WO2024060480A1 - 核反应堆多参数优化方法、装置、计算机设备和存储介质 - Google Patents

核反应堆多参数优化方法、装置、计算机设备和存储介质 Download PDF

Info

Publication number
WO2024060480A1
WO2024060480A1 PCT/CN2023/074349 CN2023074349W WO2024060480A1 WO 2024060480 A1 WO2024060480 A1 WO 2024060480A1 CN 2023074349 W CN2023074349 W CN 2023074349W WO 2024060480 A1 WO2024060480 A1 WO 2024060480A1
Authority
WO
WIPO (PCT)
Prior art keywords
optimization
optimized
parameter
value
parameters
Prior art date
Application number
PCT/CN2023/074349
Other languages
English (en)
French (fr)
Inventor
李亮国
孟祥飞
南宗宝
余健明
刘继墉
卢冬华
邢军
苏前华
吴小航
柳红超
Original Assignee
中广核研究院有限公司
中广核工程有限公司
中国广核集团有限公司
中国广核电力股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中广核研究院有限公司, 中广核工程有限公司, 中国广核集团有限公司, 中国广核电力股份有限公司 filed Critical 中广核研究院有限公司
Publication of WO2024060480A1 publication Critical patent/WO2024060480A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Definitions

  • This application relates to the field of big data technology, and in particular to a nuclear reactor multi-parameter optimization method, device, computer equipment, storage medium and computer program product.
  • reactor design usually relies on experience accumulation and expert judgment to determine relevant design parameters, thereby optimizing reactor-related design solutions. This results in a long determination period of design parameters, low reactor design efficiency, and designs obtained by manual judgment. Parameters are also prone to errors, leading to the failure to guarantee the safety and other performance of the designed reactor.
  • a nuclear reactor multi-parameter optimization method device, computer equipment, computer-readable storage medium and computer program product are provided.
  • this application provides a nuclear reactor multi-parameter optimization method, which method includes:
  • the optimization parameter model is pre-constructed according to the adaptive moment estimation algorithm
  • the initial design plan is updated according to the target optimization value of each parameter to be optimized.
  • generating an optimization function based on the initial design plan and each of the parameters to be optimized includes:
  • An optimization function is generated according to each parameter to be optimized and the optimization weight of each parameter to be optimized.
  • the optimization parameter model is called to solve the optimization function to obtain the optimization value of each parameter to be optimized, including:
  • Each of the standard values is used as an input value of the adaptive moment estimation algorithm to perform an iterative update calculation to obtain an iterative update value of each of the standard values;
  • the optimization value of each of the parameters to be optimized is determined based on each of the iterative update values.
  • determining the optimization value of each of the parameters to be optimized based on each of the iterative update values includes:
  • determining the standard values of each parameter to be optimized based on the initial design plan includes:
  • Each initial value is normalized to obtain a standard value of each parameter to be optimized corresponding to each initial value.
  • determining whether the optimization function converges based on the optimization value of each parameter to be optimized also includes:
  • the optimized value of each of the parameters to be optimized is input into the analysis model, the optimized value of each of the basic parameters is obtained, and the optimized value of each of the basic parameters is recorded.
  • this application also provides a nuclear reactor multi-parameter optimization device, which includes:
  • a parameter acquisition module used to acquire the parameters to be optimized of the target optimization object in the nuclear reactor, as well as the initial design plan of the nuclear reactor;
  • a function generation module configured to generate an optimization function of the target optimization object according to the initial design plan and each of the parameters to be optimized
  • the function solving module is used to call the optimization parameter model to solve the optimal solution of the optimization function and obtain the optimization value of each of the parameters to be optimized.
  • the optimization parameter model is pre-constructed according to the adaptive moment estimation algorithm;
  • a parameter optimization module configured to determine whether the optimization function converges based on the optimization value of each parameter to be optimized, and if it converges, determine that the optimization value of each parameter to be optimized is the target optimization value of each parameter to be optimized;
  • a solution update module configured to update the initial design solution according to the target optimization value of the parameter to be optimized.
  • the function generation module is further configured to: determine the optimization target of the target optimization object according to the initial design plan; determine the optimization weight of each of the parameters to be optimized based on the optimization target; and according to Each parameter to be optimized and the optimization weight of each parameter to be optimized generate an optimization function.
  • the function solving module is also used to: determine the standard value of each parameter to be optimized according to the initial design plan; use each standard value as an input value of the adaptive moment estimation algorithm to iterate Update calculation to obtain the iterative update value of each of the standard values; and if each of the iterative update values satisfies the update end condition, determine the optimization value of each of the parameters to be optimized based on each of the iterative update values.
  • the function solving module is further configured to: determine the constraints of each of the parameters to be optimized according to the initial design plan; and compare each of the iteratively updated values with the constraints of the corresponding parameters to be optimized. After comparison, if each iterative update value satisfies the constraint condition of the corresponding parameter to be optimized, then the optimization value of each parameter to be optimized is determined based on each iterative update value and the standard value of each parameter to be optimized.
  • the function solving module is also used to: determine the initial values of each of the parameters to be optimized according to the initial design plan; and perform normalization processing on each of the initial values to obtain the corresponding initial values.
  • the standard value corresponding to each parameter to be optimized is also used to: determine the initial values of each of the parameters to be optimized according to the initial design plan; and perform normalization processing on each of the initial values to obtain the corresponding initial values. The standard value corresponding to each parameter to be optimized.
  • the nuclear reactor parameter optimization device further includes: an analysis module for obtaining basic parameters of the target optimization object, where the basic parameters include each of the parameters to be optimized; and analyzing the parameters according to the basic parameters. Model the target optimization object to obtain an analysis model of the target optimization object; and input the optimization value of each of the parameters to be optimized into the analysis model to obtain the optimization value of each of the basic parameters. The optimized values of the above basic parameters are recorded.
  • the present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned nuclear reactor multi-parameter optimization method when executing the computer program.
  • the present application also provides a computer-readable storage medium on which a computer program is stored.
  • the computer program is executed by a processor, the steps of the above-mentioned nuclear reactor multi-parameter optimization method are implemented.
  • this application also provides a computer program product, including a computer program that implements the steps of the above nuclear reactor multi-parameter optimization method when executed by a processor.
  • Figure 1 is an application environment diagram of a nuclear reactor multi-parameter optimization method according to some embodiments
  • Figure 2 is a schematic flow chart of a multi-parameter optimization method for a nuclear reactor according to some embodiments
  • Figure 3 is a schematic flowchart of the steps of generating an optimization function based on the initial design plan and various parameters to be optimized according to some embodiments;
  • Figure 4 is a schematic flowchart of the steps of calling the optimization parameter model to solve the optimization function and obtain the optimization value of each parameter to be optimized according to some embodiments;
  • Figure 5 is a schematic flow chart of a multi-parameter optimization method for a nuclear reactor according to some embodiments
  • Figure 6 is a schematic flow diagram of a multi-parameter optimization method for a nuclear reactor according to some embodiments.
  • Figure 7 is a schematic flow chart of a multi-parameter optimization method for a nuclear reactor according to some embodiments.
  • Figure 8 is a structural block diagram of a nuclear reactor multi-parameter optimization method device according to some embodiments.
  • Figure 9 is an internal structure diagram of a computer device according to some embodiments.
  • the nuclear reactor multi-parameter optimization method provided by the embodiment of the present application can be applied in the application environment as shown in Figure 1.
  • the parameter optimization platform 102 communicates with the user terminal 104.
  • the data storage system can store data that the parameter optimization platform 102 needs to process.
  • the data storage system can be integrated on the parameter optimization platform 102, or placed on the cloud or other network servers.
  • the parameter optimization platform obtains the parameters to be optimized of the target optimization object in the nuclear reactor and the initial design plan of the nuclear reactor sent by the user terminal 104, generates the optimization function of the target optimization object based on the initial design plan and the parameters to be optimized, and calls the optimization parameter model to optimize the function Solve to obtain the optimization value of each parameter to be optimized.
  • the optimization parameter model is pre-constructed according to the adaptive moment estimation algorithm.
  • the user terminal 104 can be, but is not limited to, various personal computers, laptops, smart phones, tablets, Internet of Things devices, and portable wearable devices.
  • the Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, and smart vehicle-mounted devices. wait.
  • Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.
  • the parameter optimization platform 102 can be implemented using an independent server or a server cluster composed of multiple servers.
  • a multi-parameter optimization method for a nuclear reactor is provided.
  • the application of this method to the parameter optimization platform in Figure 1 is used as an example to illustrate, including the following steps:
  • Step 202 Obtain the parameters to be optimized of the target optimization object in the nuclear reactor and the initial design plan of the nuclear reactor.
  • the target optimization object is the equipment to be optimized among the equipment that constitutes the nuclear reactor, such as the inverted U in the nuclear reactor.
  • the parameters to be optimized of the target optimization object are extracted from the structural parameters and thermal parameters of the target optimization object.
  • the structure of the inverted U-shaped natural circulation steam generator Parameters include but are not limited to steam generator height, heat transfer tube height, heat transfer tube outer diameter, heat transfer tube outer diameter, heat transfer tube number, etc.
  • the thermal parameters include but are not limited to steam generator primary side flow rate, steam generator Primary side inlet and outlet temperature, steam generator secondary side flow rate, steam generator secondary side inlet and outlet temperature, etc.
  • the parameters to be optimized for the steam generator can be the steam generator volume (V), the primary side outlet temperature (T), the maximum flow rate of the primary side inlet and outlet ( ⁇ 1 ), the maximum secondary side flow rate ( ⁇ 2 ), and the maximum heat flow. Density (Q), etc.
  • the initial design plan is a design plan designed by the designer based on the empirical data and historical usage data of the nuclear reactor.
  • the initial design plan can reflect the initial values of each basic parameter of each equipment that constitutes the nuclear reactor, the value range of each basic parameter, and the value range of each basic parameter. The coupling relationship between basic parameters and the optimization goals of each device, etc.
