Control method and system for automatic establishment of pressurized water reactor nuclear power plant voltage stabilizer steam cavity

Abstract

The invention discloses a control method and system for automatic establishment of a pressure stabilizer steam cavity of a pressurized water reactor nuclear power plant, and the method comprises the steps: building a system model suitable for simulating the process of building the steam cavity of a pressure stabilizer, and obtaining the design priori knowledge of a controller and the simulation data required for training a neural network; designing a voltage stabilizer according to the operation flow and priori knowledge, and establishing a control system architecture and a controller of the steam cavity process; selecting simulation data to carry out offline training on the designed neural network controller; a simulator or a high-precision model is used for simulating the steam cavity building process, online simulation verification is conducted on the voltage stabilizer automatic steam cavity building control system based on the neural network, controller correction and optimization iteration are conducted according to the simulation verification result, and automatic control is achieved. The method can reduce the burden of an operator, reduces the probability of human errors, and improves the starting economy of the nuclear power plant.

Description

Background Art

[0002] A pressurized water reactor (PWR) is a common nuclear power generation facility, and its pressurizer is an important device for controlling pressure. The liquid chamber and the vapor chamber inside the pressurizer are kept in a balanced state through control means to reduce the pressure change caused by the expansion of the coolant. This balanced state is crucial to maintaining the stable operation of the nuclear power plant.

[0003] The establishment process of the pressurizer steam cavity is an important operation process in the startup of a pressurized water reactor power plant. In this process, water needs to be converted into steam through control means to form a steam cavity. This process requires precise control to ensure that the steam cavity establishment process proceeds smoothly. If there is a problem in the steam cavity establishment process, it may have an adverse impact on the safe operation and economy of the nuclear power plant.

[0004] Therefore, the pressurizer steam cavity establishment process is of great significance to the safe operation and economy of PWR nuclear power plants. If there is a problem in this process, it may lead to safety accidents of nuclear power plants or increase operating costs. Therefore, researching and developing optimization technology for the pressurizer steam cavity establishment process is of great significance to improving the safety and economy of PWR nuclear power plants.

[0005] The traditional pressurizer steam cavity establishment process usually relies on the operator's experience and intuition to control. The operator needs to pay attention to and control various parameters, including pressure, temperature, flow, etc., to ensure that the steam cavity establishment process proceeds smoothly. However, this method has some risks and uncertainties.

[0006] First, there is a risk of human error because the operator needs to constantly monitor various parameters. The operator may make mistakes or omissions due to fatigue, distraction or other reasons, which may affect the steam cavity establishment process. In addition, due to the long time and human intervention, the operator may make omissions or misjudgements during the operation, further increasing the risk and uncertainty.

[0007] Secondly, since the traditional pressurizer steam chamber establishment process relies on experience to control the electric heater, there may be problems with wrong / missed operation. If the electric heater is withdrawn too late, it may cause the pressure to exceed the limit when the steam chamber is established, thus causing safety problems; conversely, if the electric heater is withdrawn too early, it may cause the steam chamber to fail to establish, resulting in economic losses. Summary of the invention

[0008] The technical problem to be solved by the present invention is to provide a control method and system for automatically establishing the steam chamber of a pressurizer of a pressurizer of a pressurized water reactor nuclear power plant in view of the deficiencies in the above-mentioned prior art, so as to solve the technical problems that the steam chamber establishment fails or the pressure of a circuit is difficult to control when the steam chamber is established, which exist in the process of establishing the steam chamber of a pressurizer of a pressurizer of a pressurizer of a pressurizer nuclear power plant.

[0009] The present invention adopts the following technical solutions:

[0010] A control method for automatically establishing a pressurizer steam cavity for a pressurized water reactor nuclear power plant comprises the following steps:

[0011] S1. Establish a system model suitable for simulating the process of building a steam chamber for a pressurizer, and obtain the prior knowledge of controller design and the simulation data required for training the neural network;

[0012] S2. Design a voltage regulator based on the operation process and prior knowledge, establish a voltage regulator steam chamber automatic control framework based on a neural network controller, and obtain a neural network controller for the steam chamber process;

[0013] S3, selecting the simulation data obtained in step S1 to perform offline training on the neural network controller designed in step S2;

[0014] S4. Perform online simulation verification on the automatic steam chamber building system of the voltage regulator of the neural network controller trained in step S3 through a simulator or a high-precision model, and correct and optimize the results of the simulation verification to achieve automatic control.

[0015] Preferably, in step S1, based on the actual operation process of the pressurizer steam chamber establishment, a system model suitable for simulating the process is established. The model is established based on the basic requirement of completing the operation of the pressurizer steam chamber establishment process, and characterizes the influence of different heating amounts of the pressurizer on the establishment of a circuit and the steam chamber. The established system model includes a pressurizer model, an electric heater model, a coolant system, a waste heat removal system, and a chemical and volume control system.

