A nuclear power safety production control method and system

Abstract

The present invention discloses a nuclear power production safety control method and system, including: collecting the operation data of the nuclear power plant's production safety; constructing a nuclear power plant production mathematical model based on the operation data, analyzing the objective function and constraints of the production safety, and building an optimization model; establishing a transient response process, using a deep learning algorithm for prediction, and evaluating the results for operation control; optimizing the nuclear power capacity under the constraints of production safety to obtain the optimal control strategy. The beneficial effects of the present invention: by collecting and analyzing the operation data of the nuclear power plant in real time, establishing a mathematical model and a transient response process, our method can more accurately predict the system state and achieve optimal control of the production capacity under the constraints of production safety. This method not only improves the prediction accuracy and response speed of the system, but also provides an effective control strategy under emergencies, significantly improving the safety and operation efficiency of nuclear power plants.

Description

Technical Field

[0001] The present invention relates to the technical field of nuclear power production control, and particularly to a nuclear power safety production control method and system. Background Art

[0002] With the continuous growth of global energy demand, nuclear energy, as an efficient and clean energy form, has been widely used worldwide. The safe production of nuclear power plants is not only related to the stability of power supply, but also related to public safety and environmental protection. Therefore, the existing power grids have invested a large amount of resources in the safe operation and management of nuclear power plants, and developed a series of advanced technologies and methods to ensure the efficient and safe operation of nuclear power plants.

[0003] Traditional nuclear power plant safety production control technologies mainly rely on physical models and empirical formulas. To a certain extent, these methods can predict and control the operating state of nuclear power plants. However, with the increasing complexity of nuclear power plant systems, these methods gradually show their limitations. In recent years, the development of modern information technology has brought new opportunities for nuclear power plant safety production control, especially the application of data-driven analysis methods and artificial intelligence technologies. These new technologies can analyze the operating state of nuclear power plants more comprehensively and in real time, and provide more accurate prediction and optimization strategies. Although significant progress has been made in the current nuclear power plant safety production control technology, there are still some deficiencies. First, traditional methods rely too much on preset physical models and empirical formulas. When facing the complex and dynamically changing operating environment of nuclear power plants, these models and formulas often cannot accurately predict and respond to sudden situations. Second, the existing control systems usually lack the full utilization of real-time data. The lag in data processing and analysis makes the system unable to respond and adjust quickly, resulting in potential safety hazards not being discovered and processed in time. Summary of the Invention

[0004] In view of the above problems, the present invention is proposed.

[0005] Therefore, the technical problem to be solved by the present invention is: how to use real-time data for data processing and analysis to make a quick response and timely discover potential safety hazards.

[0006] To solve the above technical problem, the present invention provides the following technical solution: a nuclear power safety production control method, including:

[0007] Collect the operation data of the safe production of the nuclear power plant;

[0008] Construct a nuclear power plant production mathematical model according to the operation data, analyze to obtain the objective function and constraint conditions for safe production, and construct an optimization model;

[0009] Establish a transient response process, use a deep learning algorithm for prediction, and perform operation regulation based on the evaluation results;

[0010] Under the constraint of safe production, optimize the nuclear power production capacity to obtain the optimal control strategy.

[0011] As a preferred embodiment of the nuclear power safety production control method described in the present invention, wherein: the operation data includes data related to the reactor and coolant, data related to the steam generator and steam turbine, data related to the control system, and data related to operation and maintenance;

[0012] The overall cycle mathematical model of nuclear power plant production includes;

[0013] The neutron kinetics equation of the reactor nuclear reaction kinetics model is expressed as:

[0014]

[0015] Wherein, N represents the neutron density, ρ represents the reactivity, β represents the delayed neutron fraction, Λ represents the neutron mean lifetime, C i represents the concentration of the delayed neutron precursor group, λ i represents the decay constant of the delayed neutron precursor;

[0016] The fission product concentration equation is expressed as:

[0017]

[0018] Wherein, β i represents the fraction of the i-th delayed neutron precursor;

[0019] The thermal-hydraulic model describes the mass and energy conservation of the coolant:

[0020] The mass conservation equation is expressed as:

[0021]

[0022] The energy conservation equation is expressed as:

[0023]

[0024] Wherein, M represents the coolant mass, represents the inlet flow rate; represents the outlet flow rate; represents the input heat; output heat; h in represents the inlet enthalpy; h out represents the final outlet enthalpy.

