primary frequency regulation correction coefficient by the current turbine master control output result to obtain the corrected control output value;

[0071] Perform speed limit processing on the corrected control output value to obtain the speed limit output value;

[0072] Superimpose the speed limit output value on the feedforward signal of the PID regulator in the turbine master control loop to generate the turbine master control instruction;

[0073] Control the opening of the turbine valve through the turbine master control instruction.

[0074] It should be noted that the primary frequency regulation correction coefficient in this embodiment is obtained based on various operating data of the unit and neural network model prediction, without application scenario and special condition limitations, and can meet the full-condition power generation requirements of thermal power units. By sending the turbine master control command generated based on the primary frequency regulation correction coefficient to the electro-hydraulic control system DEH, stable and reliable control of the turbine valve opening can be achieved. In addition, the set value SP and process variable PV of the PID regulator can be configured based on existing technologies, which will not be elaborated here.

[0075] Please refer to Figure 4 , when applying the primary frequency regulation control method of this embodiment to an actual thermal power unit system, different situations also need to be divided, specifically including the following:

[0076] 1) When the primary frequency regulation input signal is 0, no primary frequency regulation operation is performed;

[0077] 2) When the unit frequency difference signal does not exceed the dead zone set by the function , regardless of whether the optimized neural network model is used to predict the primary frequency regulation correction coefficient, the feedforward signal in the feedforward signal input to the PID regulator of the turbine master control loop is 0, that is, the speed limit output value;

[0078] 3) When the primary frequency regulation input signal is 1, the primary frequency regulation correction coefficient is predicted through the optimized neural network model, and primary frequency regulation control based on the primary frequency regulation correction coefficient is performed;

[0079] 4) When the actual integrated power of the unit is greater than the theoretical integrated power, it is determined whether to perform primary frequency regulation correction by adjusting the function ;

[0080] 5) If the feedforward signal in the feedforward signal input to the PID regulator of the turbine master control loop, that is, the speed limit output value, exceeds the set range, the signal is limited to the preset value by the amplitude limiting module, and the turbine master control value is increased smoothly by the rate limiting module to ensure the safe and stable operation of the unit.

[0081] It can be understood that exceeding the set range includes being less than the minimum set value and greater than the maximum set value. Moreover, for both the amplitude limiting and rate limiting modules, the module parameters can be adjusted as needed, which are not limited in this embodiment. In addition, is a function corresponding to the compensation power set value of the main steam pressure deviation; is a function corresponding to the compensation power set value of the frequency difference signal, is a correction function of the primary frequency regulation feedforward coefficient, is a function corresponding to the feedforward of the primary frequency regulation amount for the frequency difference signal.

[0082] The primary frequency regulation control method for a thermal power unit provided by an embodiment of the present application obtains various data at different levels such as unit operation data, turbine-related data, and integrated power during unit operation, and then corrects and predicts the training of an initial neural network model based on a primary frequency regulation data set composed of these data, enabling the model to learn the correlation between actual operation data and correction coefficients. Then, the correction prediction of the real-time scenario can be realized by optimizing the neural network model, and an accurate and reliable primary frequency regulation correction coefficient can be obtained. This process is not limited by the application scenario and working conditions, so it can meet the primary frequency regulation requirements under all working conditions of the thermal power unit and ensure good frequency regulation quality. Therefore, the embodiment of the present application can solve the technical problem that the existing primary frequency regulation actions cannot meet the requirements of different working conditions in the actual scenario, resulting in poor primary frequency regulation quality.

[0083] For ease of understanding, please refer to Figure 2 , an embodiment of a primary frequency regulation control device for a thermal power unit provided by the present application includes:

[0084] A data acquisition unit 201, configured to acquire unit operation data, turbine-related data, and integrated power during the operation of the historical station unit, where the turbine-related data includes a turbine master control command;

[0085] A data set generation unit 202, configured to determine an operation data sample and a correction coefficient label for primary frequency regulation during the normal operation stage of the unit according to the unit operation data, turbine-related data, and integrated power, and generate a primary frequency regulation data set;

[0086] A model training unit 203, configured to perform correction prediction training on an initial neural network model through the primary frequency regulation data set to obtain an optimized neural network model;

[0087] A correction prediction unit 204, configured to perform correction prediction according to the real-time relevant data of the unit operation by using the optimized neural network model to obtain a primary frequency regulation correction coefficient;

[0088] A frequency regulation control unit 205, configured to perform primary frequency regulation control on the thermal power unit based on the primary frequency regulation correction coefficient.

[0089] Further, the data acquisition unit 201 is specifically configured to:

[0090] When the historical station unit is operating and triggers a primary frequency regulation action, collect unit operation data and turbine-related data;

[0091] Calculate the actual integrated power and the theoretical integrated power through the preset control system logic in the system to obtain the integrated power.

[0092] Further, it further includes:

[0093] The preprocessing unit 206 is used to perform data preprocessing operations on the unit operation data, turbine-related data, and integrated power consumption. The data preprocessing operations include data cleaning and normalization processing.

[0094] Further, the frequency modulation control unit 205 is specifically used for:

[0095] Multiply the primary frequency modulation correction coefficient by the current turbine main control output result to obtain a corrected control output value;

[0096] Perform speed limit processing on the corrected control output value to obtain a speed limit output value;

[0097] Superimpose the speed limit output value on the feedforward signal of the PID regulator in the turbine main control loop to generate a turbine main control command;

[0098] Control the opening of the turbine valve through the turbine main control command.