[0016] Preferably, in step S2, a neural network controller for automatically establishing a steam cavity process is designed, specifically:

[0017] The regulator temperature, downstream flow, the difference between the upper and lower charging and discharging flows, the primary circuit pressure difference and the surge tube heating rate are used as the input of the controller, and the electric heater power is used as the output of the controller. A regulator based on a neural network controller is designed to establish an automatic control framework for the steam cavity.

[0018] Preferably, a single hidden layer neural network is used, and the number of nodes in the hidden layer is as follows:

[0019]

[0020] Among them, h is the number of hidden layer nodes, n is the number of input nodes, y is the number of output nodes, and a represents an integer between 1 and 10.

[0021] Preferably, the number of hidden layer nodes increases from 5 to 14 in sequence. The same sample data is used for network training in each case. The mean square error is used as the evaluation function. The network with the smallest mean square error is the optimal hidden layer network node number h. best .

[0022] Preferably, the output node Y is designed to be (y1, y2, y3, y4, y5) T , y1 to y5 represent different values ​​of the total operating power of the electric heater.

[0023] Preferably, in step S3, simulation operation data with a short steam cavity successful establishment time and a stable one-loop pressure are selected for training the neural network controller, and the simulation operation data are divided into training set data and test set data; the learning rate, the initial values ​​of each connection weight and threshold are set, and then the initialized neural network controller is trained using the training set data. When the convergence conditions are met, the test set data is used to verify the correctness of the neural network controller.

[0024] Preferably, the training process is as follows:

[0025] Take the i-th group of samples (X i ,Y i )(i=1,2,3,…,m), X i Input to the network and get the network output Y io ;

[0026] calculate If J<ε, the convergence condition is met, otherwise return to modify the weight and calculate the J value again until the convergence condition is met.

[0027] Preferably, step S4 is specifically:

[0028] Based on the neural network controller trained in step S3, an automatic control system for the pressurizer to build the steam chamber is established. The automatic control system for the pressurizer to build the steam chamber is simulated and tested by a simulator or a high-precision model. According to the simulation results, it is evaluated whether the automatic control system for the pressurizer to build the steam chamber has completed the automatic control of the corresponding process, and the risk points that cause the failure of steam chamber establishment or cause the pressure of a circuit to fluctuate beyond the limit are found. Steps S2 to S3 are repeated again to perform optimization iterations of the neural network controller.

[0029] In a second aspect, an embodiment of the present invention provides a control system for automatically establishing a pressurizer steam cavity of a pressurized water reactor nuclear power plant, comprising:

[0030] Data module, which establishes a system model suitable for simulating the process of building a steam chamber for a pressurizer, and obtains prior knowledge of controller design and simulation data required for training neural networks;

[0031] Design module, design the regulator according to the operation process and prior knowledge, establish the automatic control framework of the regulator steam cavity based on the neural network controller, and obtain the neural network controller of the steam cavity process;

[0032] The training module selects the simulation data obtained by the data module to perform offline training on the neural network controller obtained by the design module;

[0033] The control module performs online simulation verification on the automatic steam chamber building system of the voltage regulator of the trained neural network controller through a simulator or a high-precision model, and corrects and optimizes the simulation verification results iteratively to achieve automatic control.

[0034] In a third aspect, a computer device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned control method for automatically establishing a pressurizer steam chamber in a pressurized water reactor nuclear power plant when executing the computer program.

[0035] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned control method for automatically establishing a pressurizer steam chamber in a pressurized water reactor nuclear power plant.

[0036] Compared with the prior art, the present invention has at least the following beneficial effects:

[0037] A control method for automatically establishing a pressurizer steam chamber in a pressurized water reactor nuclear power plant trains and iterates a neural network controller suitable for the object based on object characteristics to replace the current manual operation. This method can automatically control the amount of electric heating based on current parameter changes while meeting the primary circuit pressure fluctuation limit, quickly and stably achieve automatic establishment of the pressurizer steam chamber, shorten the startup time, and improve the production efficiency of the nuclear power plant. Compared with the traditional operator relying on engineering experience to manually establish the steam chamber, the intelligent control method for automatically establishing the pressurizer steam chamber has lower requirements on the operator, less burden, and will not cause human errors.

[0038] Furthermore, considering the difficulty in obtaining actual operating data that can be used for training neural network controllers, a system model suitable for simulating the steam chamber building process of the regulator is established according to the controlled object. This can more conveniently and accurately obtain the prior knowledge of controller design and the simulation data required for training the neural network.

[0039] Furthermore, based on the characteristics of the pressurizer, the specific operation process of the steam chamber and the operator experience, the pressurizer temperature, the discharge flow, the difference between the upper and lower discharge flows, the primary circuit pressure difference and the surge tube heating rate are used as the controller inputs, and the electric heater power is used as the controller output. The automatic control framework of the pressurizer steam chamber based on the neural network controller is designed. This framework fully considers the indicators and operator experience characterized in the steam chamber construction process. According to this control framework, any neural network algorithm can be used to train the neural network controller, not limited to the BP neural network.