[0025] As a preferred embodiment of the nuclear power production safety control method of the present invention, wherein: the construction of the nuclear power plant production mathematical model includes obtaining the mathematical model of the nuclear power plant power output according to the overall cycle mathematical model of the nuclear power plant production;

[0026] The steam generator model includes that the primary side mass conservation equation formula is expressed as:

[0027]

[0028] Wherein, M p represents the primary side coolant mass; E represents energy; M represents the coolant mass; represents the flow rate;

[0029] The primary side energy conservation equation formula is expressed as:

[0030]

[0031] Wherein, E p represents energy, and respectively represent the heat transfer amounts on the primary side and the secondary side;

[0032] The steam turbine model describes the steam expansion and work done in each stage, and the formula is expressed as:

[0033]

[0034] Wherein, W t represents the steam turbine output power; represents the steam flow rate; h s，in represents the inlet steam enthalpy; h s，out represents the outlet steam enthalpy.

[0035] As a preferred embodiment of the nuclear power production safety control method of the present invention, wherein: the objective function and constraints include analyzing the overall cycle mathematical model of the nuclear power plant production and the power output model of the nuclear power plant; under the safe production of the nuclear power plant, the objective function and constraints of the optimal power regulation need to consider the maximization of power output, the safety of the reactor, and the stability of the system;

[0036] The objective function is expressed as:

[0037]

[0038] The constraints include that the reactor safety constraint is expressed as:

[0039] ρ(t) ≤ ρ max

[0040] Wherein, ρ(t) represents the current reactivity; ρmax Represents the maximum reactivity;

[0041] The coolant flow rate and temperature limits are expressed as:

[0042] T coolant ≤T coolant，max

[0043] where T coolant represents the current coolant temperature; T coolant，max represents the maximum temperature of the coolant;

[0044] The steam generator and turbine constraints are expressed as:

[0045]

[0046] where, represents the current secondary side steam flow rate; Secondary side steam flow rate; control input limit:

[0047] u(t) ≤ u max

[0048] where, u(t) represents the current control input; u max represents the maximum value of the control input; The environmental and operating constraints are expressed as:

[0049] t operation ≤t operation，max

[0050] where, t operation represents the current operating time; t operation，max The maximum safe operating time.

[0051] As a preferred embodiment of the nuclear power safety production control method described in the present invention, wherein: the operation transient response model includes that the operation transient response refers to when the unit is in a state of unexpected deviation from safe and stable operation, dynamic regulation is performed according to the results of the transient response evaluation model; The formula of the transient response evaluation model is expressed as:

[0052]

[0053] where, N represents the number of groups of delayed neutron precursors; P i (t) represents the power corresponding to the i-th group of precursors; λ i represents the decay constant of the i-th group of precursors; β i represents the effective neutron production rate of the i-th group of precursors; Λ represents the neutron mean lifetime; p(t) represents the system pressure; μ represents the expected value of the pressure; σ represents the standard deviation of the pressure; represents the attenuation term, describing the transient change of the precursor concentration;

[0054] The formula of the normal distribution function of pressure is expressed as:

[0055]

[0056] Judgment is made based on the relationship between the evaluation result E(t) of the transient response evaluation model and the expected operating condition, and regulation is carried out according to the judgment result.

[0057] As a preferred solution of the nuclear power safety production control method described in the present invention, wherein: the establishment of the transient response process includes operating the transient response model and monitoring the operating data of the nuclear power plant;

[0058] When the evaluation result E(t) of the operating data > 0.1, the system runs stably, continue to monitor, and regularly check the system parameters to ensure that all parameters are within the normal range; when the evaluation result 0.1 ≥ E(t) > 0, the system runs close to the critical state and needs to be adjusted moderately; adjust the coolant temperature and flow rate, adjust the control input, and reduce the reactor power output; when the evaluation result E(t) ≤ 0, it is determined that the system runs unstably and major adjustments are required; significantly increase the coolant flow rate and reduce the coolant temperature, immediately reduce the reactor power output, start the emergency shutdown procedure, and adjust the control input; judge and classify the events occurring in the power plant according to the threshold values of the various constraint conditions in the emergency state;

[0059] After a reactor shutdown and major transient regulation occur, relevant investigations and cause analyses are carried out, and after completion, the reactor is restarted and full power operation is restored.