  • the parameter optimization platform obtains the parameters to be optimized of the target optimization object in the nuclear reactor sent by the user based on the user terminal, as well as the initial design plan of the nuclear reactor.
  • Step 204 Generate an optimization function of the target optimization object according to the initial design solution and the parameters to be optimized.
  • the optimization function is a function used to optimize each parameter to be optimized in the target optimization object, and the optimization function is generated based on the optimization method. It can be understood that the optimization function is based on a number of given variables, that is, an objective function composed of parameters to be optimized. By making the objective function value the largest or smallest when the variables take a certain set of values, the value of the variable at this time is called optimal. untie.
  • the parameter optimization platform can generate the optimization function of the target optimization object together with each parameter to be optimized based on the initial design plan of the nuclear reactor.
  • the optimization function can be an objective function that takes the maximum value maxf(x), or it can be an objective function that takes the minimum value minf(x), depending on the actual situation.
  • Step 206 Call the optimization parameter model to solve the optimization function to obtain the optimization value of each parameter to be optimized.
  • the optimization parameter model is pre-built according to the adaptive moment estimation algorithm.
  • the optimization parameter model is a model used to solve the optimization function. It can be understood that the parameter optimization model is pre-built according to the adaptive moment estimation algorithm and configured on the parameter optimization platform.
  • Adaptive moment estimation algorithm (adaptive moment estimation, Adam) is a random objective function optimization algorithm based on first-order gradients.
  • the Adam algorithm can be intuitively understood as the sum of the RMSprop algorithm and the Momentum algorithm, which combines the advantages of the two algorithms.
  • Adam has high computational efficiency, low storage capacity requirements, invariant diagonal rescaling of gradients, and is very suitable for larger problems in data/parameters, multi-dimensional and complex models, and has faster convergence speed.
  • the parameter optimization platform is encapsulated with a pre-built model based on the adaptive moment estimation algorithm that can solve various optimization functions. After generating the optimization function of the target optimization object, the parameter optimization platform calls the preset optimization parameter model to optimize the function. Solve and obtain the optimized values of each parameter to be optimized.
  • Step 208 Determine whether the optimization function converges based on the optimization value of each parameter to be optimized. If it converges, determine the optimization value of each parameter to be optimized as the target optimization value of each parameter to be optimized.
  • the optimization value of each parameter to be optimized can make the optimization function converge, it means that the optimization value of each parameter to be optimized is the optimal solution of the optimization function, and the initial design plan of the nuclear reactor can be updated based on the optimization value of each parameter to be optimized. If the optimization value of each parameter to be optimized cannot make the optimization function converge, it means that the optimization value of each parameter to be optimized is not the optimal solution of the optimization function. If the initial design plan is directly updated based on the optimization value of each parameter to be optimized at this time, This may cause the parameter values of each parameter in the updated scheme to be inaccurate.
  • the parameter optimization platform determines whether the optimization function converges based on the optimization value of each parameter to be optimized. When it is determined that the optimization value of each parameter to be optimized can make the optimization function converge, the current optimization value of each parameter to be optimized is determined as each parameter to be optimized. The target optimization value of the parameter.
  • Step 210 Update the initial design plan according to the target optimization value of each parameter to be optimized.
  • the parameter optimization platform updates the parameter values of the basic parameters corresponding to the target optimization objects in the initial design plan according to the target optimization values of each parameter to be optimized, and obtains the updated optimized design plan of the nuclear reactor.
  • the parameters to be optimized of the target optimization object in the nuclear reactor and the initial design plan of the nuclear reactor are obtained, the optimization function of the target optimization object is generated based on the initial design plan and the parameters to be optimized, and the adaptive moment estimation algorithm is called
  • the pre-built optimization function model solves the optimization function, which greatly improves the speed of obtaining the optimization value. Since the optimization function is generated based on the initial design plan and the parameters to be optimized, the value obtained by solving the optimization function can be considered After optimizing the parameter values, it is judged whether the optimization function has converged based on the optimization value of each parameter to be optimized.
  • the optimization value obtained at this time is the optimal solution of the optimization function
  • the optimization value to be optimized is The optimization value of the optimization function is determined as the target optimization value of the parameter to be optimized, and the initial design plan is updated according to the target optimization value of the parameter to be optimized, which effectively improves the efficiency and accuracy of the optimization of nuclear reactor parameters and design plans.
  • an optimization function is generated based on the initial design plan and various parameters to be optimized, including:
  • Step 302 Determine the optimization target of the target optimization object according to the initial design plan.
  • the optimization target of the target optimization object is designed according to the setting scenario of the nuclear reactor.
  • the optimization target can be high-performance compact layout. It can be understood that when designing the initial design plan of the nuclear reactor, the designer binds the target optimization object and its corresponding optimization target and records them in the initial design plan.
  • the parameter optimization platform searches for the optimization target corresponding to the target optimization object from the initial design plan based on the target optimization object.
  • Step 304 Determine the optimization weight of each parameter to be optimized based on the optimization goal.
  • the optimization goal of the target optimization object can determine the optimization weight of each parameter to be optimized. For example, if the optimization goal is a high-performance compact layout, it is necessary to assign higher weights to parameters such as volume.
  • the target optimization object is a nuclear reactor, U Taking a natural circulation steam generator as an example, the optimization parameters are the steam generator volume (V), the primary side outlet temperature (T), the maximum flow rate of the primary side inlet and outlet ( ⁇ 1 ), the maximum flow rate of the secondary side ( ⁇ 2 ), Maximum heat flux density (Q).
  • the basic model of the optimization function is determined as minf(x).
  • Step 306 Generate an optimization function based on each parameter to be optimized and the optimization weight of each parameter to be optimized.
  • the parameter optimization platform After determining the optimization weight corresponding to each parameter to be optimized, the parameter optimization platform generates an optimization function based on each parameter to be optimized and the optimization weight corresponding to each parameter to be optimized.
  • the parameter optimization platform determines the optimization goal of the target optimization object according to the initial design plan, determines the optimization weight of each parameter to be optimized based on the optimization goal, and generates an optimization function based on each parameter to be optimized and the optimization weight of each parameter to be optimized.
  • the optimization goal determines the optimization weight of each parameter to be optimized, which can ensure that the generated optimization function fully considers the important proportion of each parameter to be optimized in the optimization goal, thereby improving the accuracy of nuclear reactor parameter optimization.
  • the optimization parameter model is called to solve the optimization function and the optimization values of each parameter to be optimized are obtained, including:
  • Step 402 Determine the standard values of each parameter to be optimized based on the initial design plan.
  • determining the standard value of each of the parameters to be optimized according to the initial design plan includes: determining the initial value of each of the parameters to be optimized according to the initial design plan; and normalizing each of the initial values. Through unification processing, the standard value of each parameter to be optimized corresponding to each initial value is obtained.
  • the initial design plan of the nuclear reactor includes the initial values of each parameter to be optimized for the target optimization object.
  • the initial values are normalized, that is, the dimensionless value of the initial value is calculated, and the initial value of the parameter to be optimized is obtained.
  • nondimensionalization refers to removing some or all of the units of an equation involving physical quantities through a suitable variable replacement in order to simplify experiments or calculations. It is an important method in scientific research. processing ideas.
  • the initial value of the flow parameter is 250m3/h. If the initial value is dimensionless, the standard value obtained is 1. This 1 corresponds to 250m3/h.
  • Step 404 Use each standard value as an input value of the adaptive moment estimation algorithm to perform an iterative update calculation to obtain an iterative update value of each standard value.
  • each standard of each parameter to be optimized in the optimization function is used as a set of input parameters, and the input parameter is a multi-dimensional vector.
  • the initialization parameters include the step value ⁇ and the initial parameters ⁇ i of each parameter to be optimized.
  • the initial parameters are the standard values corresponding to each parameter to be optimized obtained in step 402. , the numerical stability quantity ⁇ , the first-order momentum attenuation coefficient ⁇ 1 , and the second-order momentum attenuation coefficient ⁇ 2 .
  • the first-order momentum s and the second-order momentum r are all initialized to 0. It can be understood that the numerical stability quantity, first-order momentum attenuation coefficient, and second-order momentum attenuation coefficient can all use the preset values of the adaptive moment estimation algorithm, or can be set by the designer according to the actual situation.
  • the numerical stability quantity is 10 -8
  • the first-order momentum attenuation coefficient is 0.9
  • the second-order momentum attenuation coefficient is 0.999.
  • the gradient of the objective function f(x) of the optimization function with respect to x is a vector composed of partial derivatives:
  • Each partial derivative element in the gradient Represents the rate of change of f(x) at xi .
  • the adaptive moment estimation algorithm not only computes an estimate of the second moment of the exponentially decaying gradient squared v t , it also computes an estimate of the first moment of the exponentially decaying gradient m t , similar to momentum.
  • m t ⁇ 1 m t-1 +(1 ⁇ 1 )g t
  • m t is the estimate (mean) of the first-order moment, initialized to a 0 vector
  • v t is the estimate (variance) of the second-order moment, initialized to a 0 vector.
  • Step 406 If each iterative update value satisfies the update end condition, determine the optimization value of each parameter to be optimized based on each iterative update value.
  • the update end condition is that the gradient descent distance of all calculated iterative update values is less than the numerical stability amount. If the gradient descent distance of each iterative update value is less than the numerical stability amount, then it is determined based on the iterative update value at this time. is the optimized value of each parameter to be optimized. If the gradient descent distance of each iterative update value has an update value that is greater than the numerical stability amount, return to the iterative step and continue the iterative update until each iterative update value satisfies the update end condition.
  • the standard value of each parameter to be optimized is obtained according to the initial value of each parameter to be optimized, and the standard value is input into the parameter optimization model as part of the initialization parameters in the adaptive moment estimation algorithm for iterative calculation.
  • the optimized value of each parameter to be optimized is obtained based on each iterative update value, which provides a data basis for subsequently obtaining the target optimization value of each parameter to be optimized.
