Main steam pressure prediction model training method, control method and corresponding device
By training the main steam pressure prediction model and applying it to the boiler control circuit, the problem of main steam pressure control deviation of the boiler is solved and the stability of the boiler is improved.
Patent Information
- Application Number
- CN202311586198.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-24
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2043-11-24
AI Technical Summary
In thermal power units, the prior art has deviations in the control of the boiler main steam pressure control circuit, which may lead to problems such as boiler overtemperature, overpressure and parameter out of control.
By training the main steam pressure prediction model, the model is updated using historical operating parameter data and measured values, fault data is eliminated, characteristic values are extracted, inputted into the target prediction model, the main steam pressure prediction value is generated, and the prediction value is determined based on the predicted value and measured value. The loss value is updated until the preset condition is reached and applied to the main steam pressure control circuit.
It reduces the boiler's overtemperature, overpressure and out of control parameters, and improves the stability of boiler operation.
Smart Images

Figure CN117806242B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of computer technology, and in particular to a training method, a control method and a corresponding device of a main steam pressure prediction model. Background Art
[0002] Thermal power units are devices that mainly use fuel combustion to generate heat energy, use the heat energy to generate steam, and use the steam to drive generators to generate electricity.
[0003] In the related art, the main steam pressure control loop of the boiler in the thermal power unit is controlled by combining feedforward control with proportional-differential-integral feedback control. However, when this method is used to control the main steam pressure control loop, the main steam pressure generated by the boiler may deviate, which may cause the boiler to overheat, overpressure, parameter loss of control, etc. in serious cases. Summary of the invention
[0004] The purpose of the present disclosure is to provide a training method, a control method and a corresponding device for a steam pressure prediction model to solve the problems existing in the related art.
[0005] In order to achieve the above object, the present disclosure provides a training method for a main steam pressure prediction model, the training method comprising:
[0006] Determine performance data and a main steam pressure measured value, wherein the performance data is operating parameter data of the boiler in a historical time period, and the main steam pressure measured value is a main steam pressure measured value of the boiler in the historical time period;
[0007] Inputting the performance data into the target prediction model to obtain a main steam pressure prediction value;
[0008] determining a loss value according to the measured value of the main steam pressure and the predicted value of the main steam pressure;
[0009] The target prediction model is updated according to the loss value until the target prediction model meets a preset condition.
[0010] Optionally, the inputting the performance data into the target prediction model to obtain a main steam pressure prediction value includes:
[0011] Eliminate fault data from the performance data to obtain first sub-performance data;
[0012] Extracting characteristic values from the first sub-performance data by filtering to obtain second sub-performance data;
[0013] The second sub-performance data is input into the target prediction model to obtain the main steam pressure prediction value.
[0014] In a second aspect, the present disclosure further provides a method for controlling main steam pressure, the control method comprising:
[0015] Determine the boiler's target sliding pressure curve and real-time performance parameters;
[0016] Inputting the real-time performance parameter into a target prediction model to obtain target prediction data, wherein the target prediction model is obtained by training according to the training method provided in the first aspect of the present disclosure;
[0017] Determining an operating sliding pressure curve according to the target prediction data and the target sliding pressure curve;
[0018] The main steam pressure control loop of the boiler is controlled by the operating sliding pressure curve.
[0019] Optionally, determining an operating sliding-pressure curve according to the target prediction data and the target sliding-pressure curve includes:
[0020] Determining a target prediction curve according to the target prediction data;
[0021] An operating sliding pressure curve is determined according to the target prediction curve and the target sliding pressure curve.
[0022] Optionally, the target prediction curve includes a target prediction upper limit curve and a target prediction lower limit curve, and determining an operating sliding pressure curve according to the target prediction curve and the target sliding pressure curve includes:
[0023] Determining a target prediction area according to the target prediction upper limit curve and the target prediction lower limit curve;
[0024] The target sliding pressure curve within the target prediction region is determined as the operating sliding pressure curve.
[0025] Optionally, determining the target sliding pressure curve includes:
[0026] determining an operating load of the boiler;
[0027] The target sliding pressure curve is determined according to the operating load and a preset corresponding relationship, wherein the preset corresponding relationship is used to characterize the corresponding relationship between the operating load and the sliding pressure curve.