[0060] As a preferred solution of the nuclear power safety production control method described in the present invention, wherein: the optimal regulation strategy includes using an improved particle swarm algorithm to perform an optimization operation on the optimization model; initializing particles and calculating the initial fitness of each particle;

[0061] Calculate the fitness. For each particle, calculate its fitness, that is, the objective function value W t ;

[0062] Check whether all constraint conditions are satisfied. If not, for the particles that violate the constraints, apply a penalty function to reduce their fitness values:

[0063]

[0064] Among them, f(x) represents the original objective function, g i (x) represents the constraint condition, and λ i represents the penalty factor

[0065] Update the particle's best position pbest. For each particle, if the current fitness is better than its historical best fitness, update its historical best position and fitness; update the global best position gbest. Among all particles, select the particle position with the optimal fitness as the global best position;

[0066] Update the velocity and position. Combining the adaptive inertia weight and the dynamic learning factor, the formula is expressed as:

[0067] v i (t + 1) = w(t)·v i (t) + c 1 (t)·r 1 ·(pbest i -x i (t)) + c 2 (t)·r 2 ·(gbest - x i x i (t + 1) = x i (t) + v i (t + 1)

[0068] Among them, w(t) represents the inertia weight; c 1 (t) represents the individual learning factor; c 2 (t) represents the swarm learning factor; r 1 , r 2 represents a random number; v i (t) represents the velocity vector; x i (t) represents the position vector;

[0069] Keep the elite particles unchanged; repeat the iteration until the fitness no longer improves significantly; use the final global best position gbest as the optimal solution and decode it into actual physical variables;

[0070] Verify whether the optimal solution satisfies all constraint conditions. Use the penalty function method to adjust the fitness of the particles that violate the constraints and correct the positions of the particles that violate the constraints to the nearest feasible solutions; if the optimal solution satisfies all constraint conditions, output the optimal solution and its objective function value;

[0071] Output the optimal solution, including the best steam flow rate and the best enthalpy of inlet and outlet steam; output the corresponding objective function value to obtain the optimal power control strategy.

[0072] A nuclear power safety production control system adopting the method described in any one of the present inventions, wherein:

[0073] The data collection and preprocessing module collects the safety production operation data of the nuclear power plant and preprocesses the operation data; collects the data of the reactor, coolant, steam generator, steam turbine, control system, operation and maintenance from sensors and monitoring systems;

[0074] Mathematical model construction and optimization module, which constructs a production mathematical model of a nuclear power plant based on operation data, analyzes to obtain the objective function and constraint conditions for safe production, and constructs an optimization model;

[0075] Transient response prediction and evaluation module, which establishes a transient response process and uses a deep learning algorithm for prediction; evaluates the prediction results and conducts operation regulation according to the results;

[0076] Optimization and regulation strategy module, which uses an improved particle swarm algorithm to optimize the optimization model; obtains the optimal regulation strategy.

[0077] A computer device, comprising: a memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the method described in any one of the present invention are implemented.

[0078] A computer-readable storage medium, on which a computer program is stored, characterized in that: when the computer program is executed by a processor, the steps of the method described in any one of the present invention are implemented.

[0079] Advantages of the present invention: By collecting and analyzing the operation data of a nuclear power plant in real time, establishing a mathematical model and a transient response process, our method can more accurately predict the system state and achieve optimal regulation of production capacity under the constraint conditions of safe production. This method not only improves the prediction accuracy and response speed of the system, but also can provide effective regulation strategies in case of emergencies, significantly improving the safety and operation efficiency of the nuclear power plant. Brief Description of the Drawings

[0080] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Among them:

[0081] Figure 1 It is the overall flowchart of a nuclear power safety production control method provided by the first embodiment of the present invention. Detailed Embodiments

[0082] In order to make the above objects, features and advantages of the present invention more obvious and understandable, the following will describe the detailed embodiments of the present invention with reference to the drawings of the specification. Obviously, the described embodiments are some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0083] Example 1

[0084] Reference Figure 1 , which is an embodiment of the present invention, provides a nuclear power safety production control method, including:

[0085] S1: Collect the operation data of the nuclear power plant's safety production.

[0086] Furthermore, collecting the data related to the reactor and coolant includes reactivity parameters, maximum reactivity, current reactivity, coolant parameters, maximum temperature of the coolant, and current coolant temperature.