  • determining the optimization value of each parameter to be optimized based on each iterative update value includes: determining the constraint conditions of each parameter to be optimized according to the initial design plan; comparing each iterative update value with the corresponding constraint conditions of the parameter to be optimized. By comparison, if each iterative update value satisfies the constraint condition of the corresponding parameter to be optimized, then the optimization value of each parameter to be optimized is determined based on each iterative update value and the standard value of each parameter to be optimized.
  • the constraint conditions of each parameter to be optimized are the constraints of the value of each parameter to be optimized, which can be the value range of each parameter to be optimized. It is understandable that the constraint conditions of each parameter to be optimized are determined by the designer based on the value of each parameter to be optimized. The usage of the corresponding target optimization object in the actual use process is determined, and is pre-bound with each parameter to be optimized and recorded in the initial design plan.
  • the constraint conditions can be expressed by equations or inequalities.
  • the optimization function is f(x), and the parameters to be optimized are all variables in the optimization function. If there are constraints on the variables, the constraints include all equations and inequalities related to the values of the variables.
  • the feasible domain is the area enclosed by the constraints in space.
  • the feasible solution is that every point in the feasible domain is a feasible point of the original problem.
  • the optimal solution is the feasible solution that can make the optimization function reach the maximum or minimum.
  • the parameter optimization platform determines the constraints of each parameter to be optimized from the initial design plan based on each parameter to be optimized, and compares each iterative update value with the corresponding constraint conditions of the parameter to be optimized. If any of the iterative update values does not satisfy The corresponding update value of the constraint of the parameter to be optimized means that the iterative update value obtained here cannot be used. If it is forcibly used, it will easily put the safety of the nuclear reactor at risk. It is necessary to readjust the optimization according to the gradient and step size inverse optimization. The iteratively updated value of the parameter.
  • the optimization value of each parameter to be optimized is determined based on each iterative update value and the standard value of each parameter to be optimized.
  • the standard value of the flow optimization parameter is 1 corresponding to 250m3/h.
  • the iterative update value is 1.2.
  • the parameter optimization platform compares the iteratively updated value of each parameter to be optimized with the constraint conditions corresponding to each parameter to be optimized, and then determines whether the iteratively updated value is It can be directly used as the optimization value of each parameter to be optimized, further ensuring the safety and accuracy of the optimization value of each parameter to be optimized.
  • determining whether the optimization function has converged based on the optimization value of each parameter to be optimized also includes:
  • Step 502 Obtain the basic parameters of the target optimization object.
  • the basic parameters include parameters to be optimized.
  • the parameter optimization platform obtains the basic parameters of the target optimization object from the initial design plan.
  • the basic parameters are the structural parameters and thermal parameters of the target optimization object.
  • the basic parameters include various parameters to be optimized that need to be optimized.
  • Step 504 Model the target optimization object according to basic parameters to obtain an analysis model of the target optimization object.
  • the parameter optimization platform models the target optimization object based on the obtained basic parameters, and obtains an analysis model of the target optimization object.
  • the parameter optimization platform uses reactor system safety analysis programs such as RELAP and CATHARE to model the basic parameters of the target optimization object to obtain an analysis model of the target optimization object.
  • reactor system safety analysis programs such as RELAP and CATHARE
  • Step 506 Input the optimization value of each parameter to be optimized into the analysis model, obtain the optimization value of each basic parameter, and record the optimization value of each basic parameter.
  • the parameter optimization platform inputs the obtained optimization values of each parameter to be optimized into the analysis model, and based on the coupling association between each basic parameter, each basic parameter is optimized accordingly through the optimization value of each parameter to be optimized, and each basic parameter is obtained. Optimized values of basic parameters, and record and save the optimized values of each basic parameter.
  • the parameter optimization platform saves the optimized values of each basic parameter in the form of a matrix. If the optimized values of each parameter to be optimized cannot make the optimization function converge, the saved matrix is directly used as a multi-dimensional vector. Adapting the input parameters in the moment estimation algorithm makes the calculation more convenient and faster.
  • updating the initial design scheme according to the target optimization value of each parameter to be optimized includes: inputting the target optimization value of each parameter to be optimized into the analysis model to obtain the target optimization value of the basic parameters of the target optimization object, and updating the initial design scheme according to the target optimization value of the basic parameters of the target optimization object to obtain an optimized design scheme of the nuclear reactor.
  • the parameter optimization platform models the target optimization object according to the basic parameters of the target optimization object to obtain an analysis model of the target optimization object.
  • the analysis model analyzes the optimization values of each parameter to be optimized and obtains the optimization of each basic parameter.
  • the parameter optimization platform records the optimized values of each basic parameter. Based on the coupling relationship between each parameter to be optimized and other parameters in the basic parameters, the optimized value of the basic parameter is obtained through the optimization value of each parameter to be optimized, which provides a data basis for subsequent updates of the initial design plan and a more accurate optimized design plan. .
  • a nuclear reaction multi-parameter optimization method is provided, as shown in Figure 6.
  • the method is generally divided into 5 steps, which are:
  • Step 601 Establish a multi-objective optimization function of the target optimization object.
  • Step 602 Model the target optimization object.
  • Step 603 Call the optimization parameter model to perform multi-objective parameter optimization analysis based on the adaptive moment estimation algorithm.
  • Step 604 Obtain multi-objective parameter optimization results.
  • Step 605 Update the initial design plan to obtain the optimized design plan.
  • the parameter optimization platform determines the parameters to be optimized of the steam generator and the initial design plan of the target optimization object.
  • the parameters to be optimized include the steam generator volume (V), the primary side outlet temperature (T), the maximum flow rate of the primary side inlet and outlet ( ⁇ 1 ), the maximum secondary side flow rate ( ⁇ 2 ), and the maximum heat flow density (Q )
  • the initial design plan includes the basic parameters of each target optimization object, the initial values of each parameter to be optimized, the constraint boundary conditions of each parameter to be optimized, the optimization goals of each target optimization object, etc.
  • the optimization parameter model perform parameter optimization on each parameter to be optimized based on the optimization function, the standard value of each parameter to be optimized, and the constraint boundary conditions of each parameter to be optimized, and find the optimal value of each parameter to be optimized. Determine the parameters to be optimized Whether the optimization value satisfies the boundary value in the constraint boundary condition, if not, inverse optimization is performed based on the gradient and step size.
  • the basic parameters are the thermal parameters and structural parameters of the target optimization object.
  • the basic parameters mainly include the height of the steam generator, the height of the heat transfer tube, the outer diameter of the heat transfer tube, Structural parameters such as outer diameter of heat transfer tubes and number of heat transfer tubes, thermal engineering parameters such as steam generator primary side flow rate, steam generator primary side inlet and outlet temperature, steam generator secondary side flow rate, steam generator secondary side inlet and outlet temperature, etc. parameter.
  • embodiments of the present application also provide a nuclear reactor multi-parameter optimization device for implementing the above-mentioned nuclear reactor multi-parameter optimization method.
  • the solution to the problem provided by this device is similar to the solution recorded in the above method. Therefore, the specific limitations in the embodiments of one or more nuclear reactor multi-parameter optimization devices provided below can be found in the above article on multi-parameter optimization of nuclear reactors. The limitations of the method will not be repeated here.
  • a nuclear reactor multi-parameter optimization device including: a parameter acquisition module 801, a function generation module 802, a function solution module 803, a parameter optimization module 804 and a solution update module 805, where :
  • the parameter acquisition module 801 is used to acquire various parameters to be optimized of the target optimization object in the nuclear reactor and the initial design scheme of the nuclear reactor.
  • the function generation module 802 is used to generate the optimization function of the target optimization object according to the initial design plan and each parameter to be optimized.
  • the function solving module 803 is used to call the optimization parameter model to solve the optimal solution of the optimization function and obtain the optimized value of each parameter to be optimized.
  • the optimization parameter model is pre-built according to the adaptive moment estimation algorithm.
  • the parameter optimization module 804 is configured to determine whether the optimization function converges based on the optimization value of each parameter to be optimized. If it converges, determine the optimization value of each parameter to be optimized as the target optimization value of each parameter to be optimized.
  • the solution update module 805 is used to update the initial design solution according to the target optimization value of the parameter to be optimized.
  • the above-mentioned nuclear reactor multi-parameter optimization device obtains the parameters to be optimized of the target optimization object in the nuclear reactor and the initial design plan of the nuclear reactor, generates the optimization function of the target optimization object based on the initial design plan and the parameters to be optimized, and calls the adaptive moment estimation algorithm in advance
  • the constructed optimization function model solves the optimization function, which greatly improves the speed of obtaining the optimization value. Since the optimization function is generated based on the initial design plan and the parameters to be optimized, the value obtained by solving the optimization function can be considered as optimization. After the parameter values are passed, it is judged whether the optimization function has converged based on the optimization value of each parameter to be optimized.
  • the optimization value obtained at this time is the optimal solution of the optimization function
  • the optimization value to be optimized is The optimization value of the function is determined as the target optimization value of the parameter to be optimized, and the initial design plan is updated based on the target optimization value of the parameter to be optimized, which effectively improves the efficiency and accuracy of the optimization of nuclear reactor parameters and design plans.
  • the function generation module is also used to: determine the optimization goal of the target optimization object according to the initial design plan; determine the optimization weight of each parameter to be optimized based on the optimization goal; and determine the optimization weight of each parameter to be optimized based on each parameter to be optimized and each parameter to be optimized. Generate optimization functions.
  • the function solving module is also used to: determine the criteria for each parameter to be optimized according to the initial design plan value; use each standard value as the input value of the adaptive moment estimation algorithm for iterative update calculation to obtain the iterative update value of each standard value; if each iterative update value meets the update end condition, determine each parameter to be optimized based on each iterative update value optimized value.
  • the function solving module is also used to: determine the constraints of each parameter to be optimized based on the initial design plan; compare each iterative update value with the constraints of the corresponding parameter to be optimized, and if each iterative update value satisfies the constraints of the corresponding parameter to be optimized, then determine the optimized value of each parameter to be optimized based on each iterative update value and the standard value of each parameter to be optimized.