[0040] The neural network algorithm has good nonlinear mapping ability, learning ability, generalization ability and fault tolerance ability. The neural network controller after training iteration using excellent successful steam cavity data can better realize the automation of the steam cavity building process. This method is not limited to the BP neural network algorithm, and other neural network algorithms can also be used for the training of the controller.

[0041] Furthermore, simulation operation data with short steam cavity establishment time and stable primary circuit pressure are selected for training the neural network controller, and the simulation operation data are divided into training set data and test set data; the learning rate, the initial values ​​of each connection weight and threshold are set, and then the initialized neural network controller is trained using the training set data. When the convergence conditions are met, the correctness of the neural network controller is verified using the test set data. This method can ensure that the trained neural network controller can complete the automatic control of the steam cavity establishment process.

[0042] Furthermore, the training process of the neural network controller sets a convergence condition, and the convergence condition is set according to the actual situation to ensure that the accuracy of the trained neural network controller meets the requirements for subsequent automatic steam cavity control.

[0043] Furthermore, based on the neural network controller trained in step S3, an automatic control system for building a steam chamber for a pressurizer is built, and a simulation test is performed on the automatic control system for building a steam chamber for a pressurizer through a simulator or a high-precision model. According to the simulation results, it is evaluated whether the automatic control system for building a steam chamber for a pressurizer has completed the automatic control of the corresponding process, and the risk points that cause the failure of steam chamber establishment or cause the pressure of a circuit to fluctuate beyond the limit are found. Steps S2 to S3 are repeated again to perform optimization iterations of the neural network controller. This step will apply the trained neural network controller to verify whether it meets the requirements, and analyze the application results to determine whether the controller still needs iterative training, so as to ensure that the neural network controller finally designed can replace manual operation in actual engineering.

[0044] It can be understood that the beneficial effects of the second aspect mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0045] In summary, the present invention can reduce the burden on operators, reduce the probability of human errors and improve the economy of nuclear power plant startup.

[0046] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A flow chart of an intelligent control method for automatically establishing a pressurizer steam chamber for a pressurizer nuclear power plant of a pressurized water reactor according to the present invention;

[0048] Figure 2 Build a steam cavity model process flow chart for the regulator;

[0049] Figure 3 Build steam cavity intelligent control schematic for voltage stabilizer;

[0050] Figure 4 Design a flow chart for the BP neural network controller structure;

[0051] Figure 5 A training flow chart of a steam cavity neural network controller is provided for the present invention;

[0052] Figure 6 A schematic diagram of a computer device provided by an embodiment of the present invention;

[0053] Figure 7 The present invention is a block diagram of an electronic device provided according to an embodiment. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] In the description of the present invention, it should be understood that the terms “include” and “comprises” indicate the presence of described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0056] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0057] It should be further understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects are in an "or" relationship.

[0058] It should be understood that, although the terms first, second, third, etc. may be used to describe preset ranges, etc. in the embodiments of the present invention, these preset ranges should not be limited to these terms. These terms are only used to distinguish preset ranges from each other. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0059] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0060] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0061] In order to reduce the impact of manual intervention on the process of establishing the pressurizer steam chamber, make full use of expert experience and operation data to improve the efficiency and stability of the process of establishing the pressurizer steam chamber, the present invention proposes a method for automatically establishing the pressurizer steam chamber of a pressurized water reactor nuclear power plant based on a neural network. The method of the present invention can automatically control the electric heating amount according to the current changes in various parameters while meeting the primary circuit pressure fluctuation limit, quickly and stably realize the automatic establishment of the pressurizer steam chamber, shorten the startup time, and improve the production efficiency of the nuclear power plant. Compared with the traditional operator relying on engineering experience to manually establish the steam chamber, the intelligent control method for automatically establishing the pressurizer steam chamber has lower requirements on the operator, less burden, and no human error will occur.

[0062] The present invention provides a control method for automatically establishing a pressurizer steam chamber in a pressurized water reactor nuclear power plant. First, based on the pressurizer steam chamber operation process and system design content, a pressurizer steam chamber system model for obtaining controller design priori knowledge and simulation operation data is built; then, an automatic control system framework and a neural network controller for the pressurizer steam chamber process are designed, including the type of controller used, the specific structure, the controller input and output, and the function representation; then, the simulation operation data is divided into training set data and test set data, the training set data is used to train the designed neural network controller, and after the convergence condition is met, the test set data is used to verify the correctness of the network model until a trained neural network model is obtained; finally, a neural network-based pressurizer steam chamber automatic control system is built on a simulator or a high-precision model to test and verify the control effect, and the controller is iteratively optimized according to the simulation result, until a rapid and stable automatic establishment process of the nuclear power plant pressurizer steam chamber is achieved.