[0087] Even further, collecting the data related to the steam generator and steam turbine includes steam flow parameters, maximum value of the secondary side steam flow, current secondary side steam flow, steam enthalpy parameters, inlet steam enthalpy of the steam, and outlet steam enthalpy of the steam.

[0088] Even further, the data related to the control system, control input parameters, maximum value of the control input, current control input; the data related to operation and maintenance.

[0089] It should be noted that the reactivity parameters: include maximum reactivity and current reactivity. The reactivity parameters critically reflect the neutron multiplication status of the nuclear reactor and are the core indicators for the safe operation of the nuclear power plant. Coolant parameters: include the maximum temperature of the coolant and the current coolant temperature. Monitoring the coolant temperature is crucial for preventing the nuclear reactor from overheating and maintaining the integrity of the reactor nuclear fuel.

[0090] S2: Construct a nuclear power plant production mathematical model based on the operation data, analyze to obtain the objective function and constraint conditions for safe production, and construct an optimization model.

[0091] Furthermore, the operation data includes the data related to the reactor and coolant, the data related to the steam generator and steam turbine, the data related to the control system, and the data related to operation and maintenance.

[0092] Even further, the overall cycle mathematical model of nuclear power plant production includes.

[0093] Even further, the neutron kinetics equation formula of the reactor nuclear reaction kinetics model is expressed as:

[0094]

[0095] Among them, N represents neutron density, ρ represents reactivity, β represents delayed neutron fraction, Λ represents neutron mean lifetime, C i represents the concentration of delayed neutron precursor groups, λ i represents the decay constant of delayed neutron precursors.

[0096] Furthermore, the formula of the fission product concentration equation is expressed as:

[0097]

[0098] where β i represents the fraction of the i-th delayed neutron precursor.

[0099] Furthermore, the formula of the reactor power equation is expressed as:

[0100]

[0101] where P in is the power generated by nuclear reactions; P out is the power carried away by the coolant; τ is the power time constant.

[0102] Furthermore, the formula of the heat exchanger heat transfer characteristic model is expressed as:

[0103] Q = hA(T surface - T fluid )

[0104] Furthermore, the formula of the fluid physical property change model is expressed as:

[0105] h = f(T, p, ρ, μ)

[0106] Furthermore, the thermal-hydraulic model describes the mass and energy conservation of the coolant. The formula of the mass conservation equation is expressed as:

[0107]

[0108] Furthermore, the formula of the energy conservation equation is expressed as:

[0109]

[0110] where M represents the coolant mass, represents the inlet flow rate; represents the outlet flow rate; represents the input heat; the output heat; h in represents the input enthalpy; h out represents the final output enthalpy.

[0111] Furthermore, constructing the nuclear power plant production mathematical model includes obtaining the mathematical model of the nuclear power plant power output according to the overall cycle mathematical model of the nuclear power plant production.

[0112] Furthermore, the steam generator model includes that the formula of the mass conservation equation on the primary side is expressed as:

[0113]

[0114] Among them, M p represents the primary coolant mass; E represents energy; M represents coolant mass; represents the flow rate.

[0115] Furthermore, the primary - side energy - conservation equation formula is expressed as:

[0116]

[0117] Among them, E p represents energy, and represent the heat transfer amounts on the primary side and the secondary side respectively.

[0118] Furthermore, the steam turbine model describing the expansion and work - doing processes of steam at each stage is expressed as:

[0119]

[0120] Among them, W t represents the output power of the steam turbine; represents the steam flow rate; h s，in represents the inlet enthalpy of the steam; h s，out represents the outlet enthalpy of the steam.

[0121] It should be noted that the operation data of the nuclear power plant is predicted and analyzed using deep - learning algorithms, and then dynamic regulation is implemented. The innovation of this method lies in that it allows for a rapid and accurate response to the unexpected behavior of the reactor, effectively preventing possible safety accidents. By combining real - time data analysis with deep - learning technology, more accurate predictions of the reactor transient behavior can be made, and necessary regulation measures can be implemented.

[0122] S3: Establish a transient response process, use deep - learning algorithms for prediction, and conduct operation regulation based on the evaluation results.

[0123] Furthermore, the objective function and constraints include analyzing the overall cycle mathematical model of the nuclear power plant production and the power output model of the nuclear power plant; under the safe production of the nuclear power plant, the objective function and constraints of optimal power regulation need to consider the maximization of power output, the safety of the reactor, and the stability of the system.