[0028] In a third aspect, the present disclosure further provides a training device for a main steam pressure prediction model, the training device comprising a first determination module, a first calculation module, a second determination module, and an update module;
[0029] The first determination module is used to determine performance data and a main steam pressure measured value, wherein the performance data is the operating parameter data of the boiler in a historical time period, and the main steam pressure measured value is the main steam pressure measured value of the boiler in the historical time period;
[0030] The first calculation module is used to input the performance data into the target prediction model to obtain a main steam pressure prediction value;
[0031] The second determination module is used to determine the loss value according to the measured value of the main steam pressure and the predicted value of the main steam pressure;
[0032] The updating module is used to update the target prediction model according to the loss value until the target prediction model meets a preset condition.
[0033] Optionally, the first calculation module includes:
[0034] A data elimination module, used to eliminate faulty data in the performance data to obtain first sub-performance data;
[0035] A filtering module, used for extracting characteristic values from the first sub-performance data by filtering to obtain second sub-performance data;
[0036] The third calculation module is used to input the second sub-performance data into the target prediction model to obtain the main steam pressure prediction value.
[0037] In a fourth aspect, the present disclosure further provides a main steam pressure control device, the control device comprising a third determination module, a second calculation module, a fourth determination module and a control module;
[0038] The third determination module is used to determine the target sliding pressure curve and real-time performance parameters of the boiler;
[0039] The second calculation module is used to input the real-time performance parameter into a target prediction model to obtain target prediction data, wherein the target prediction model is obtained by training according to the training method provided in the first aspect or the training device provided in the fourth aspect of the present disclosure;
[0040] The fourth determination module is used to determine an operating sliding pressure curve according to the target prediction data and the target sliding pressure curve;
[0041] The control module is used to control the main steam pressure control loop of the boiler through the operating sliding pressure curve.
[0042] Optionally, the fourth determining module includes:
[0043] A first determination submodule, used to determine a target prediction curve according to the target prediction data;
[0044] The second determination submodule is used to determine an operating sliding pressure curve according to the target prediction curve and the target sliding pressure curve.
[0045] Optionally, the target prediction curve includes a target prediction upper limit curve and a target prediction lower limit curve, and the first determination submodule includes:
[0046] A third determination submodule is used to determine a target prediction area according to the target prediction upper limit curve and the target prediction lower limit curve;
[0047] The fourth determining submodule is used to determine the target sliding pressure curve in the target prediction area as the operating sliding pressure curve.
[0048] Optionally, the third determining module includes:
[0049] A fifth determination submodule, used to determine the operating load of the boiler;
[0050] The sixth determination submodule is used to determine the target sliding pressure curve according to the operating load and a preset corresponding relationship, wherein the preset corresponding relationship is used to characterize the corresponding relationship between the operating load and the sliding pressure curve.
[0051] In a fifth aspect, the present disclosure further provides a non-temporary computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the training method steps provided in the first aspect or the control method steps provided in the second aspect of the present disclosure.
[0052] A sixth aspect is an electronic device, comprising:
[0053] a memory having a computer program stored thereon;
[0054] A processor is used to execute the computer program in the memory to implement the training method steps provided in the first aspect or the control method steps provided in the second aspect of the present disclosure.
[0055] Through the above technical solution, the operating parameter data of the boiler in the historical time period is input into the target prediction model, the target prediction model is trained, the main steam pressure prediction value is obtained, and then the loss value is determined according to the main steam pressure measured value and the main steam pressure prediction value, and the target prediction model is updated by the loss value. The target prediction model obtained by the training can be applied to the main steam pressure control loop of the boiler to control the main steam pressure control loop of the boiler, thereby reducing the occurrence of boiler overtemperature, overpressure, parameter loss of control, etc., and improving the stability of boiler operation.
[0056] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings:
[0058] Figure 1 It is a schematic diagram showing a training method of a main steam pressure prediction model according to an exemplary embodiment of the present disclosure.
[0059] Figure 2 is a schematic diagram showing a method for controlling main steam pressure according to an exemplary embodiment of the present disclosure.
[0060] Figure 3 is a schematic diagram showing determination of an operating sliding pressure curve according to an exemplary embodiment of the present disclosure.
[0061] Figure 4 is a schematic diagram showing a training device for a main steam pressure prediction model according to an exemplary embodiment of the present disclosure.
[0062] Figure 5 is a schematic diagram showing a main steam pressure control device according to an exemplary embodiment of the present disclosure.
[0063] Figure 6 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION
[0064] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.