  • the function solving module is also used to: determine the initial value of each parameter to be optimized according to the initial design plan; perform normalization processing on each initial value to obtain the standard value of each parameter to be optimized corresponding to each initial value. .
  • the nuclear reactor multi-parameter optimization device also includes: an analysis module, used to obtain the basic parameters of the target optimization object, where the basic parameters include various parameters to be optimized; and the target optimization object is modeled according to the basic parameters to obtain the target optimization object.
  • the analysis model input the optimization value of each parameter to be optimized into the analysis model, obtain the optimization value of each basic parameter, and record the optimization value of each basic parameter.
  • Each module in the above-mentioned nuclear reactor multi-parameter optimization device can be realized in whole or in part through software, hardware and their combination.
  • Each of the above modules may be embedded in or independent of the processor of the computer device in the form of hardware, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
  • a computer device may be a terminal or server integrated with a parameter optimization platform, and its internal structure diagram may be as shown in Figure 9.
  • the computer device includes a processor, memory, and network interfaces connected through a system bus. Wherein, the processor of the computer device is used to provide computing and control capabilities.
  • the memory of the computer device includes non-volatile storage media and internal memory.
  • the non-volatile storage medium stores operating systems, computer programs and databases. This internal memory provides an environment for the execution of operating systems and computer programs in non-volatile storage media.
  • the database of the computer equipment is used to store data such as initial design plans, parameters to be optimized, and optimized parameter models.
  • the network interface of the computer device is used to communicate with external terminals through a network connection.
  • the computer program when executed by a processor, implements a nuclear reactor multi-parameter optimization method.
  • Figure 9 is only a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied.
  • Specific computer equipment can May include more or fewer parts than shown, or combine certain parts, or have a different arrangement of parts.
  • a computer device including a memory and a processor.
  • a computer program is stored in the memory.
  • the processor executes the computer program, it implements the following steps:
  • the optimization parameter model is called to solve the optimization function to obtain the optimized value of each parameter to be optimized.
  • the optimization parameter model is pre-built according to the adaptive moment estimation algorithm;
  • the processor when the processor executes the computer program, the processor further implements the following steps:
  • An optimization function is generated according to each parameter to be optimized and the optimization weight of each parameter to be optimized.
  • the processor also performs the following steps when executing the computer program:
  • the optimization value of each parameter to be optimized is determined based on each iteration update value.
  • the processor also performs the following steps when executing the computer program:
  • the processor also performs the following steps when executing the computer program:
  • Each initial value is normalized to obtain the standard value of each parameter to be optimized corresponding to each initial value.
  • the processor also performs the following steps when executing the computer program:
  • a computer-readable storage medium is provided with a computer program stored thereon.
  • the computer program is executed by a processor, the following steps are implemented:
  • the optimization parameter model is called to solve the optimization function and the optimization values of each parameter to be optimized are obtained.
  • the optimization parameter model is pre-built according to the adaptive moment estimation algorithm;
  • An optimization function is generated based on each parameter to be optimized and the optimization weight of each parameter to be optimized.
  • the computer program when executed by the processor, also implements the following steps:
  • the optimization value of each parameter to be optimized is determined based on each iteration update value.
  • the computer program when executed by the processor, also implements the following steps:
  • the computer program when executed by the processor, also implements the following steps:
  • Each initial value is normalized to obtain the standard value of each parameter to be optimized corresponding to each initial value.
  • the computer program when executed by the processor, also implements the following steps:
  • a computer program product comprising a computer program that, when executed by a processor, implements the following steps:
  • the optimization parameter model is called to solve the optimization function and the optimization values of each parameter to be optimized are obtained.