[0124] Furthermore, the objective function is expressed as:

[0125]

[0126] Furthermore, the constraints include that the reactor safety constraint is expressed as:

[0127] ρ(t) ≤ ρmax

[0128] Among them, ρ(t) represents the current reactivity; ρ max represents the maximum reactivity.

[0129] Furthermore, the coolant flow rate and temperature limit are expressed as:

[0130] T coolant ≤T coolant，max

[0131] Among them, T coolant represents the current coolant temperature; T coolant，max represents the maximum temperature of the coolant.

[0132] Furthermore, the steam generator and turbine constraints are expressed as:

[0133]

[0134] Among them, represents the current secondary side steam flow rate; secondary side steam flow rate; control input limit:

[0135] u(t)≤u max

[0136] Among them, u(t) represents the current control input; u max represents the maximum value of the control input; the environmental and operating constraints are expressed as:

[0137] t operation ≤t operation，max

[0138] Among them, t operation represents the current operating time; t operation，max maximum safe operating time.

[0139] Furthermore, the operating transient response model includes that the operating transient response refers to the dynamic regulation according to the results of the transient response evaluation model when the unit is in a state of unexpected deviation from safe and stable operation; the formula of the transient response evaluation model is expressed as:

[0140]

[0141] Among them, N represents the number of groups of delayed neutron precursors; P i (t) represents the power corresponding to the i-th group of precursors; λ i represents the decay constant of the i-th group of precursors; β i represents the effective neutron production rate of the i-th group of precursors; Λ represents the neutron mean lifetime; p(t) represents the system pressure; μ represents the expected value of the pressure; σ represents the standard deviation of the pressure; Represents the attenuation term, describing the transient change of the precursor concentration.

[0142] Furthermore, the normal distribution function formula of pressure is expressed as:

[0143]

[0144] Furthermore, based on the relationship between the evaluation result E(t) of the transient response evaluation model and the expected operating condition, a judgment is made, and regulation is carried out according to the judgment result.

[0145] Furthermore, establishing the transient response process includes running the transient response model and monitoring the nuclear power plant operation data.

[0146] Furthermore, when the evaluation result E(t) of the operation data > 0.1, the system runs stably, continue to monitor, and regularly check the system parameters to ensure that all parameters are within the normal range; when the evaluation result 0.1 ≥ E(t) > 0, the system runs close to the critical state, and moderate adjustment is required; adjust the coolant temperature and flow rate, adjust the control input, and reduce the reactor power output; when the evaluation result E(t) ≤ 0, it is determined that the system runs unstably, and major adjustment is required; greatly increase the coolant flow rate and reduce the coolant temperature, immediately reduce the reactor power output, start the emergency shutdown procedure, and adjust the control input; according to the threshold values of the various constraint conditions of the emergency state, judge and classify the events occurring in the power plant.

[0147] Furthermore, after a reactor shutdown and major transient regulation occur, relevant investigations and cause analyses are carried out, and after completion, the reactor is restarted and full power operation is restored.

[0148] It should be noted that the model provides a method for accurately predicting and controlling the reactor state by quantitatively describing variables such as neutron density, reactivity, delayed neutron fraction, and decay constant. Compared with the prior art, this model provides higher accuracy and response speed in real-time monitoring and predicting the behavior of nuclear reactors, thereby greatly improving the safe operation ability of the reactor.

[0149] S4: Optimize the nuclear power production capacity under the constraints of safe production to obtain the optimal regulation strategy.

[0150] Further, the optimal regulation strategy includes using an improved particle swarm algorithm to perform an optimization operation on the optimization model; initializing the particles and calculating the initial fitness of each particle.

[0151] Furthermore, calculate the fitness. For each particle, calculate its fitness, that is, the objective function value W t 。

[0152] Furthermore, check whether all the constraint conditions are satisfied. If not, apply a penalty function to the particles that violate the constraints to reduce their fitness values:

[0153]

[0154] Among them, f(x) represents the original objective function, and g i (x) represents the constraint condition, and λ i represents the penalty factor

[0155] Furthermore, update the particle best position pbest. For each particle, if the current fitness is better than its historical best fitness, update its historical best position and fitness; update the global best position gbest, and select the particle position with the best fitness among all particles as the global best position.