[0063] See also Figure 1 The present invention provides a control method for automatically establishing a pressurizer steam chamber for a pressurized water reactor nuclear power plant, comprising the following steps:

[0064] S1. According to the research object's regulator principle, parameters and control process of steam chamber construction, a system model suitable for simulating the process of pressurizer steam chamber construction is established to obtain a priori knowledge of controller design and a large amount of simulation data required for training neural networks;

[0065] See also Figure 2 , a large amount of operating data used for the subsequent neural network controller design is difficult to obtain from the actual operating PWR, so the simulation operation data is used to train the controller. The operation process of the pressurizer steam chamber establishment in a PWR nuclear power plant involves the coolant system, the chemical and volume control system that controls the pressure of the primary circuit, and the residual heat removal system that controls the temperature of the primary circuit. In order to obtain the prior knowledge for designing the controller and the simulation experimental data for training the neural network controller, before carrying out the specific design, it is necessary to study the specific design content involved in the process based on the actual operation process of the pressurizer steam chamber establishment, and establish a system model suitable for simulating the process. The model is established based on the basic requirements of completing the operation of the pressurizer steam chamber establishment process, which can characterize the influence of different heating amounts of the pressurizer on the establishment of the primary circuit and the steam chamber. The established system model must include the pressurizer model, the electric heater model, the coolant system, the residual heat removal system, and the chemical and volume control system.

[0066] S2. Based on step S1, design the automatic control system framework and neural network controller of the pressurizer to establish the steam chamber process according to the operation process and prior knowledge, including system principle, controller structure, and function representation;

[0067] After completing the preparatory operations before building the steam chamber, such as reducing the upper filling flow, reducing the opening of the lower discharge valve and heating the first circuit to 140℃, close the spray valve and fully open the six electric heaters to heat the pressurizer to start the steam chamber process. The specific operation process is to monitor the temperature and pressure of the first circuit, the pressurizer temperature, the surge tube temperature, the upper filling and lower discharge flow, etc. at all times during the pressurizer heating process. The time and number of groups to exit the heater are determined according to the changes in various parameters. The heating amount curve during the steam chamber construction process shows a step-by-step decline. The difference in the heating amount curve will cause the pressure to exceed the limit when the steam chamber is established, causing safety problems, or cause the steam chamber to fail to establish, causing economic losses. It can be seen that the control principle of the steam chamber construction process is to infer the pressurizer heating power curve based on the changes in multiple parameters.

[0068] See also Figure 3 As an excellent learning and reasoning tool, neural network can play an excellent role in information acquisition, reasoning and other fields. In the present invention, based on the characteristics of the pressurizer, the specific operation process of the steam chamber and the operator experience are established, the pressurizer temperature, the discharge flow, the difference between the upper and lower discharge flows, the primary circuit pressure difference and the surge tube heating rate are used as the input of the controller, and the electric heater power is used as the output of the controller. The automatic control framework of the pressurizer steam chamber based on the neural network controller is as follows: Figure 3 shown.

[0069] In order to better illustrate the design details of the neural network controller based on this framework, the present invention uses the most widely used and most versatile BP (Back Propagation) neural network algorithm to explain the neural network model for controller design. It should be noted that other neural network algorithms such as radial basis function neural network, learning vector quantization network, etc. are not limited, and the purpose can be achieved by designing based on this framework. The process of designing using the BP neural network algorithm is as follows: Figure 4 shown.

[0070] According to the above, the input of the neural network controller is the monitoring parameters, and the output is the electric heating power. The specific input node X = (x1, x2, x3, x4, x5) T, x1 is the temperature of the pressurizer, x2 is the discharge flow, x3 is the difference between the upper charging and lower discharge flows, x4 is the difference between the pressure of a circuit and the set value, and x5 is the heating rate of the surge tube. In order to better illustrate the design process of the present invention, the parameters and operation process of Hualong One are taken as an example here. The detailed description provided below is not intended to limit the scope of the invention claimed for protection. Different configurations of different parameters of different reactor types can be configured with different numbers and values ​​of output nodes, but the control principle remains unchanged, and the output is the heater power. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The output node Y designed in the present invention is Y = (y1, y2, y3, y4, y5) T , y1 to y5 are different values ​​of the total power of the electric heater at this time. y1 is a heating power of 1872kW, y2 is a heating power of 1584kW, y3 is a heating power of 1284kW, y4 is a heating power of 988kW, and y5 is a heating power of 576kW.

[0071] In order to facilitate training, a single hidden layer neural network is used, and the number of nodes in the hidden layer is estimated using the following empirical formula (1):

[0072]

[0073] Among them, h is the number of hidden layer nodes, n is the number of input nodes, y is the number of output nodes, and a represents an integer between 1 and 10.