  • the optimization parameter model is pre-built according to the adaptive moment estimation algorithm;
  • the computer program when executed by the processor, also implements the following steps:
  • An optimization function is generated according to each parameter to be optimized and the optimization weight of each parameter to be optimized.
  • the computer program when executed by the processor, also implements the following steps:
  • the optimization value of each parameter to be optimized is determined based on each iteration update value.
  • the computer program when executed by the processor, also implements the following steps:
  • the computer program when executed by the processor, also implements the following steps:
  • Each initial value is normalized to obtain the standard value of each parameter to be optimized corresponding to each initial value.
  • the computer program when executed by the processor, also implements the following steps:
  • the optimized value of each parameter to be optimized is input into the analysis model to obtain the optimized value of each basic parameter, and the optimized value of each basic parameter is recorded.
  • the user information including but not limited to user equipment information, user personal information, etc.
  • data including but not limited to data used for analysis, stored data, displayed data, etc.
  • the computer program can be stored in a non-volatile computer-readable storage.
  • the computer program when executed, may include the processes of the above method embodiments.
  • Any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory.
  • Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetic variable memory (Magnetoresistive Random Access Memory (MRAM), ferroelectric memory (Ferroelectric Random Access Memory (FRAM)), phase change memory (Phase Change Memory, PCM), graphene memory, etc.
  • Volatile memory may include random access memory (Random Access Memory, RAM) or external cache memory.
  • RAM Random Access Memory
  • RAM Random Access Memory
  • RAM random access memory
  • RAM Random Access Memory
  • RAM random access memory
  • RAM Random Access Memory
  • RAM random access memory
  • RAM Random Access Memory
  • SRAM static random access memory
  • DRAM Dynamic Random Access Memory
  • the databases involved in the various embodiments provided in this application may include at least one of a relational database and a non-relational database.
  • Non-relational databases may include blockchain-based distributed databases, etc., but are not limited thereto.
  • the processors involved in the various embodiments provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, and quantum computing-based data processing logic devices. etc., not limited to this.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Water Supply & Treatment (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Monitoring And Testing Of Nuclear Reactors (AREA)

Abstract

一种核反应堆多参数优化方法，包括：获取核反应堆中目标优化对象的各待优化参数，以及核反应堆的初始设计方案；根据初始设计方案与各待优化参数生成目标优化对象的优化函数；调用优化参数模型对优化函数进行求解，得到各待优化参数的优化值，优化参数模型根据自适应矩估计算法预先构建；基于各待优化参数的优化值判断优化函数是否收敛，若收敛，则确定各待优化参数的优化值为各待优化参数的目标优化值；根据各待优化参数的目标优化值更新初始设计方案。

Description

核反应堆多参数优化方法、装置、计算机设备和存储介质
本申请要求2022年09月21日申请的，申请号为202211149834X，名称为“核反应堆多参数优化方法、装置、计算机设备和存储介质”的中国专利申请的优先权，在此将其全文引入作为参考。
技术领域
本申请涉及大数据技术领域，特别是涉及一种核反应堆多参数优化方法、装置、计算机设备、存储介质和计算机程序产品。
背景技术
在随着核电事业的发展，为满足空间核动力、移动核电站和海水淡化等领域的需求，国际上竞相研发结构简单、体积小、重量轻、寿命长、固有安全性好的的新一代反应堆。
传统技术中，反应堆的设计通常依赖经验积累和专家判断来确定相关设计参数，进而实现反应堆相关设计方案的优选，这导致设计参数的确定周期较长，反应堆设计效率低，且人工判断得到的设计参数也容易存在误差，导致设计的反应堆安全性等性能得不到保证。
发明内容
根据本申请的各种实施例提供了一种核反应堆多参数优化方法、装置、计算机设备、计算机可读存储介质和计算机程序产品。
第一方面，本申请提供了一种核反应堆多参数优化方法，所述方法包括：
获取核反应堆中目标优化对象的各待优化参数，以及所述核反应堆的初始设计方案；
根据所述初始设计方案与各所述待优化参数生成所述目标优化对象的优化函数；
调用优化参数模型对所述优化函数进行求解，得到各所述待优化参数的优化值，所述优化参数模型根据自适应矩估计算法预先构建；
基于各所述待优化参数的优化值判断所述优化函数是否收敛，若收敛，则确定各所述待优化参数的优化值为各所述待优化参数的目标优化值；及
根据各所述待优化参数的目标优化值更新所述初始设计方案。
在其中一些实施例中，所述根据所述初始设计方案与各所述待优化参数生成优化函数，包括：
根据所述初始设计方案确定所述目标优化对象的优化目标；
基于所述优化目标确定各所述待优化参数的优化权重；及
根据各所述待优化参数与各所述待优化参数的优化权重生成优化函数。
在其中一些实施例中，所述调用优化参数模型对所述优化函数进行求解，得到各所述待优化参数的优化值，包括：
根据所述初始设计方案确定各所述待优化参数的标准值；
将各所述标准值作为自适应矩估计算法的输入值进行迭代更新计算，得到各所述标准值的迭代更新值；及
若各所述迭代更新值满足更新结束条件，则根据各所述迭代更新值确定各所述待优化参数的优化值。
在其中一些实施例中，所述根据各所述迭代更新值确定各所述待优化参数的优化值，包括：
根据所述初始设计方案确定各所述待优化参数的约束条件；及
将各所述迭代更新值与对应的待优化参数的约束条件进行比较，若各所述迭代更新值均满足对应的待优化参数的约束条件，则根据各所述迭代更新值与各所述待优化参数的标 准值确定各所述待优化参数的优化值。
在其中一些实施例中，所述根据所述初始设计方案确定各所述待优化参数的标准值，包括：
根据所述初始设计方案确定各所述待优化参数的初始值；及
对各所述初始值进行归一化处理，得到与各初始值对应的各所述待优化参数的标准值。
在其中一些实施例中，所述基于各所述待优化参数的优化值判断所述优化函数是否收敛，之前还包括：
获取所述目标优化对象的基本参数，所述基本参数包括各所述待优化参数；
根据所述基本参数对所述目标优化对象进行建模，得到所述目标优化对象的分析模型；及
将各所述待优化参数的优化值输入至所述分析模型中，得到各所述基本参数的优化值，对各所述基本参数的优化值进行记录。
第二方面，本申请还提供了一种核反应堆多参数优化装置，所述装置包括：
参数获取模块，用于获取核反应堆中目标优化对象的各待优化参数，以及所述核反应堆的初始设计方案；
函数生成模块，用于根据所述初始设计方案与各所述待优化参数生成所述目标优化对象的优化函数；
函数求解模块，用于调用优化参数模型对所述优化函数求解最优解，得到各所述待优化参数的优化值，所述优化参数模型根据自适应矩估计算法预先构建；
参数优化模块，用于基于各所述待优化参数的优化值判断所述优化函数是否收敛，若收敛，则确定各所述待优化参数的优化值为各所述待优化参数的目标优化值；及
方案更新模块，用于根据所述待优化参数的目标优化值更新所述初始设计方案。
在其中一些实施例中，所述函数生成模块还用于：根据所述初始设计方案确定所述目标优化对象的优化目标；基于所述优化目标确定各所述待优化参数的优化权重；及根据各所述待优化参数与各所述待优化参数的优化权重生成优化函数。
在其中一些实施例中，所述函数求解模块还用于：根据所述初始设计方案确定各所述待优化参数的标准值；将各所述标准值作为自适应矩估计算法的输入值进行迭代更新计算，得到各所述标准值的迭代更新值；及若各所述迭代更新值满足更新结束条件，则根据各所述迭代更新值确定各所述待优化参数的优化值。
在其中一些实施例中，所述函数求解模块还用于：根据所述初始设计方案确定各所述待优化参数的约束条件；及将各所述迭代更新值与对应的待优化参数的约束条件进行比较，若各所述迭代更新值均满足对应的待优化参数的约束条件，则根据各所述迭代更新值与各所述待优化参数的标准值确定各所述待优化参数的优化值。