[0099] This application also provides a primary frequency modulation control device for a thermal power unit. The device includes a processor and a memory;

[0100] The memory is used to store program code and transmit the program code to the processor;

[0101] The processor is used to execute the primary frequency modulation control method for the thermal power unit in the above method embodiment according to the instructions in the program code.

[0102] This application also provides a computer-readable storage medium. The computer-readable storage medium is used to store program code, and the program code is used to execute the primary frequency modulation control method for the thermal power unit in the above method embodiment.

[0103] In several embodiments provided by this application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0104] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] In addition, in each embodiment of the present application, each functional unit may be integrated into a processing unit, may exist separately as individual physical units, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0106] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (English full name: Read-Only Memory, English abbreviation: ROM), random access memories (English full name: Random Access Memory, English abbreviation: RAM), magnetic disks, or optical discs that can store program codes.

[0107] As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

Claims

1. A primary frequency modulation control method for a thermal power unit, characterized in that: include: Acquire the unit operation data, steam turbine related data and integrated power when the unit is running at the historical station, wherein the steam turbine related data includes the steam turbine master control instruction; Determine the operation data sample and correction coefficient label of the primary frequency regulation during the normal operation phase of the unit according to the unit operation data, the steam turbine related data and the integrated power, and generate a primary frequency regulation data set; Performing correction prediction training on the initial neural network model through the primary frequency modulation data set to obtain an optimized neural network model; The optimized neural network model is used to perform correction prediction according to the real-time relevant data of the unit operation to obtain a primary frequency regulation correction coefficient; The primary frequency regulation control of the thermal power unit is performed based on the primary frequency regulation correction coefficient.

2. The primary frequency modulation control method of a thermal power unit according to claim 1, characterized in that: The acquisition of the unit operation data, turbine-related data and integrated power during the operation of the unit at the historical station, wherein the turbine-related data includes the turbine master control instructions, includes: When the historical station unit is running and triggers a frequency regulation action, the unit operation data and steam turbine related data are collected; The actual integrated power and the theoretical integrated power are calculated by the preset control system logic in the system to obtain the integrated power.

3. The primary frequency modulation control method of a thermal power unit according to claim 1, characterized in that: The acquisition of the unit operation data, turbine-related data and integrated power during the operation of the historical station unit, wherein the turbine-related data includes the turbine master control instruction, further includes: A data preprocessing operation is performed on the unit operation data, the steam turbine related data and the integrated electrical quantity, and the data preprocessing operation includes data cleaning and normalization processing.

4. The primary frequency modulation control method of a thermal power unit according to claim 1, characterized in that: The primary frequency regulation control of the thermal power unit based on the primary frequency regulation correction coefficient includes: Multiplying the primary frequency modulation correction coefficient by the current turbine main control output result to obtain a corrected control output value; Performing speed limit processing on the corrected control output value to obtain a speed limit output value; The speed limit output value is added to the feedforward signal of the PID regulator of the steam turbine main control loop to generate a steam turbine main control instruction; The steam turbine valve opening is controlled by the steam turbine master control instruction.

5. A primary frequency modulation control device for a thermal power unit, characterized in that: include: A data acquisition unit, used to acquire the unit operation data, steam turbine related data and integrated power when the unit is running at the historical station, wherein the steam turbine related data includes the steam turbine master control instruction; A data set generating unit, configured to determine the operating data samples and correction coefficient labels of the primary frequency regulation during the normal operating phase of the unit according to the unit operating data, the steam turbine related data and the integrated power, and generate a primary frequency regulation data set; A model training unit, used to perform correction prediction training on the initial neural network model through the primary frequency modulation data set to obtain an optimized neural network model; A correction prediction unit, used to use the optimized neural network model to perform correction prediction according to the real-time relevant data of the unit operation to obtain a primary frequency modulation correction coefficient; A frequency regulation control unit is used to perform primary frequency regulation control of the thermal power unit based on the primary frequency regulation correction coefficient.

6. The primary frequency modulation control device of a thermal power unit according to claim 5, characterized in that: The data acquisition unit is specifically used for: When the historical station unit is running and triggers a frequency regulation action, the unit operation data and steam turbine related data are collected; The actual integrated power and the theoretical integrated power are calculated by the preset control system logic in the system to obtain the integrated power.

7. The primary frequency modulation control device of a thermal power unit according to claim 5, characterized in that: Also includes: The preprocessing unit is used to perform data preprocessing operations on the unit operation data, the steam turbine related data and the integrated electrical quantity, wherein the data preprocessing operations include data cleaning and normalization processing.

8. The primary frequency modulation control device of a thermal power unit according to claim 5, characterized in that: The frequency modulation control unit is specifically used for: Multiplying the primary frequency modulation correction coefficient by the current turbine main control output result to obtain a corrected control output value; Performing speed limit processing on the corrected control output value to obtain a speed limit output value; The speed limit output value is added to the feedforward signal of the PID regulator of the steam turbine main control loop to generate a steam turbine main control instruction; The steam turbine valve opening is controlled by the steam turbine master control instruction.

9. A primary frequency modulation control device for a thermal power unit, characterized in that: The device comprises a processor and a memory; The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the primary frequency regulation control method of a thermal power unit according to any one of claims 1 to 4 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program codes, and the program codes are used to execute the primary frequency regulation control method for a thermal power unit according to any one of claims 1 to 4.

Images