[0065] In the related art, when controlling the boiler control loop in a thermal power unit, a corresponding sliding pressure curve is matched according to the operating load of the boiler, and the boiler operates according to the sliding pressure curve. The sliding pressure curve is a curve used to characterize the combustion characteristics and performance of the boiler during operation.
[0066] The inventors have discovered that when this method is used to control the control loop of the boiler's main steam pressure, the parameters of the automatic gain control are constantly changing, which may cause deviations in the main steam pressure generated by the boiler. In severe cases, this may lead to boiler overheating, overpressure, and parameter loss of control.
[0067] In view of this, the present disclosure provides a method to solve the problems in the related art: since the parameters of the automatic gain control are constantly changing, the main steam pressure generated by the boiler may deviate, which may cause boiler overtemperature, overpressure, parameter loss of control, etc. in severe cases.
[0068] like Figure 1 As shown, Figure 1 is a schematic diagram showing a training method of a main steam pressure prediction model according to an exemplary embodiment of the present disclosure, with reference to Figure 1 ,include:
[0069] S101: Determine performance data and a main steam pressure actual measurement value, wherein the performance data is operating parameter data of the boiler in a historical period, and the main steam pressure actual measurement value is a main steam pressure actual measurement value of the boiler in the historical period;
[0070] S102: Inputting the performance data into the target prediction model to obtain a main steam pressure prediction value;
[0071] S103: determining a loss value according to the measured value of the main steam pressure and the predicted value of the main steam pressure;
[0072] S104: updating the target prediction model according to the loss value until the target prediction model meets a preset condition.
[0073] Through the above technical solution, the operating parameter data of the boiler in the historical time period is input into the target prediction model, the target prediction model is trained, the main steam pressure prediction value is obtained, and then the loss value is determined according to the main steam pressure measured value and the main steam pressure prediction value, and the target prediction model is updated by the loss value. The target prediction model obtained by the training can be applied to the main steam pressure control loop of the boiler to control the main steam pressure control loop of the boiler, thereby reducing the occurrence of boiler overtemperature, overpressure, parameter loss of control, etc., and improving the stability of boiler operation.
[0074] In order to enable those skilled in the art to better understand the training method of the main steam pressure prediction model provided by the present disclosure, the above steps are described in detail with examples below.
[0075] For example, the performance data may be parameter data collected during the operation of the boiler in a historical time period, and the parameter data may include operation data such as the boiler's operation load data, fuel quantity data, air supply quantity data, water supply quantity data, and flue gas oxygen content data. The load data may be data obtained at 50%, 60%, 70%, 80%, 90%, and 100% load sections, respectively. The main steam pressure measured value may be the pressure of the steam generated by the boiler, and the main steam pressure measured value may be obtained by measuring the operation of the boiler in a historical time period.
[0076] The target prediction model may be an RBF (Radial Basis Function) neural network model or an MLP (Multilayer Perceptron) neural network model, which is not specifically limited in the embodiments of the present disclosure. In the target prediction model, an activation function, the number of hidden layers, and the number of nodes in each layer are established.
[0077] In the disclosed embodiment, the performance data and the measured value of the main steam pressure can be determined first. Then, the performance data is input into the target prediction model for training to obtain the predicted value of the main steam pressure. In the process of training the target prediction model, overfitting can be prevented by using cross-validation methods and early stopping techniques.
[0078] Afterwards, the loss value can be determined based on the measured value of the main steam pressure and the predicted value of the main steam pressure. The target prediction model can be updated by the loss value until the target prediction model reaches the preset condition and stops updating. The preset condition can be that the difference between the predicted value of the main steam pressure and the measured value of the main steam pressure approaches zero.
[0079] By continuously updating the target prediction model until the preset conditions are met, the trained target prediction model can be applied to the boiler main steam pressure control loop to control the main steam pressure control loop, thereby reducing the occurrence of boiler overtemperature, overpressure, parameter loss of control, etc., and improving the stability of boiler operation.
[0080] In a possible manner, the performance data is input into a target prediction model to obtain a main steam pressure prediction value, including:
[0081] Eliminate fault data from the performance data to obtain first sub-performance data;
[0082] Extracting characteristic values from the first sub-performance data by filtering to obtain second sub-performance data;
[0083] The second sub-performance data is input into the target prediction model to obtain a main steam pressure prediction value.
[0084] It should be understood that the fault data may be abnormal data such as missing fragments of data, blank data or duplicate data. The acquired performance data may include fault data, which may have a certain impact on the training results during the training process. Therefore, the fault data in the performance data can be removed by the standard deviation method to obtain the first sub-performance data.