[0156] Furthermore, update the velocity and position. Combining the adaptive inertia weight and the dynamic learning factor, the formula is expressed as:

[0157] v i (t + 1) = w(t)·v i (t) + c 1 (t)·r 1 ·(pbest i - x i (t)) + c 2 (t)·r 2 ·(gbest - x i x i (t + 1) = x i (t) + v i (t + 1)

[0158] Among them, w(t) represents the inertia weight; c 1 (t) represents the individual learning factor; c 2 (t) represents the swarm learning factor; r 1 , r 2 represents a random number; v i (t) represents the velocity vector; x i (t) represents the position vector.

[0159] Furthermore, keep the elite particles unchanged; repeat the iteration until the fitness no longer improves significantly; use the final global best position gbest as the optimal solution and decode it into actual physical variables.

[0160] Furthermore, verify whether the optimal solution satisfies all the constraint conditions, use the penalty function method to adjust the fitness of the particles that violate the constraints, and correct the positions of the particles that violate the constraints to the nearest feasible solutions; if the optimal solution satisfies all the constraint conditions, output the optimal solution and its objective function value.

[0161] Furthermore, the optimal solution is output, including the optimal steam flow rate and the optimal enthalpy of inlet and outlet steam; the corresponding objective function value is output to obtain the optimal power control strategy.

[0162] It should be noted that the overall production of the nuclear power plant is optimized by the improved particle swarm optimization algorithm. The innovation of this step lies in that it not only considers the maximization of power output, but also takes into account the safety of the reactor and the stability of the system. This algorithm ensures the optimal power output under the premise of meeting all safety constraints by intelligently adjusting the positions and velocities of the particles.

[0163] On the other hand, the present embodiment also provides a nuclear power safety production control system, which includes:

[0164] A data collection and preprocessing module, which collects the safety production operation data of the nuclear power plant and preprocesses the operation data; collects the data of the reactor, coolant, steam generator, steam turbine, control system, operation and maintenance from sensors and monitoring systems.

[0165] A mathematical model construction and optimization module, which constructs a nuclear power plant production mathematical model according to the operation data, analyzes and obtains the objective function and constraint conditions for safety production, and constructs an optimization model.

[0166] A transient response prediction and evaluation module, which establishes a transient response process and uses a deep learning algorithm for prediction; evaluates the prediction results and conducts operation regulation according to the results.

[0167] An optimization and regulation strategy module, which uses the improved particle swarm algorithm to optimize the optimization model; obtains the optimal regulation strategy.

[0168] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0169] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in conjunction with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0170] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0171] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0172] Embodiment 2

[0173] The following is an embodiment of the present invention, which provides a nuclear power safety production control method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0174] Data acquisition: Collect the operation data of the nuclear power plant through a real-time monitoring system, including parameters such as the neutron density, reactivity, coolant temperature, and flow rate of the reactor, as well as data such as the steam flow rate and enthalpy value of the steam generator and steam turbine. The data acquisition period is once per hour and lasts for one month.

[0175] Data processing: Preprocess the collected data, including removing outliers, filling in missing values, and normalizing, to ensure the accuracy and consistency of the data.

[0176] Model establishment: Based on the collected data, construct a reactor nuclear reaction kinetics model, a thermal-hydraulics model, a steam generator model, and a steam turbine model. Specific formulas include the neutron kinetics equation, the fission product concentration equation, the thermal-hydraulics equation, the mass and energy conservation equations, etc.

[0177] Transient response process: Use deep learning algorithms for prediction, evaluate the operating data, and perform real-time regulation according to the evaluation results.

[0178] Optimize the model: Under the constraint conditions of safe production, optimize the nuclear power production capacity, and use an improved particle swarm algorithm for optimization operations. Some experimental results are shown in Table 1.

[0179] Table 1 Partial test object table of the simulated power station.

[0180]

[0181] By comparing parameters such as the neutron density, current reactivity, coolant temperature, secondary side steam flow rate, steam inlet enthalpy, and outlet enthalpy of each test object, the following is analyzed:

[0182] Neutron density and reactivity: The neutron density and current reactivity of each test object are within a reasonable range, indicating that the reactor nuclear reaction kinetics model can effectively monitor and control the operating state of the reactor to ensure the safety of the reactor.

[0183] Coolant temperature: The coolant temperature varies between 290°C and 310°C. By regulating the coolant temperature through the thermal-hydraulics model, it is possible to effectively prevent the coolant temperature from being too high and ensure the safe operation of the reactor.