在其中一些实施例中，所述函数求解模块还用于：根据所述初始设计方案确定各所述待优化参数的初始值；及对各所述初始值进行归一化处理，得到与各初始值对应的各所述待优化参数的标准值。
在其中一些实施例中，所述核反应堆参数优化装置还包括：分析模块，用于获取所述目标优化对象的基本参数，所述基本参数包括各所述待优化参数；根据所述基本参数对所述目标优化对象进行建模，得到所述目标优化对象的分析模型；及将各所述待优化参数的优化值输入至所述分析模型中，得到各所述基本参数的优化值，对各所述基本参数的优化值进行记录。
第三方面，本申请还提供了一种计算机设备，包括存储器和处理器，所述存储器存储有计算机程序，所述处理器执行所述计算机程序时实现上述核反应堆多参数优化方法的步骤。
第四方面，本申请还提供了一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现上述核反应堆多参数优化方法的步骤。
第五方面，本申请还提供了一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现上述核反应堆多参数优化方法的步骤。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其它特征、目的和优点将从说明书、附图以及权利要求书变得明显。
附图说明
为了更清楚地说明本申请实施例或传统技术中的技术方案，下面将对实施例或传统技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据公开的附图获得其他的附图。
图1为根据一些实施例的核反应堆多参数优化方法的应用环境图；
图2为根据一些实施例的核反应堆多参数优化方法的流程示意图；
图3为根据一些实施例的根据初始设计方案与各待优化参数生成优化函数步骤的流程示意图；
图4为根据一些实施例的调用优化参数模型对优化函数进行求解，得到各待优化参数的优化值步骤的流程示意图；
图5为根据一些实施例的核反应堆多参数优化方法的流程示意图；
图6为根据一些实施例的核反应堆多参数优化方法的流程示意图；
图7为根据一些实施例的核反应堆多参数优化方法的流程示意图；
图8为根据一些实施例的核反应堆多参数优化方法装置的结构框图；
图9为根据一些实施例的计算机设备的内部结构图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本申请实施例提供的核反应堆多参数优化方法，可以应用于如图1所示的应用环境中。其中，参数优化平台102与用户终端104进行通信。数据存储系统可以存储参数优化平台102需要处理的数据。数据存储系统可以集成在参数优化平台102上，也可以放在云上或其他网络服务器上。参数优化平台获取用户终端104发送的核反应堆中目标优化对象的各待优化参数以及核反应堆的初始设计方案，根据初始设计方案与各待优化参数生成目标优化对象的优化函数，调用优化参数模型对优化函数进行求解，得到各待优化参数的优化值，优化参数模型根据自适应矩估计算法预先构建，基于各待优化参数的优化值判断优化函数是否收敛，若收敛，则确定各待优化参数的优化值为各待优化参数的目标优化值，根据待优化参数的目标优化值更新初始设计方案。其中，用户终端104可以但不限于是各种个人计算机、笔记本电脑、智能手机、平板电脑、物联网设备和便携式可穿戴设备，物联网设备可为智能音箱、智能电视、智能空调、智能车载设备等。便携式可穿戴设备可为智能手表、智能手环、头戴设备等。参数优化平台102可以用独立的服务器或者是多个服务器组成的服务器集群来实现。
在一些实施例中，如图2所示，提供了一种核反应堆多参数优化方法，以该方法应用于图1中的参数优化平台为例进行说明，包括以下步骤：
步骤202，获取核反应堆中目标优化对象的各待优化参数，以及核反应堆的初始设计方案。
其中，目标优化对象为构成核反应堆的设备中待优化的设备，例如核反应堆中的倒U 型自然循环蒸汽发生器、驱动汽轮发动机等。目标优化对象的待优化参数是从目标优化对象的结构参数和热工参数中提取得到的，以目标优化对象为倒U型自然循环蒸汽发生器为例，倒U型自然循环蒸汽发生器的结构参数包括但不限于蒸汽发生器高度、传热管高度、传热管外径、传热管外径、传热管数目等，热工参数包括但不限于蒸汽发生器一次侧流速、蒸汽发生器一次侧进出口温度、蒸汽发生器二次侧流速、蒸汽发生器二次侧进出口温度等。而蒸汽发生器的待优化参数可以为蒸汽发生器体积(V)、一次侧出口温度(T)、一次侧进出口的最大流速(ν1)、二次侧最大流速(ν2)、最大热流密度(Q)等。
其中，初始设计方案是设计人员根据核反应堆的经验数据和历史使用数据设计得到的设计方案，初始设计方案可以反映构成核反应堆的各设备的各基本参数的初始值、各基本参数的取值范围、各基本参数之间的耦合关系以及各设备的优化目标等。
具体地，参数优化平台获取用户基于用户终端发送的核反应堆中目标优化对象的各待优化参数，以及核反应堆的初始设计方案。
步骤204，根据初始设计方案与各待优化参数生成目标优化对象的优化函数。
其中，优化函数是用于对目标优化对象中各待优化参数进行优化的函数，优化函数是基于优化方法生成的。可以理解的，优化函数是根据给定的若干变量，即待优化参数组成的目标函数，通过使得变量取某一组值时目标函数值最大或最小，此时变量的取值便称为最优解。
具体地，由于初始设计方案中包括了目标优化对象的各待优化参数的基本信息，因此参数优化平台可以根据核反应堆的初始设计方案与各待优化参数一起生成目标优化对象的优化函数。可以理解的，优化函数可以是取最大值maxf(x)的目标函数，也可以是取最小值minf(x)的目标函数，根据实际情况而定。
步骤206，调用优化参数模型对优化函数进行求解，得到各待优化参数的优化值，优化参数模型根据自适应矩估计算法预先构建。
其中，优化参数模型是用于对优化函数进行求解的模型，可以理解的，参数优化模型是根据自适应矩估计算法预先构建，并配置在参数优化平台上的。
自适应矩估计算法(adaptive moment estimation，Adam)是一种基于一阶梯度的随机目标函数优化算法，Adam算法直观上可以理解为RMSprop算法和Momentum算法的加和，结合了两种算法的优点，Adam计算效率高、存储容量要求低、对梯度的对角重新缩放不变，并且非常适合于数据/参数方面较大的问题、多维复杂的模型，具有更快的收敛速度。
具体地，由于优化函数是基于目标优化对象的多个待优化参数生成的，因此优化函数的求解是一个关键且较为复杂的过程。参数优化平台中封装有根据自适应矩估计算法预先构建的可以对各种优化函数进行求解的模型，在生成了目标优化对象的优化函数后，参数优化平台调用预先设置的优化参数模型对优化函数进行求解，得到各待优化参数的优化值。
步骤208，基于各待优化参数的优化值判断优化函数是否收敛，若收敛，则确定各待优化参数的优化值为各待优化参数的目标优化值。
其中，对优化函数进行求解得到的各待优化参数的优化值是否能使优化函数收敛，是判断各待优化参数的优化值是否是优化函数的最优解的关键条件。
若各待优化参数的优化值能使优化函数收敛，则说明各待优化参数的优化值是该优化函数的最优解，可以根据各待优化参数的优化值更新核反应堆的初始设计方案。若各待优化参数的优化值不能使优化函数收敛，则说明各待优化参数的优化值并不是该优化函数的最优解，如果直接根据此时各待优化参数的优化值更新初始设计方案，可能会导致更新后的方案中各参数的参数值并不准确。
具体地，参数优化平台基于各待优化参数的优化值判断优化函数是否收敛，当确定各待优化参数的优化值能使优化函数收敛时，将当前各待优化参数的优化值确定为各待优化参数的目标优化值。
步骤210，根据各待优化参数的目标优化值更新初始设计方案。
具体地，参数优化平台根据各待优化参数的目标优化值更新初始设计方案中目标优化对象对应的基本参数的参数值，得到更新后的核反应堆的优化设计方案，
上述核反应堆多参数优化方法中，获取核反应堆中目标优化对象的各待优化参数以及核反应堆的初始设计方案，根据初始设计方案和各待优化参数生成目标优化对象的优化函数，调用根据自适应矩估计算法预先构建的优化函数模型对优化函数进行求解，大大提升了得到优化值的速度，由于优化函数是根据初始设计方案和各待优化参数生成的，因此对优化函数进行求解得到的值即可认为是优化过后的参数值，基于各待优化参数的优化值判断优化函数是否收敛，当得到的优化值可以使优化函数收敛时，说明此时得到的优化值为优化函数的最优解，将该待优化函数的优化值确定为待优化参数的目标优化值，并根据待优化参数的目标优化值更新初始设计方案，有效提高了核反应堆参数与设计方案优化的效率与准确性。
在一些实施例中，如图3所示，根据初始设计方案与各待优化参数生成优化函数，包括：
步骤302，根据初始设计方案确定目标优化对象的优化目标。
其中，目标优化对象的优化目标是根据核反应堆的设置场景进行设计的，例如在对性能紧凑性比较高的设置场景中，优化目标可以为高性能紧凑布置。可以理解的，设计人员在设计核反应堆的初始设计方案时，将目标优化对象与其对应的优化目标进行绑定后，记录在初始设计方案中。
具体地，参数优化平台根据目标优化对象从初始设计方案中查找该目标优化对象对应的优化目标。
步骤304，基于优化目标确定各待优化参数的优化权重。
具体地，目标优化对象的优化目标可以决定各待优化参数的优化权重，例如，若优化目标为高性能紧凑布置，则需要对体积等参数赋值较高的权重，以目标优化对象为核反应堆倒U型自然循环蒸汽发生器为例，优化参数为蒸汽发生器体积(V)、一次侧出口温度(T)、一次侧进出口的最大流速(ν1)、二次侧最大流速(ν2)、最大热流密度(Q)。为了方便计算，将该优化函数的基本模型确定为minf(x)，该优化函数的函数表达式为：minf(x)＝min(W1V+W2T+W3ν1+W4ν2+W5Q)，其中，其中Wn代表各待优化参数所占的比重。进而实现了各个待优化参数以及f(x)的归一化处理。
若该蒸汽发生器的优化目标为高性能紧凑布置蒸汽发生器，根据优化目标确定各待优化参数的优化权重分别为：W1＝0.5，W2＝0.2，W3＝0.1，W4＝0.1，W5＝0.1。
步骤306，根据各待优化参数与各待优化参数的优化权重生成优化函数。
具体地，参数优化平台在确定了各待优化参数对应的优化权重后，根据各待优化参数与各待优化参数对应的优化权重生成优化函数。
例如，当参数优化平台确定进而得到各待优化参数的优化权重分别为：W1＝0.5，W2＝0.2，W3＝0.1，W4＝0.1，W5＝0.1，根据各待优化参数与各待优化参数对应的优化权重生成优化函数的最终表达式为：minf(x)＝min(0.5V+0.2T+0.1ν1+0.1ν2+0.1Q)。
本实施例中，参数优化平台根据初始设计方案确定目标优化对象的优化目标，基于优化目标确定各待优化参数的优化权重，根据各待优化参数与各待优化参数的优化权重生成优化函数，通过优化目标确定各待优化参数的优化权重，可以保证生成的优化函数充分考虑了各待优化参数在优化目标中所占重要比例，进而提高核反应堆参数优化的准确性。
在一些实施例中，如图4，调用优化参数模型对优化函数进行求解，得到各待优化参数的优化值，包括：
步骤402，根据初始设计方案确定各待优化参数的标准值。
在一些实施例中，根据所述初始设计方案确定各所述待优化参数的标准值，包括：根据所述初始设计方案确定各所述待优化参数的初始值；对各所述初始值进行归一化处理，得到与各初始值对应的各所述待优化参数的标准值。
具体地，核反应堆的初始设计方案中包括了目标优化对象各待优化参数的初始值，对该初始值进行归一化处理，即计算该初始值的无量纲化值，得到与该待优化参数初始值对应的标准值。其中，无量纲化(nondimensionalize或者dimensionless)是指通过一个合适的变量替代，将一个涉及物理量的方程的部分或全部的单位移除，以求简化实验或者计算的目的，是科学研究中一种重要的处理思想。通过对各待优化参数的初始值进行归一化处理，可以直观的获取不同待优化参数取值形成的数组下优化函数的取值。
例如，流量参数的初始值为250m3/h，对该初始值进行无量纲化，得到的标准值为1，这个1对应的就是250m3/h。
步骤404，将各标准值作为自适应矩估计算法的输入值进行迭代更新计算，得到各标准值的迭代更新值。
其中，在自适应矩估计算法中，将优化函数中各待优化参数的各标准作为一组输入参数，输入参数为一个多维向量。