[0085] After obtaining the first sub-performance data, the characteristic value in the first sub-performance data can be extracted by filtering to obtain the second sub-performance data. The second sub-performance data is input into the target prediction model to obtain the main steam pressure prediction value.
[0086] By eliminating the fault data in the performance data, extracting the feature value in the first sub-performance data to obtain the second sub-performance data, and inputting the second sub-performance data into the target prediction model to obtain the main steam pressure prediction value, the calculation result of the target prediction model trained by the training method can be made more accurate.
[0087] Based on the same concept, the present disclosure also provides a method for controlling the main steam pressure of a boiler. Figure 2 As shown, Figure 2 is a schematic diagram showing a method for controlling main steam pressure according to an exemplary embodiment of the present disclosure, with reference to Figure 2 , the control method comprises:
[0088] S201: Determine the target sliding pressure curve and real-time performance parameters of the boiler;
[0089] S202: inputting the real-time performance parameter into a target prediction model to obtain target prediction data, wherein the target prediction model is obtained by training according to the training method of the main steam pressure prediction model provided by an embodiment of the present disclosure;
[0090] S203: Determine an operating sliding pressure curve according to the target prediction data and the target sliding pressure curve;
[0091] S204: Control the main steam pressure control loop of the boiler by running the sliding pressure curve.
[0092] For example, during the operation of the boiler, the target sliding pressure operation curve and the real-time performance parameters can be determined according to the operating load of the boiler. The real-time performance parameters can be real-time operation data such as real-time fuel quantity data, real-time air supply quantity data, water supply quantity data, and flue gas oxygen content data during the operation of the boiler. Afterwards, the real-time performance data can be input into the target prediction model to obtain the target prediction data, wherein the target prediction model can be obtained by training according to the training method of the main steam pressure prediction model provided in the embodiment of the present disclosure.
[0093] Afterwards, an operating sliding pressure curve can be obtained according to the target prediction data and the target sliding pressure curve, and the main steam pressure control loop can be controlled by the operating sliding pressure curve. When the operating sliding pressure curve is obtained according to the target prediction data and the target sliding pressure curve, the operating sliding pressure curve can be determined according to the relationship between the two curves by drawing the target prediction data into a curve, and the embodiments of the present disclosure do not make specific limitations on this.
[0094] By obtaining the operating sliding pressure curve based on the target prediction data and the target sliding pressure curve, and controlling the main steam pressure control loop of the boiler through the operating sliding pressure curve, the amplitude of the main control adjustment during the operation of the boiler can be reduced, the deviation of the main steam pressure can be reduced, and the stability of the boiler operation can be ensured.
[0095] In a possible manner, determining an operating sliding pressure curve according to the target prediction data and the target sliding pressure curve includes:
[0096] Determining a target prediction curve according to the target prediction data;
[0097] An operating sliding pressure curve is determined according to the target prediction curve and the target sliding pressure curve.
[0098] It should be understood that after obtaining the target prediction data, a target prediction curve can be drawn according to the target prediction data, and the target prediction curve and the target sliding pressure curve can be drawn in a table of the same coordinate system, and the target prediction curve can be determined according to the drawn curve. When determining the target prediction curve according to the drawn curve, two regions can be respectively formed according to the two curves, and the target sliding pressure curve in the overlapping region of the two regions is used as the target prediction curve, and the embodiments of the present disclosure do not make specific limitations on this.
[0099] In a possible manner, the target prediction curve includes a target prediction upper limit curve and a target prediction lower limit curve. According to the target prediction curve and the target sliding pressure curve, determining the operating sliding pressure curve includes:
[0100] Determine the target prediction area according to the target prediction upper limit curve and the target prediction lower limit curve;
[0101] The target sliding pressure curve within the target prediction area is determined as the operating sliding pressure curve.
[0102] It should be understood that the target prediction data can be divided into target prediction upper limit data and target prediction lower limit data. Figure 3 As shown, the target prediction upper limit curve can be obtained in the coordinate system according to the target prediction upper limit data, and the target prediction lower limit curve can be obtained in the coordinate system according to the target prediction lower limit data. Then, the target prediction area can be obtained in the coordinate system according to the target prediction upper limit curve and the target prediction lower limit curve.