[0074] According to the empirical formula, the range of hidden nodes is roughly 5-14. To determine the optimal number of hidden layer nodes in this range, the number of hidden layer nodes can be increased from 5 to 14 in sequence. The same sample data is used for network training in each case, and the mean square error is used as the evaluation function. The network with the smallest mean square error is the optimal number of hidden layer network nodes h. best .

[0075] S3, based on step S1 and step S2, select excellent steam chamber construction process simulation sample data to perform offline training on the designed neural network controller, and use test data to verify the model accuracy until the training is completed;

[0076] Based on step S1, an experienced operator operates on the simulation model and obtains a large amount of simulation data for establishing the steam cavity, from which the simulation operation data with a short successful steam cavity establishment time and a stable one-circuit pressure are selected for subsequent training of the neural network model, and the simulation operation data are divided into training set data and test set data; based on the neural network determined in step S2, the learning rate of the network, the initial values ​​of each connection weight and threshold are set.

[0077] The training set data is then used to train the initialized neural network controller. The specific training algorithm is summarized as follows:

[0078] 1) Take the i-th group of samples (X i ,Y i )(i=1,2,3,…,m), X i Input to the network and get the network output Y io .

[0079] 2) Calculation If J<ε, the convergence condition is met, otherwise return to modify the weight and calculate the J value again until the convergence condition is met.

[0080] After the convergence conditions are met, the test set data is used to verify the correctness of the network model. The accuracy requirement is determined according to the size of the test sample, which is temporarily set at 95%. If the accuracy requirement is not met, return to the training step and train again until a neural network model that meets the requirements is obtained. The overall training process is as follows Figure 5 shown.

[0081] S4. Based on step S3, the neural network control system is verified online by simulating the steam cavity establishment process through a simulator or a high-precision model, and corrections and optimization iterations are performed according to the verification results.

[0082] Based on the neural network controller trained in step S3, an automatic control system for the pressurizer to build a steam chamber is established. The automatic control system is simulated and tested by a simulator or a high-precision model to verify it. According to the simulation results, it is evaluated whether the neural network-based pressurizer steam chamber control system can successfully complete the automatic control of the process, and the risk points that may cause the failure of steam chamber establishment or cause the pressure of a circuit to fluctuate beyond the limit are found. Steps S2 to S3 are repeated again to perform optimization iterations of the neural network controller.

[0083] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as systems, methods or program products. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits", "modules" or "platforms".

[0084] In yet another embodiment of the present invention, a control system for automatically establishing a pressurizer steam chamber in a pressurizer reactor nuclear power plant is provided. The system can be used to implement the above-mentioned control method for automatically establishing a pressurizer steam chamber in a pressurizer reactor nuclear power plant. Specifically, the control system for automatically establishing a pressurizer steam chamber in a pressurizer reactor nuclear power plant includes a data module, a design module, a training module and a control module.

[0085] Among them, the data module establishes a system model suitable for simulating the process of building a steam chamber for the regulator, and obtains the prior knowledge of controller design and the simulation data required for training the neural network;

[0086] Design module, design the regulator according to the operation process and prior knowledge, establish the automatic control framework of the regulator steam cavity based on the neural network controller, and obtain the neural network controller of the steam cavity process;

[0087] The training module selects the simulation data obtained by the data module to perform offline training on the neural network controller obtained by the design module;

[0088] The control module performs online simulation verification on the automatic steam chamber building system of the voltage regulator of the trained neural network controller through a simulator or a high-precision model, and corrects and optimizes the simulation verification results iteratively to achieve automatic control.

[0089] In another embodiment of the present invention, a terminal device is provided, the terminal device includes a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement corresponding method flows or corresponding functions; the processor described in the embodiment of the present invention can be used for the operation of the control method for automatic establishment of the pressurizer steam chamber of a pressurized water reactor nuclear power plant, including:

[0090] Establish a system model suitable for simulating the process of building a steam chamber for a pressurizer, obtain prior knowledge for controller design and simulation data required for training the neural network; design the pressurizer according to the operating process and prior knowledge, establish an automatic control framework for the pressurizer steam chamber based on a neural network controller, and obtain a neural network controller for the steam chamber process; select simulation data to train the neural network controller offline; perform online simulation verification on the pressurizer automatic steam chamber system of the trained neural network controller through a simulator or a high-precision model, and correct and optimize the results of the simulation verification to achieve automatic control.