[0184] Steam flow rate and enthalpy value: The data of the secondary side steam flow rate and steam enthalpy value indicate that through the steam generator and steam turbine models, it is possible to effectively optimize the steam flow and energy conversion and improve the energy efficiency of the nuclear power plant.

[0185] Compared with the prior art, the transient response process and optimization model of the present invention can achieve precise monitoring and prediction: Through deep learning algorithms and an improved particle swarm optimization algorithm, precise monitoring and prediction of the operating state of the nuclear power plant are realized, enabling rapid response and regulation of unexpected operating states, and improving the safety and stability of the nuclear power plant.

[0186] Optimize energy efficiency: The optimization model achieves the best balance among power output, reactor safety, and system stability. Through real-time regulation and optimization, the energy efficiency and production efficiency of the nuclear power plant are improved.

[0187] Innovative control strategy: By constructing an overall cycle mathematical model for nuclear power plant production and combining deep learning and optimization algorithms, the present invention proposes an innovative control strategy, significantly improving the response ability and regulation effect of nuclear power plants under complex operating conditions.

[0188] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A nuclear power production safety control method, characterized in that: include: Collect operational data on safe production of nuclear power plants; Construct a nuclear power plant production mathematical model based on operating data, analyze and obtain the objective function and constraints of safe production, and build an optimization model; Establish a transient response process, use deep learning algorithms for prediction, and evaluate the results for operational control; Under the constraints of safe production, the nuclear power capacity is optimized to obtain the optimal control strategy; The operation transient response model includes: the operation transient response refers to the dynamic regulation based on the results of the transient response evaluation model when the unit is in a state that deviates unexpectedly from safe and stable operation; The transient response evaluation model formula is expressed as: Where N represents the number of delayed neutron precursors; P i (t) represents the power corresponding to the i-th group of precursors; λ i represents the decay constant of the i-th group of precursors; β i represents the effective neutron production rate of the i-th group of precursors; Λ represents the average neutron lifetime; p(t) represents the system pressure; μ represents the expected value of the pressure; σ represents the standard deviation of the pressure; represents the decay term, describing the transient change of the precursor concentration; The normal distribution function formula of pressure is expressed as: Make a judgment based on the relationship between the evaluation result E(t) of the transient response evaluation model and the expected operating conditions, and make adjustments based on the judgment result; The transient response process includes running a transient response model and monitoring nuclear power plant operation data; When the evaluation result E(t)>0.1 based on the operating data, the system is running stably, and monitoring continues, and system parameters are checked regularly to ensure that all parameters are within the normal range; when the evaluation result 0.1≥E(t)>0, the system is close to a critical state and needs to be adjusted appropriately; adjust the coolant temperature and flow, adjust the control input, and reduce the reactor power output; when the evaluation result E(t)≤0, it is determined that the system is running unstable and requires major adjustments; significantly increase the coolant flow and reduce the coolant temperature, immediately reduce the reactor power output, start the emergency shutdown procedure, and adjust the control input; judge and classify the events that occur in the power plant according to the various constraint condition thresholds of the emergency state; After a shutdown or major transient regulation occurs, conduct relevant investigations and cause analysis, and upon completion restart the reactor and resume full power operation; The optimal control strategy includes: using a modified particle swarm algorithm to perform an optimization operation on the optimization model; initializing particles and calculating the initial fitness of each particle; Calculate the fitness. For each particle, calculate its fitness, that is, the objective function value W t ; Check whether all constraints are met. If not, apply a penalty function to particles that violate the constraints to reduce their fitness values: Among them, f(x) represents the original objective function, g i (x) represents the constraint condition, λ i Penalty factor Update the particle's best position pbest. For each particle, if the current fitness is better than its historical best fitness, update its historical best position and fitness; update the global best position gbest. Among all particles, select the particle position with the best fitness as the global best position; Update speed and position, combined with adaptive inertia weight and dynamic learning factor, the formula is expressed as: v i (t+1)=w(t)·v i (t)+c1(t)·r1·(pbest i -x i (t))+c2(t)·r2·(gbest-x i x i (t+1)=x i (t)+v i (t+1) Among them, w(t) represents the inertia weight; c1(t) represents the individual learning factor; c2(t) represents the group learning factor; r1, r2 represent random numbers; v i (t) represents the velocity vector; x i (t) represents the position vector; Keep the elite particles unchanged; repeat the iteration until the fitness is no longer significantly improved; take the final global best position gbest as the optimal solution and decode it into actual physical variables; Verify whether the optimal solution satisfies all constraints, use the penalty function method to adjust the fitness of particles that violate the constraints, and correct the position of particles that violate the constraints to the nearest feasible solution; if the optimal solution satisfies all constraints, output the optimal solution and its objective function value; Output the optimal solution, including the optimal steam flow rate and the optimal inlet and outlet steam enthalpy; output the corresponding objective function value to obtain the optimal power control strategy.