[0103] The target sliding pressure area can be obtained in the same coordinate system according to the target sliding pressure curve. The target sliding pressure area can be determined within the normal range according to the target sliding pressure curve. For example, Figure 3As shown in the figure, when the normal error range of the target sliding pressure curve is ±2Mpa, the target sliding pressure curve can be moved up by 2Mpa as a whole to obtain the target sliding pressure upper limit curve, and the target sliding pressure curve can be moved down by 2Mpa as a whole to obtain the target sliding pressure lower limit curve. The target sliding pressure area can be obtained according to the target sliding pressure upper limit curve and the target sliding pressure lower limit curve. Then, the target sliding pressure curve in the area where the target sliding pressure area overlaps with the target prediction area can be determined as the operating sliding pressure curve.
[0104] By determining the operating sliding pressure curve by combining the target prediction curve with the target sliding pressure curve, and using the operating sliding pressure curve to control the main steam pressure control loop of the boiler, the occurrence of boiler overtemperature, overpressure, parameter loss of control, etc. can be reduced, thereby improving the stability of boiler operation.
[0105] In a possible manner, determining the target sliding pressure curve includes:
[0106] determining an operating load of the boiler;
[0107] The target sliding pressure curve is determined according to the operating load and a preset corresponding relationship, wherein the preset corresponding relationship is used to characterize the corresponding relationship between the operating load and the sliding pressure curve.
[0108] It should be understood that the predicted corresponding relationship may be the relationship between the operating load and the sliding pressure curve, wherein one operating load may correspond to one sliding pressure curve, multiple operating loads may correspond to one sliding pressure curve, or multiple operating loads may correspond to different sliding pressure curves, which is not specifically limited in the embodiments of the present disclosure.
[0109] During the operation of the boiler, the operating load of the boiler is firstly obtained, and then the corresponding sliding pressure curve can be matched in a preset corresponding relationship according to the operating load, and the matched sliding pressure curve is the target sliding pressure curve.
[0110] Based on the same concept, the present disclosure also provides a training device 400 for a boiler main steam pressure prediction model. Figure 4 , the training device 400 includes a first determination module 401, a first calculation module 402, a second determination module 403 and an update module 404;
[0111] The first determination module 401 is used to determine performance data and a main steam pressure measured value, wherein the performance data is the operating parameter data of the boiler in a historical time period, and the main steam pressure measured value is the main steam pressure measured value of the boiler in the historical time period;
[0112] The first calculation module 402 is used to input the performance data into the target prediction model to obtain a main steam pressure prediction value;
[0113] The second determination module 403 is used to determine the loss value according to the measured value of the main steam pressure and the predicted value of the main steam pressure;
[0114] The updating module 404 is used to update the target prediction model according to the loss value until the target prediction model meets a preset condition.
[0115] Optionally, the first calculation module 402 includes:
[0116] A data elimination module, used to eliminate faulty data in the performance data to obtain first sub-performance data;
[0117] A filtering module, used for extracting characteristic values from the first sub-performance data by filtering to obtain second sub-performance data;
[0118] The third calculation module is used to input the second sub-performance data into the target prediction model to obtain the main steam pressure prediction value.
[0119] Based on the same concept, the present disclosure also provides a control device 500 for the main steam pressure of a boiler, referring to Figure 5 , the control device 500 includes a third determination module 501, a second calculation module 502, a fourth determination module 503 and a control module 504;
[0120] The third determination module 501 is used to determine the target sliding pressure curve and real-time performance parameters of the boiler;
[0121] The second calculation module 502 is used to input the real-time performance parameter into the target prediction model to obtain target prediction data, wherein the target prediction model is obtained by training according to the main steam pressure prediction model training method provided by the embodiment of the present disclosure or the main steam pressure prediction model training device provided by the embodiment of the present disclosure;
[0122] The fourth determination module 503 is used to determine an operating sliding pressure curve according to the target prediction data and the target sliding pressure curve;
[0123] The control module 504 is used to control the main steam pressure control loop of the boiler through the operating sliding pressure curve.
[0124] Optionally, the fourth determining module 503 includes:
[0125] A first determination submodule, used to determine a target prediction curve according to the target prediction data;
[0126] The second determination submodule is used to determine an operating sliding pressure curve according to the target prediction curve and the target sliding pressure curve.