具体地，首先，设置自适应矩估计算法中的初始化参数，初始化参数包括步进值δ，各个待优化参数的初始参数θi，初始参数即为步骤402中得到的各个待优化参数对应的标准值，数值稳定量ε、一阶动量衰减系数β1、二阶动量衰减系数β2，对于计算中涉及到的中间变量：一阶动量s、二阶动量r均初始化取0。可以理解的，数值稳定量、一阶动量衰减系数、二阶动量衰减系数均可以使用自适应矩估计算法的预设值，也可以由设计人员根据实际情况进行设定。
在其中一些实施例中，数值稳定量取10-8，一阶动量衰减系数取0.9，二阶动量衰减系数取0.999。
其次，优化函数的目标函数f(x)关于x的梯度是一个由偏导数组成的向量：
梯度中每个偏导元素代表着f(x)在xi的变化率。
对于任何函数f(x)假如是f(x)的局部极小点且f(x)在处可微，那么必有
当在梯度方向的相反方向时，方向导数f(x)被最小化。所以，可以通过下面的梯度下降算法来不断降低目标函数f(x)的值：
当在梯度方向的相反方向时，方向导数f(x)被最小化。所以，可以通过下面的梯度下降算法来不断降低目标函数f(x)的值：
确定当前位置的损失函数的梯度，对于xi,其梯度表达式如下：
用步长乘以损失函数的梯度，得到当前位置下降的距离，即：
自适应矩估计算法不仅计算指数衰减梯度平方的二阶矩的估计vt，其还计算指数衰减梯度的一阶矩的估计mt，类似于动量。
mt＝β1mt-1+(1β1)gt
其中mt为一阶矩的估计(均值)，初始化为0向量；vt为二阶矩的估计(方差)，初始化为0向量。当衰减率很小时(β1和β2接近于1)，mt和vt最终都趋于0。因而，自适应矩估计算法最终对一阶矩和二阶矩进行校正(β1和β2的上标t代表t次方)：

最终，自适应矩估计算法的更新规则为：
步骤406，若各迭代更新值满足更新结束条件，则根据各迭代更新值确定各待优化参数的优化值。
其中，更新结束条件为所有计算得到的迭代更新值的梯度下降的距离都小于数值稳定量，若各迭代更新值的梯度梯度下降距离都小于数值稳定量，则根据此时的各迭代更新值确定为各待优化参数的优化值。若各迭代更新值的梯度梯度下降距离存在大于数值稳定量的更新值，则重新返回至迭代步骤继续迭代更新，直至各迭代更新值均满足更新结束条件为止。
具体地，确定是否所有的计算结果θi的梯度下降的距离都小于ε，如果小于ε则算法终止，根据当前所有的θi(i＝0,1,...n)确定各待优化参数的优化值。如果θi的梯度下降的距离不小于ε，则返回至计算计算指数衰减梯度平方的二阶矩的估计vt与指数衰减梯度的一阶矩的估计mt的步骤。
在上述实施例中，根据各待优化参数的初始值得到各待优化参数的标准值，将该标准值作为自适应矩估计算法中初始化参数的一部分输入至参数优化模型中进行迭代计算，当各迭代更新值满足更新结束条件时，根据各迭代更新值得到各待优化参数的优化值，为后续得到各待优化参数的目标优化值提供了数据基础。
在一些实施例中，根据各迭代更新值确定各待优化参数的优化值，包括：根据初始设计方案确定各待优化参数的约束条件；将各迭代更新值与对应的待优化参数的约束条件进行比较，若各迭代更新值均满足对应的待优化参数的约束条件，则根据各迭代更新值与各待优化参数的标准值确定各待优化参数的优化值。
其中，各待优化参数的约束条件为各待优化参数取值的约束条件，可以是各待优化参数的取值范围，可以理解的，各待优化参数的约束条件是设计人员根据各待优化参数对应的目标优化对象在实际使用过程中的使用情况确定的，并预先与各待优化参数绑定后记录在初始设计方案中，约束条件可以用等式或不等式进行表示。
在优化方法的常用概念中，优化函数为f(x)，各待优化参数为优化函数中的所有变量，若变量存在约束条件，则约束条件包含了与变量取值相关的所有等式和不等式，可行域为约束条件在空间围成的区域，可行解为可行域中的每个点都是原问题的一个可行点，最优解为能够使优化函数达到最大或最小的可行解。
具体地，参数优化平台根据各待优化参数从初始设计方案确定各待优化参数的约束条件，将各迭代更新值与对应的待优化参数的约束条件进行比价，若各迭代更新值中存在不能满足对应的待优化参数的约束条件的更新值，则说明此处得到的迭代更新值无法使用，若强行使用容易使得核反应堆的安全性存在风险，需要根据梯度和步长逆优化，重新调整各待优化参数的迭代更新值。
若各迭代更新值均满足对应的待优化参数的约束条件，则根据各迭代更新值与各待优化参数的标准值确定各待优化参数的优化值。例如，流量优化参数的标准值为1对应250m3/h，迭代更新计算后得到迭代更新值为1.2，此时流量优化参数的优化值即为1.2×250m3/h＝300m3/h。
本实施例中，参数优化平台在得到了各待优化参数的迭代更新值后，通过将各待优化参数的迭代更新值与各待优化参数对应的约束条件进行比较，进而确定该迭代更新值是否能够直接作为各待优化参数的优化值，进一步保证了各待优化参数优化值的安全性和准确性。
由于核反应堆原型各个基本参数相互之间存在耦合关联，因此，当其中某个参数发生变化时，其他的参数由于耦合关联的原因也需要进行相应的改变。在一些实施例中，如图5所示，基于各待优化参数的优化值判断优化函数是否收敛，之前还包括：
步骤502，获取目标优化对象的基本参数，基本参数包括各待优化参数。
具体地，参数优化平台从初始设计方案中获取目标优化对象的基本参数，基本参数为目标优化对象的结构参数与热工参数，基本参数中包括了需要进行优化的各待优化参数。
步骤504，根据基本参数对目标优化对象进行建模，得到目标优化对象的分析模型。
具体地，参数优化平台根据获得的基本参数对目标优化对象进行建模，得到目标优化对象的分析模型。
在其中一些实施例中，参数优化平台代用RELAP、CATHARE等反应堆系统安全分析程序对目标优化对象的基本参数进行建模，得到目标优化对象的分析模型。
步骤506，将各待优化参数的优化值输入至分析模型中，得到各基本参数的优化值，对各基本参数的优化值进行记录。
具体地，参数优化平台将获得的各待优化参数的优化值输入至分析模型中，基于各基本参数之间的耦合关联，通过各待优化参数的优化值对各基本参数进行相应优化，得到各基本参数的优化值，并对各基本参数的优化值进行记录保存。
在其中一些实施例中，参数优化平台将各基本参数的优化值以矩阵的形式进行保存，若各待优化参数的优化值无法使优化函数进行收敛，则直接将保存的矩阵作为多维向量作为自适应矩估计算法中的输入参数，使计算更加方便快捷。
在其中一些实施例中，根据各所述待优化参数的目标优化值更新所述初始设计方案包括：将各待优化参数的目标优化值输入至分析模型中，得到目标优化对象的基本参数的目标优化值，根据目标优化对象的基本参数的目标优化值对初始设计方案进行更新，得到核反应堆的优化设计方案。
上述实施例中，参数优化平台根据目标优化对象的基本参数对目标优化对象进行建模，得到目标优化对象的分析模型，分析模型根据各待优化参数的优化值进行分析后得到各基本参数的优化值，参数优化平台对各基本参数的优化值进行记录。基于各待优化参数与基本参数中其他参数的耦合联系，通过各待优化参数的优化值得到基本参数的优化值，为后续对初始设计方案进行更新，得到更加准确的优化设计方案提供了数据基础。
在一些实施例中，提供了一种核反应多参数优化方法，如图6所示，该方法总体分为5个步骤，分别为：
步骤601，建立目标优化对象的多目标优化函数。
步骤602，对目标优化对象建模。
步骤603，调用优化参数模型基于适应性矩估计算法进行多目标参数优化分析。
步骤604，获取多目标参数优化结果。
步骤605，更新初始设计方案得到优化设计方案。
具体地，如图7所示，以该方法中的目标优化对象为核反应堆的倒U型自然循环蒸汽发生器为例进行说明，该方法的具体实施步骤如下：
首先，参数优化平台确定蒸汽发生器的各待优化参数以及目标优化对象的初始设计方案。其中，各待优化参数包括蒸汽发生器体积(V)、一次侧出口温度(T)、一次侧进出口的最大流速(ν1)、二次侧最大流速(ν2)、最大热流密度(Q)，初始设计方案包括各目标优化对象的基本参数、各待优化参数的初始值、各待优化参数的约束边界条件，各目标优化对象的优化目标等。
根据初始设计方案与各待优化参数确定优化函数minf(x)＝min(0.5V+0.2T+0.1ν1+0.1ν2+0.1Q)、各待优化参数的标准值以及各待优化参数的约束边界条件。
调用优化参数模型，根据优化函数、各待优化参数的标准值以及各待优化参数的约束边界条件对各待优化参数进行参数优化，寻找各待优化参数的优化值。确定各待优化参数 的优化值是否满足约束边界条件中的边界限值，若不满足，则根据梯度和步长逆优化。
若满足，则根据目标优化对象的各基本参数生成分析模型，基本参数为目标优化对象的热工参数和结构参数，基本参数主要包括蒸汽发生器高度、传热管高度、传热管外径、传热管外径、传热管数目等结构参数，蒸汽发生器一次侧流速、蒸汽发生器一次侧进出口温度、蒸汽发生器二次侧流速、蒸汽发生器二次侧进出口温度等热工参数。
将各待优化参数的优化值输入至分析模型中，分析并记录各基本参数的优化值，并根据各待优化参数的优化值判断目标函数是否收敛，若不收敛，则根据梯度和步长继续进行正优化。若收敛，则记录各待优化参数的最优解为目标优化值，并根据目标优化值分析得到各基本参数的目标优化值。根据各基本参数的目标优化值更新初始设计方案，得到优化设计方案。
应该理解的是，虽然如上所述的各实施例所涉及的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，如上所述的各实施例所涉及的流程图中的至少一部分步骤可以包括多个步骤或者多个阶段，这些步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤中的步骤或者阶段的至少一部分轮流或者交替地执行。
基于同样的发明构思，本申请实施例还提供了一种用于实现上述所涉及的核反应堆多参数优化方法的核反应堆多参数优化装置。该装置所提供的解决问题的实现方案与上述方法中所记载的实现方案相似，故下面所提供的一个或多个核反应堆多参数优化装置实施例中的具体限定可以参见上文中对于核反应堆多参数优化方法的限定，在此不再赘述。
在一些实施例中，如图8所示，提供了一种核反应堆多参数优化装置，包括：参数获取模块801、函数生成模块802、函数求解模块803、参数优化模块804和方案更新模块805，其中：
参数获取模块801，用于获取核反应堆中目标优化对象的各待优化参数，以及核反应堆的初始设计方案。
函数生成模块802，用于根据初始设计方案与各待优化参数生成目标优化对象的优化函数。
函数求解模块803，用于调用优化参数模型对优化函数求解最优解，得到各待优化参数的优化值，优化参数模型根据自适应矩估计算法预先构建。
参数优化模块804，用于基于各待优化参数的优化值判断优化函数是否收敛，若收敛，则确定各待优化参数的优化值为各待优化参数的目标优化值。
方案更新模块805，用于根据待优化参数的目标优化值更新初始设计方案。
上述核反应堆多参数优化装置，获取核反应堆中目标优化对象的各待优化参数以及核反应堆的初始设计方案，根据初始设计方案和各待优化参数生成目标优化对象的优化函数，调用根据自适应矩估计算法预先构建的优化函数模型对优化函数进行求解，大大提升了得到优化值的速度，由于优化函数是根据初始设计方案和各待优化参数生成的，因此对优化函数进行求解得到的值即可认为是优化过后的参数值，基于各待优化参数的优化值判断优化函数是否收敛，当得到的优化值可以使优化函数收敛时，说明此时得到的优化值为优化函数的最优解，将该待优化函数的优化值确定为待优化参数的目标优化值，并根据待优化参数的目标优化值更新初始设计方案，有效提高了核反应堆参数与设计方案优化的效率与准确性。
在一些实施例中，函数生成模块还用于：根据初始设计方案确定目标优化对象的优化目标；基于优化目标确定各待优化参数的优化权重；根据各待优化参数与各待优化参数的优化权重生成优化函数。
在一些实施例中，函数求解模块还用于：根据初始设计方案确定各待优化参数的标准 值；将各标准值作为自适应矩估计算法的输入值进行迭代更新计算，得到各标准值的迭代更新值；若各迭代更新值满足更新结束条件，则根据各迭代更新值确定各待优化参数的优化值。
在一些实施例中，函数求解模块还用于：根据初始设计方案确定各待优化参数的约束条件；将各迭代更新值与对应的待优化参数的约束条件进行比较，若各迭代更新值均满足对应的待优化参数的约束条件，则根据各迭代更新值与各待优化参数的标准值确定各待优化参数的优化值。
在一些实施例中，函数求解模块还用于：根据初始设计方案确定各待优化参数的初始值；对各初始值进行归一化处理，得到与各初始值对应的各待优化参数的标准值。
在一些实施例中，核反应堆多参数优化装置还包括：分析模块，用于获取目标优化对象的基本参数，基本参数包括各待优化参数；根据基本参数对目标优化对象进行建模，得到目标优化对象的分析模型；将各待优化参数的优化值输入至分析模型中，得到各基本参数的优化值，对各基本参数的优化值进行记录。