[0091] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understandable that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device, and can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that more specific examples (non-exhaustive list) of the computer-readable storage medium here include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0092] Computer readable storage media also include data signals propagated in baseband or as part of a carrier wave, which carry readable program codes. Such propagated data signals can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium can also be any readable medium other than a readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or device. The program code contained on the readable storage medium can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0093] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0094] The processor may load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the control method for automatically establishing a pressurizer steam chamber in a pressurized water reactor nuclear power plant in the above embodiment; the processor may load and execute the following steps of one or more instructions in the computer-readable storage medium:

[0095] Establish a system model suitable for simulating the process of building a steam chamber for a pressurizer, obtain prior knowledge for controller design and simulation data required for training the neural network; design the pressurizer according to the operating process and prior knowledge, establish an automatic control framework for the pressurizer steam chamber based on a neural network controller, and obtain a neural network controller for the steam chamber process; select simulation data to train the neural network controller offline; perform online simulation verification on the pressurizer automatic steam chamber system of the trained neural network controller through a simulator or a high-precision model, and correct and optimize the results of the simulation verification to achieve automatic control.

[0096] See also Figure 6 , the terminal device is a computer device, and the computer device 60 of this embodiment includes: a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61. When the computer program 63 is executed by the processor 61, the control method for automatically establishing a pressurizer steam chamber of a pressurized water reactor nuclear power plant in the embodiment is implemented. To avoid repetition, it is not described one by one here. Alternatively, when the computer program 63 is executed by the processor 61, the functions of each model / unit in the control system for automatically establishing a pressurizer steam chamber of a pressurized water reactor nuclear power plant in the embodiment are implemented. To avoid repetition, it is not described one by one here.

[0097] The computer device 60 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 60 may include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art will appreciate that Figure 6 This is only an example of the computer device 60 and does not constitute a limitation of the computer device 60. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0098] The processor 61 may be a central processing unit (CPU), or other general-purpose processors, central processing units, graphics processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, data processing logic based on quantum computing, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0099] The memory 62 may be an internal storage unit of the computer device 60, such as a hard disk or memory of the computer device 60. The memory 62 may also be an external storage device of the computer device 60, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the computer device 60.

[0100] Furthermore, the memory 62 may include both an internal storage unit of the computer device 60 and an external storage device. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 may also be used to temporarily store data that has been output or is to be output.

[0101] Any reference to memory, database or other media used in the embodiments provided in the present application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0102] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0103] See also Figure 7 The terminal device 600 is an electronic device, and the electronic device is in the form of a general computing device. The components of the electronic device may include but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0104] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 performs the steps according to various exemplary embodiments of the present invention described in the above method section of this specification. For example, the processing unit 610 can perform the following steps: Figure 1 Follow the steps shown in .

[0105] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0106] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0107] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0108] The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, etc.

[0109] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention described and shown in the drawings here can usually be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0110] Development of automatic control system for steam chamber process of pressurizer based on neural network

[0111] S1: Establishing system model and acquiring simulation data

[0112] Model construction:

[0113] Use simulation software such as MATLAB / Simulink or Modelica to build a detailed system model of the regulator and its steam chamber process. The model should include the physical structure, thermodynamic characteristics, fluid dynamics characteristics, etc. of the regulator, and consider the dynamic changes of key parameters such as steam chamber pressure, temperature, and flow.

[0114] A variety of operating condition simulations are introduced, such as different load conditions, ambient temperature changes, external disturbances, etc., to fully reflect the complexity of the regulator in actual operation.

[0115] Simulation run:

[0116] Set reasonable initial conditions and boundary conditions in the model and start the simulation.

[0117] Record the time series data of key parameters during the simulation process, including steam cavity pressure, temperature, flow rate, etc., as well as changes in control signals (such as valve opening).

[0118] Data preprocessing:

[0119] The collected simulation data is cleaned to remove noise and outliers.

[0120] Data normalization is performed to ensure the stability and convergence of data in neural network training.

[0121] S2: Designing a Neural Network Controller

[0122] Network architecture design:

[0123] According to the dynamic characteristics and control requirements of the regulator cavity process, a suitable network architecture is selected, such as LSTM (Long Short-Term Memory Network) or GRU (Gated Recurrent Unit).

[0124] Design hyperparameters such as the number of network layers, the number of neurons in each layer, and activation functions to ensure that the network can learn the complex dynamic relationships of the system.

[0125] Input and output definitions:

[0126] Determine the input variables of the neural network, such as the current steam cavity pressure, temperature, flow rate and possible external control signals.

[0127] The output variable is defined as a control signal (such as valve adjustment amount) used to adjust the steam cavity state to achieve the target value.

[0128] Controller Integration:

[0129] The designed neural network controller is integrated into the voltage regulator system model to replace the original control algorithm.

[0130] S3: Offline training of neural network controller

[0131] Data partitioning:

[0132] The preprocessed simulation data is divided into training set, validation set and test set.

[0133] Training process:

[0134] The neural network controller is trained using the training set data, and the network weights and biases are adjusted through the back-propagation algorithm.

[0135] After each training cycle, the validation set is used to evaluate the model performance and hyperparameters such as learning rate and batch size are adjusted as needed.