[0127] Optionally, the target prediction curve includes a target prediction upper limit curve and a target prediction lower limit curve, and the first determination submodule includes:
[0128] A third determination submodule is used to determine a target prediction area according to the target prediction upper limit curve and the target prediction lower limit curve;
[0129] The fourth determining submodule is used to determine the target sliding pressure curve in the target prediction area as the operating sliding pressure curve.
[0130] Optionally, the third determining module 501 includes:
[0131] A fifth determination submodule, used to determine the operating load of the boiler;
[0132] The sixth determination submodule is used to determine the target sliding pressure curve according to the operating load and a preset corresponding relationship, wherein the preset corresponding relationship is used to characterize the corresponding relationship between the operating load and the sliding pressure curve.
[0133] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0134] Based on the same concept, the present disclosure also provides a non-temporary computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, it implements the training method of the main steam pressure prediction model provided by the embodiment of the present disclosure or the main steam pressure control method steps provided by the embodiment of the present disclosure.
[0135] Based on the same concept, the present disclosure also provides an electronic device, including:
[0136] a memory having a computer program stored thereon;
[0137] A processor is used to execute the computer program in the memory to implement the training method of the main steam pressure prediction model or the main steam pressure control method steps provided in the embodiment of the present disclosure.
[0138] Figure 6 FIG. 6 is a block diagram of an electronic device 600 according to an exemplary embodiment. Figure 6 As shown, the electronic device 600 may include: a processor 601 , a memory 602 . The electronic device 600 may also include one or more of a multimedia component 603 , an input / output (I / O) interface 604 , and a communication component 605 .
[0139] The processor 601 is used to control the overall operation of the electronic device 600 to complete all or part of the steps of the training method of the main steam pressure prediction model or the control method of the main steam pressure. The memory 602 is used to store various types of data to support the operation of the electronic device 600. For example, these data may include instructions for any application or method used to operate on the electronic device 600, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 602 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 603 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, which is used to receive external audio signals. The received audio signal may be further stored in the memory 602 or sent through the communication component 605. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 604 provides an interface between the processor 601 and other interface modules, and the above-mentioned other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 605 is used for wired or wireless communication between the electronic device 600 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 605 may include: Wi-Fi module, Bluetooth module, NFC module, etc.
[0140] In an exemplary embodiment, the electronic device 600 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned main steam pressure prediction model training method or main steam pressure control method.
[0141] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the training method of the main steam pressure prediction model or the main steam pressure control method described above are implemented. For example, the computer-readable storage medium may be the memory 602 including the program instructions, and the program instructions may be executed by the processor 601 of the electronic device 600 to complete the training method of the main steam pressure prediction model or the main steam pressure control method described above.
[0142] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.
[0143] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.
[0144] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.
Claims
1. A training method for a main steam pressure prediction model, characterized in that: The training method comprises: Determine performance data and a main steam pressure measured value, wherein the performance data is operating parameter data of the boiler in a historical time period, and the main steam pressure measured value is a main steam pressure measured value of the boiler in the historical time period; Inputting the performance data into a target prediction model to obtain a main steam pressure prediction value; Determining a loss value according to the measured value of the main steam pressure and the predicted value of the main steam pressure; Updating the target prediction model according to the loss value until the target prediction model meets a preset condition; Wherein, the target prediction model is used to obtain target prediction data according to the real-time performance parameters of the boiler, and the target prediction data is used to determine a target prediction curve, and the target prediction curve includes a target prediction upper limit curve and a target prediction lower limit curve, and the target prediction upper limit curve and the target prediction lower limit curve are used to determine a target prediction area, and the target sliding pressure curve of the boiler in the target prediction area is used to determine an operating sliding pressure curve, and the operating sliding pressure curve is used to control the main steam pressure control loop of the boiler; The operating sliding pressure curve is a target sliding pressure curve in an area where a target sliding pressure area overlaps with the target prediction area, and the target sliding pressure area is determined within a normal range difference according to the target prediction curve.
2. The training method according to claim 1, characterized in that: The step of inputting the performance data into the target prediction model to obtain a main steam pressure prediction value includes: Eliminate fault data from the performance data to obtain first sub-performance data; Extracting characteristic values from the first sub-performance data by filtering to obtain second sub-performance data; The second sub-performance data is input into the target prediction model to obtain the main steam pressure prediction value.