2. The nuclear power production safety control method according to claim 1, characterized in that: The operation data includes data related to the reactor and coolant, data related to the steam generator and steam turbine, data related to the control system, and data related to operation and maintenance; The overall cycle mathematical model of nuclear power plant production includes; The neutron kinetic equation of the reactor nuclear reaction kinetic model is expressed as: Where N is the neutron density, ρ is the reactivity, β is the delayed neutron fraction, Λ is the average neutron lifetime, and C i represents the delayed neutron precursor population concentration, λ i represents the delayed neutron precursor decay constant; The fission product concentration equation is expressed as: Among them, β i represents the fraction of the i-th delayed neutron precursor; The thermal hydraulics model describes the conservation of mass and energy of the coolant: The mass conservation equation is expressed as: The energy conservation equation is expressed as: Where M represents the coolant mass, Indicates incoming traffic; Describe the output flow; represents the input heat; Output heat; h in represents the input enthalpy; h out State the enthalpy of the final output.

3. The nuclear power production safety control method according to claim 2, characterized in that: The constructing of the nuclear power plant production mathematical model includes obtaining a mathematical model of the nuclear power plant power output according to the overall cycle mathematical model of the nuclear power plant production; The steam generator model includes the primary side mass conservation equation as follows: Among them, M p represents the mass of the primary side coolant; E represents energy; M represents the mass of the coolant; Indicates flow rate; The energy conservation equation on the primary side is expressed as: Among them, E p Indicates energy, and Represent the heat transfer on the primary and secondary sides respectively; The steam turbine model describes the expansion and work process of steam at each stage as follows: Among them, W t Indicates the turbine output power; Indicates steam flow rate; h s,in Indicates the intake enthalpy of steam; h s,out It represents the steam outlet enthalpy.

4. The nuclear power production safety control method according to claim 3, characterized in that: The objective function and constraint conditions include analyzing the overall cycle mathematical model of nuclear power plant production and the power output model of the nuclear power plant; under the safe production of the nuclear power plant, the objective function and constraint conditions of optimal power control need to consider the maximization of power output, the safety of the reactor and the stability of the system; The objective function is expressed as: The constraints include: the reactor safety constraints are expressed as: ρ(t)≤ρ max Among them, ρ(t) represents the current reactivity; ρ max indicates maximum reactivity; Coolant flow and temperature limits are expressed as: T coolant ≤T coolant,max Among them, T coolant Indicates the current coolant temperature; T coolant,max Indicates the maximum temperature of the coolant; The steam generator and turbine constraints are expressed as: in, Indicates the current secondary side steam flow; Secondary side steam flow; control input limit: u(t)≤u max Where u(t) represents the current control input; u max represents the maximum value of the control input; the environmental and operating constraints are expressed as: t operation ≤t operation,max Among them, t operation Indicates the current operation time; t operation,max Maximum safe operating time.

5. A nuclear power production safety control system using the method according to any one of claims 1 to 4, characterized in that: Data collection and preprocessing module, which collects the safe production and operation data of nuclear power plants and preprocesses the operation data; collects reactor, coolant, steam generator, turbine, control system, operation and maintenance data from sensors and monitoring systems; Mathematical model building and optimization module: builds the nuclear power plant production mathematical model based on the operation data, analyzes the objective function and constraint conditions of safe production, and builds the optimization model; The transient response prediction and evaluation module establishes a transient response process and uses deep learning algorithms to make predictions; evaluates the prediction results and performs operation control based on the results; The optimization and control strategy module uses the improved particle swarm algorithm to optimize the optimization model and obtain the optimal control strategy.

6. A computer device comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the nuclear power safety production control method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the nuclear power production safety control method according to any one of claims 1 to 4 are implemented.

Images