[0136] Record key indicators such as loss function value and accuracy during training to ensure that the model converges and achieves the expected control effect.

[0137] S4: Online simulation verification and optimization iteration

[0138] Online simulation:

[0139] The trained neural network controller is integrated into the online simulation environment of the voltage regulator system model.

[0140] Set initial conditions and boundary conditions similar to the actual situation and start the online simulation.

[0141] Result analysis:

[0142] Observe and record the changes in key parameters during the simulation process to evaluate the control effect of the neural network controller.

[0143] Analyze performance indicators such as stability, response speed, overshoot, etc. during the control process to identify possible problems.

[0144] Fixes and Optimizations:

[0145] According to the results of simulation verification, the network structure, hyperparameters or control strategy of the neural network controller are modified and optimized.

[0146] Repeat the online simulation verification process until a satisfactory control effect is achieved.

[0147] Iterative improvement:

[0148] In practical applications, system operation data is continuously collected for online learning or regular updates of the neural network controller.

[0149] Through continuous optimization and iteration, the adaptability and robustness of the neural network controller are improved to ensure the stable operation of the voltage stabilizer system.

[0150] The embodiments of the present invention are mainly reflected in the following aspects:

[0151] 1. Accuracy and robustness

[0152] Precise control: Through the training of a large amount of simulation data by neural network, the controller can learn the complex dynamic characteristics of the steam chamber process of the regulator, thus achieving more precise control. This helps to reduce system errors and improve control accuracy.

[0153] Strong robustness: The neural network controller can adapt to changes in different working conditions and environmental conditions, and has strong anti-interference ability to external disturbances and internal parameter changes, ensuring stable operation of the system.

[0154] 2. Efficiency and real-time performance

[0155] Fast response: Neural network controllers usually have a faster computing speed and can make control decisions in a short time, improving the response speed of the system.

[0156] Optimization iteration: Through simulation verification and correction optimization iteration, the control strategy can be continuously improved and the control efficiency can be improved. At the same time, online learning and regular update mechanisms also ensure that the controller can continuously adapt to changes in system characteristics.

[0157] 3. Data-driven and intelligent

[0158] Data-driven: The entire design and verification process is based on a large amount of simulation data, making the controller design more scientific and reasonable. Through data analysis and mining, the potential laws and trends of system operation can be discovered, providing strong support for the optimization of control strategies.

[0159] Intelligent control: The introduction of the neural network controller realizes the intelligent control of the steam chamber process of the regulator. It can automatically adjust the control strategy according to the changes in the system status and external environment without manual intervention, thus improving the automation level of control.

[0160] 4. Reduce costs and improve efficiency

[0161] Reduce development costs: In the early stages of system development, a large number of tests and verifications through simulation models can identify potential problems early and optimize them, reducing the number and cost of physical tests. At the same time, the self-learning and optimization capabilities of the neural network controller also reduce the cost of later maintenance and debugging.

[0162] Improve system benefits: Accurate control strategies and efficient response speed help improve the operating efficiency and stability of the voltage stabilizer system, reduce energy consumption and failure rate, and thus improve the economic and social benefits of the entire system.

[0163] 5. Flexibility and scalability

[0164] High flexibility: The design of the neural network controller has a certain degree of flexibility, and the network structure and parameters can be adjusted according to actual needs. At the same time, it can also be combined with other control algorithms to form a more complex and efficient control strategy.

[0165] Strong scalability: With the continuous development of technology and the expansion of application scenarios, neural network controllers can adapt to new control requirements and application scenarios by expanding network scale, optimizing algorithms, etc. This provides broad space for future technology upgrades and expansions.

[0166] The embodiment of the present invention realizes automatic control of the steam chamber process of the regulator by introducing a neural network controller, and has the advantages and benefits of accuracy, high efficiency, data-driven, intelligence, cost reduction, improved efficiency, flexibility and scalability.

[0167] In summary, the present invention provides a control method and system for automatically establishing a pressurizer steam chamber in a pressurized water reactor nuclear power plant. Based on the operating process and characteristics of the pressurizer to establish the steam chamber, the system makes full use of expert experience and operating data to train a neural network controller. The constructed automatic control system for pressurizer steam chamber establishment based on the neural network controller can automatically output the power of the electric heater according to various parameters of the current primary circuit of the nuclear power plant, realize automatic control of the pressurizer steam chamber establishment process, and quickly and stably establish the steam chamber.

[0168] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0169] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0170] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0171] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0172] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0173] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, 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 software functional units.