3. A method for controlling main steam pressure, characterized in that: The control method comprises: Determine the boiler's target sliding pressure curve and real-time performance parameters; Inputting the real-time performance parameter into a target prediction model to obtain target prediction data, wherein the target prediction model is obtained by training according to the training method of claim 1 or 2; Determining an operating sliding pressure curve according to the target prediction data and the target sliding pressure curve; Controlling the main steam pressure control loop of the boiler through the operating sliding pressure curve; Determining an operating sliding pressure curve according to the target prediction data and the target sliding pressure curve includes: Determining a target prediction curve according to the target prediction data; Determining an operating sliding pressure curve according to the target prediction curve and the target sliding pressure curve; The target prediction curve includes a target prediction upper limit curve and a target prediction lower limit curve, and determining the operating sliding pressure curve according to the target prediction curve and the target sliding pressure curve includes: Determining a target prediction area according to the target prediction upper limit curve and the target prediction lower limit curve; The target sliding pressure curve within the target prediction region is determined as the operating sliding pressure curve.
4. The control method according to claim 3, characterized in that: Determining the target sliding pressure curve of the boiler includes: determining an operating load of the boiler; The target sliding pressure curve is determined according to the operating load and a preset corresponding relationship, wherein the preset corresponding relationship is used to characterize the corresponding relationship between the operating load and the sliding pressure curve.
5. A training device for a main steam pressure prediction model, characterized in that: The training device includes a first determination module, a first calculation module, a second determination module and an update module; The first determination module is used to determine performance data and a main steam pressure measured value, wherein the performance data is the operating parameter data of the boiler in a historical time period, and the main steam pressure measured value is the main steam pressure measured value of the boiler in the historical time period; The first calculation module is used to input the performance data into the target prediction model to obtain a main steam pressure prediction value; The second determination module is used to determine the loss value according to the measured value of the main steam pressure and the predicted value of the main steam pressure; The updating module is used to update the target prediction model according to the loss value until the target prediction model meets the preset condition; Wherein, the target prediction model is used to obtain target prediction data according to the real-time performance parameters of the boiler, and the target prediction data is used to determine a target prediction curve, and the target prediction curve includes a target prediction upper limit curve and a target prediction lower limit curve, and the target prediction upper limit curve and the target prediction lower limit curve are used to determine a target prediction area, and the target sliding pressure curve of the boiler in the target prediction area is used to determine an operating sliding pressure curve, and the operating sliding pressure curve is used to control the main steam pressure control loop of the boiler; The operating sliding pressure curve is a target sliding pressure curve in an area where a target sliding pressure area overlaps with the target prediction area, and the target sliding pressure area is determined within a normal range difference according to the target prediction curve.
6. The training device according to claim 5, characterized in that The first calculation module includes: A data elimination module, used to eliminate faulty data in the performance data to obtain first sub-performance data; A filtering module, used for extracting characteristic values from the first sub-performance data by filtering to obtain second sub-performance data; The third calculation module is used to input the second sub-performance data into the target prediction model to obtain the main steam pressure prediction value.
7. A main steam pressure control device, characterized in that: The control device includes a third determination module, a second calculation module, a fourth determination module and a control module; The third determination module is used to determine the target sliding pressure curve and real-time performance parameters of the boiler; The second calculation module is used to input the real-time performance parameters into the target prediction model to obtain target prediction data. The target prediction model is Obtained by training according to the training method of claim 1 or 2 or the training device of claim 6; The fourth determination module is used to determine an operating sliding pressure curve according to the target prediction data and the target sliding pressure curve; The control module is used to control the main steam pressure control loop of the boiler through the operating sliding pressure curve; The fourth determination module comprises: A first determination submodule, used to determine a target prediction curve according to the target prediction data; A second determination submodule, configured to determine an operating sliding pressure curve according to the target prediction curve and the target sliding pressure curve; The target prediction curve includes a target prediction upper limit curve and a target prediction lower limit curve, and the first determination submodule includes: A third determination submodule is used to determine a target prediction area according to the target prediction upper limit curve and the target prediction lower limit curve; The fourth determining submodule is used to determine the target sliding pressure curve in the target prediction area as the operating sliding pressure curve.
8. The control device according to claim 7, characterized in that: The third determination module comprises: A fifth determination submodule, used to determine the operating load of the boiler; The sixth determination submodule is used to determine the target sliding pressure curve according to the operating load and a preset corresponding relationship, wherein the preset corresponding relationship is used to characterize the corresponding relationship between the operating load and the sliding pressure curve.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 4 are implemented.
10. An electronic device, characterized in that: include: a memory having a computer program stored thereon; 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 to 4.