[0174] If the integrated module / 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 this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0175] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0176] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0177] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0178] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A control method for automatically establishing a pressurizer steam chamber in a pressurized water reactor nuclear power plant, characterized in that: The following steps are involved: S1. Establish a system model suitable for simulating the process of building a steam chamber for a pressurizer, and obtain the prior knowledge of controller design and the simulation data required for training the neural network; S2. Design a voltage regulator based on the operation process and prior knowledge, establish a voltage regulator steam chamber automatic control framework based on a neural network controller, and obtain a neural network controller for the steam chamber process; S3, selecting the simulation data obtained in step S1 to perform offline training on the neural network controller obtained in step S2; S4. Perform online simulation verification on the automatic steam chamber building system of the voltage regulator of the neural network controller trained in step S3 through a simulator or a high-precision model, and correct and optimize the results of the simulation verification to achieve automatic control.

2. The control method for automatically establishing a pressurizer steam chamber in a pressurized water reactor nuclear power plant according to claim 1, characterized in that: In step S1, based on the actual operation process of the pressurizer steam chamber establishment, a system model suitable for simulating the process is established. The model is established based on the basic requirement of completing the operation of the pressurizer steam chamber establishment process, and characterizes the influence of different heating amounts of the pressurizer on the primary circuit and the steam chamber establishment. The established system model includes a pressurizer model, an electric heater model, a coolant system, a waste heat removal system, and a chemical and volume control system.

3. The control method for automatically establishing a pressurizer steam chamber for a pressurized water reactor nuclear power plant according to claim 1, characterized in that: In step S2, a neural network controller for automatically establishing the steam cavity process is designed, specifically: The regulator temperature, downstream flow, the difference between the upper and lower charging and discharging flows, the primary circuit pressure difference and the surge tube heating rate are used as the input of the controller, and the electric heater power is used as the output of the controller. A regulator based on a neural network controller is designed to establish an automatic control framework for the steam cavity.

4. The control method for automatically establishing a pressurizer steam chamber for a pressurized water reactor nuclear power plant according to claim 3, characterized in that: A single hidden layer neural network is used, and the number of nodes in the hidden layer is as follows: Among them, h is the number of hidden layer nodes, n is the number of input nodes, y is the number of output nodes, and a represents an integer between 1 and 10.

5. The control method for automatically establishing a pressurizer steam chamber in a pressurized water reactor nuclear power plant according to claim 4, characterized in that: The number of hidden layer nodes increases from 5 to 14. The same sample data is used for network training in each case. The mean square error is used as the evaluation function. The network with the smallest mean square error is the optimal hidden layer network node number h. best .

6. The control method for automatically establishing a pressurizer steam chamber for a pressurized water reactor nuclear power plant according to claim 3, characterized in that: Design output node Y = (y1, y2, y3, y4, y5) T , y1 to y5 represent different values ​​of the total operating power of the electric heater.

7. The control method for automatically establishing a pressurizer steam chamber for a pressurized water reactor nuclear power plant according to claim 1, characterized in that: In step S3, simulation operation data with short steam cavity establishment time and stable primary circuit pressure are selected for training the neural network controller, and the simulation operation data are divided into training set data and test set data; The learning rate, the initial values ​​of each connection weight and the threshold are set, and then the initialized neural network controller is trained using the training set data. When the convergence conditions are met, the correctness of the neural network controller is verified using the test set data.

8. The control method for automatically establishing a pressurizer steam chamber in a pressurized water reactor nuclear power plant according to claim 7, characterized in that: The training process is as follows: Take the i-th group of samples (X i ,Y i ), i = 1, 2, 3, ..., m, and X i Input to the network and get the network output Y io ; calculate If J<ε, the convergence condition is met, otherwise return to modify the weight and calculate the J value again until the convergence condition is met.

9. The control method for automatically establishing a pressurizer steam chamber in a pressurized water reactor nuclear power plant according to claim 1, characterized in that: Step S4 is specifically as follows: Based on the neural network controller trained in step S3, an automatic control system for the pressurizer to build the steam chamber is established. The automatic control system for the pressurizer to build the steam chamber is simulated and tested by a simulator or a high-precision model. According to the simulation results, it is evaluated whether the automatic control system for the pressurizer to build the steam chamber has completed the automatic control of the corresponding process, and the risk points that cause the failure of steam chamber establishment or cause the pressure of a circuit to fluctuate beyond the limit are found. Steps S2 to S3 are repeated again to perform optimization iterations of the neural network controller.

10. A control system for automatically establishing a pressurizer steam chamber in a pressurized water reactor nuclear power plant, characterized in that: include: Data module, which establishes a system model suitable for simulating the process of building a steam chamber for a pressurizer, and obtains prior knowledge of controller design and simulation data required for training neural networks; Design module, design the regulator according to the operation process and prior knowledge, establish the automatic control framework of the regulator steam cavity based on the neural network controller, and obtain the neural network controller of the steam cavity process; The training module selects the simulation data obtained by the data module to perform offline training on the neural network controller obtained by the design module; The control module performs online simulation verification on the automatic steam chamber building system of the voltage regulator of the trained neural network controller through a simulator or a high-precision model, and corrects and optimizes the simulation verification results iteratively to achieve automatic control.

Images