上述核反应堆多参数优化装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在一些实施例中，提供了一种计算机设备，该计算机设备可以是集成了参数优化平台的终端或服务器，其内部结构图可以如图9所示。该计算机设备包括通过系统总线连接的处理器、存储器和网络接口。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质和内存储器。该非易失性存储介质存储有操作系统、计算机程序和数据库。该内存储器为非易失性存储介质中的操作系统和计算机程序的运行提供环境。该计算机设备的数据库用于存储初始设计方案、各待优化参数、优化参数模型等数据。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机程序被处理器执行时以实现一种核反应堆多参数优化方法。
本领域技术人员可以理解，图9中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
在一些实施例中，提供了一种计算机设备，包括存储器和处理器，存储器中存储有计算机程序，该处理器执行计算机程序时实现以下步骤：
获取核反应堆中目标优化对象的各待优化参数，以及核反应堆的初始设计方案；
根据初始设计方案与各待优化参数生成目标优化对象的优化函数；
调用优化参数模型对优化函数进行求解，得到各待优化参数的优化值，优化参数模型根据自适应矩估计算法预先构建；
基于各待优化参数的优化值判断优化函数是否收敛，若收敛，则确定各待优化参数的优化值为各待优化参数的目标优化值；及
根据各待优化参数的目标优化值更新初始设计方案。
在一些实施例中，处理器执行计算机程序时还实现以下步骤：
根据初始设计方案确定目标优化对象的优化目标；
基于优化目标确定各待优化参数的优化权重；及
根据各待优化参数与各待优化参数的优化权重生成优化函数。
在一些实施例中，处理器执行计算机程序时还实现以下步骤：
根据初始设计方案确定各待优化参数的标准值；
将各标准值作为自适应矩估计算法的输入值进行迭代更新计算，得到各标准值的迭代更新值；及
若各迭代更新值满足更新结束条件，则根据各迭代更新值确定各待优化参数的优化值。
在一些实施例中，处理器执行计算机程序时还实现以下步骤：
根据初始设计方案确定各待优化参数的约束条件；及
将各迭代更新值与对应的待优化参数的约束条件进行比较，若各迭代更新值均满足对应的待优化参数的约束条件，则根据各迭代更新值与各待优化参数的标准值确定各待优化参数的优化值。
在一些实施例中，处理器执行计算机程序时还实现以下步骤：
根据初始设计方案确定各待优化参数的初始值；及
对各初始值进行归一化处理，得到与各初始值对应的各待优化参数的标准值。
在一些实施例中，处理器执行计算机程序时还实现以下步骤：
获取目标优化对象的基本参数，基本参数包括各待优化参数；
根据基本参数对目标优化对象进行建模，得到目标优化对象的分析模型；及
将各待优化参数的优化值输入至分析模型中，得到各基本参数的优化值，对各基本参数的优化值进行记录。
在一些实施例中，提供了一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行时实现以下步骤：
获取核反应堆中目标优化对象的各待优化参数，以及核反应堆的初始设计方案；
根据初始设计方案与各待优化参数生成目标优化对象的优化函数；
调用优化参数模型对优化函数进行求解，得到各待优化参数的优化值，优化参数模型根据自适应矩估计算法预先构建；
基于各待优化参数的优化值判断优化函数是否收敛，若收敛，则确定各待优化参数的优化值为各待优化参数的目标优化值；及
根据各待优化参数的目标优化值更新初始设计方案。
在一些实施例中，计算机程序被处理器执行时还实现以下步骤：
根据初始设计方案确定目标优化对象的优化目标；
基于优化目标确定各待优化参数的优化权重；及
根据各待优化参数与各待优化参数的优化权重生成优化函数。
在一些实施例中，计算机程序被处理器执行时还实现以下步骤：
根据初始设计方案确定各待优化参数的标准值；
将各标准值作为自适应矩估计算法的输入值进行迭代更新计算，得到各标准值的迭代更新值；及
若各迭代更新值满足更新结束条件，则根据各迭代更新值确定各待优化参数的优化值。
在一些实施例中，计算机程序被处理器执行时还实现以下步骤：
根据初始设计方案确定各待优化参数的约束条件；及
将各迭代更新值与对应的待优化参数的约束条件进行比较，若各迭代更新值均满足对应的待优化参数的约束条件，则根据各迭代更新值与各待优化参数的标准值确定各待优化参数的优化值。
在一些实施例中，计算机程序被处理器执行时还实现以下步骤：
根据初始设计方案确定各待优化参数的初始值；及
对各初始值进行归一化处理，得到与各初始值对应的各待优化参数的标准值。
在一些实施例中，计算机程序被处理器执行时还实现以下步骤：
获取目标优化对象的基本参数，基本参数包括各待优化参数；
根据基本参数对目标优化对象进行建模，得到目标优化对象的分析模型；及
将各待优化参数的优化值输入至分析模型中，得到各基本参数的优化值，对各基本参数的优化值进行记录。
在一些实施例中，提供了一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现以下步骤：
获取核反应堆中目标优化对象的各待优化参数，以及核反应堆的初始设计方案；
根据初始设计方案与各待优化参数生成目标优化对象的优化函数；
调用优化参数模型对优化函数进行求解，得到各待优化参数的优化值，优化参数模型根据自适应矩估计算法预先构建；
基于各待优化参数的优化值判断优化函数是否收敛，若收敛，则确定各待优化参数的优化值为各待优化参数的目标优化值；及
根据各待优化参数的目标优化值更新初始设计方案。
在一些实施例中，计算机程序被处理器执行时还实现以下步骤：
根据初始设计方案确定目标优化对象的优化目标；
基于优化目标确定各待优化参数的优化权重；及
根据各待优化参数与各待优化参数的优化权重生成优化函数。
在一些实施例中，计算机程序被处理器执行时还实现以下步骤：
根据初始设计方案确定各待优化参数的标准值；
将各标准值作为自适应矩估计算法的输入值进行迭代更新计算，得到各标准值的迭代更新值；及
若各迭代更新值满足更新结束条件，则根据各迭代更新值确定各待优化参数的优化值。
在一些实施例中，计算机程序被处理器执行时还实现以下步骤：
根据初始设计方案确定各待优化参数的约束条件；及
将各迭代更新值与对应的待优化参数的约束条件进行比较，若各迭代更新值均满足对应的待优化参数的约束条件，则根据各迭代更新值与各待优化参数的标准值确定各待优化参数的优化值。
在一些实施例中，计算机程序被处理器执行时还实现以下步骤：
根据初始设计方案确定各待优化参数的初始值；及
对各初始值进行归一化处理，得到与各初始值对应的各待优化参数的标准值。
在一些实施例中，计算机程序被处理器执行时还实现以下步骤：
获取目标优化对象的基本参数，基本参数包括各待优化参数；
根据基本参数对目标优化对象进行建模，得到目标优化对象的分析模型；及
将各待优化参数的优化值输入至分析模型中，得到各基本参数的优化值，对各基本参数的优化值进行记录。
需要说明的是，本申请所涉及的用户信息(包括但不限于用户设备信息、用户个人信息等)和数据(包括但不限于用于分析的数据、存储的数据、展示的数据等)，均为经用户授权或者经过各方充分授权的信息和数据。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一非易失性计算机可读取存储介质中，该计算机程序在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、数据库或其它介质的任何引用，均可包括非易失性和易失性存储器中的至少一种。非易失性存储器可包括只读存储器(Read-Only Memory，ROM)、磁带、软盘、闪存、光存储器、高密度嵌入式非易失性存储器、阻变存储器(ReRAM)、磁变存储器(Magnetoresistive Random Access Memory，MRAM)、铁电存储器(Ferroelectric Random Access Memory，FRAM)、相变存储器(Phase Change Memory，PCM)、石墨烯存储器等。易失性存储器可包括随机存取存储器(Random Access Memory，RAM)或外部高速缓冲存储器等。作为说明而非局限，RAM可以是多种形式，比如静态随机存取存储器(Static Random Access Memory，SRAM)或动态随机存取存储器(Dynamic Random Access Memory，DRAM)等。本申请所提供的各实施例中所涉及的数据库可包括关系型数据库和非关系型数据库中至少一种。非关系型数据库可包括基于区块链的分布式数据库等，不限于此。本申请所提供的各实施例中所涉及的处理器可为通用处理器、中央处理器、图形处理器、数字信号处理器、可编程逻辑器、基于量子计算的数据处理逻辑器 等，不限于此。
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对本申请专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请的保护范围应以所附权利要求为准。

Claims (15)

  1. 一种核反应堆多参数优化方法，其特征在于，所述方法包括：
    获取核反应堆中目标优化对象的各待优化参数，以及所述核反应堆的初始设计方案；
    根据所述初始设计方案与各所述待优化参数生成所述目标优化对象的优化函数；
    调用优化参数模型对所述优化函数进行求解，得到各所述待优化参数的优化值，所述优化参数模型根据自适应矩估计算法预先构建；
    基于各所述待优化参数的优化值判断所述优化函数是否收敛，若收敛，则确定各所述待优化参数的优化值为各所述待优化参数的目标优化值；及
    根据各所述待优化参数的目标优化值更新所述初始设计方案。
  2. 根据权利要求1所述的方法，其特征在于，所述根据所述初始设计方案与各所述待优化参数生成优化函数，包括：
    根据所述初始设计方案确定所述目标优化对象的优化目标；
    基于所述优化目标确定各所述待优化参数的优化权重；及
    根据各所述待优化参数与各所述待优化参数的优化权重生成优化函数。
  3. 根据权利要求1所述的方法，其特征在于，所述调用优化参数模型对所述优化函数进行求解，得到各所述待优化参数的优化值，包括：
    根据所述初始设计方案确定各所述待优化参数的标准值；
    将各所述标准值作为自适应矩估计算法的输入值进行迭代更新计算，得到各所述标准值的迭代更新值；及
    若各所述迭代更新值满足更新结束条件，则根据各所述迭代更新值确定各所述待优化参数的优化值。
  4. 根据权利要求3所述的方法，其特征在于，所述根据各所述迭代更新值确定各所述待优化参数的优化值，包括：
    根据所述初始设计方案确定各所述待优化参数的约束条件；及
    将各所述迭代更新值与对应的待优化参数的约束条件进行比较，若各所述迭代更新值均满足对应的待优化参数的约束条件，则根据各所述迭代更新值与各所述待优化参数的标准值确定各所述待优化参数的优化值。
  5. 根据权利要求3所述的方法，其特征在于，所述根据所述初始设计方案确定各所述待优化参数的标准值，包括：
    根据所述初始设计方案确定各所述待优化参数的初始值；及
    对各所述初始值进行归一化处理，得到与各初始值对应的各所述待优化参数的标准值。
  6. 根据权利要求1至5任意一项所述的方法，其特征在于，所述基于各所述待优化参数的优化值判断所述优化函数是否收敛，之前还包括：
    获取所述目标优化对象的基本参数，所述基本参数包括各所述待优化参数；
    根据所述基本参数对所述目标优化对象进行建模，得到所述目标优化对象的分析模型；及
    将各所述待优化参数的优化值输入至所述分析模型中，得到各所述基本参数的优化值，对各所述基本参数的优化值进行记录。
  7. 一种核反应堆多参数优化装置，其特征在于，所述装置包括：
    参数获取模块，用于获取核反应堆中目标优化对象的各待优化参数，以及所述核反应堆的初始设计方案；
    函数生成模块，用于根据所述初始设计方案与各所述待优化参数生成所述目标优化对象的优化函数；
    函数求解模块，用于调用优化参数模型对所述优化函数求解最优解，得到各所述待优化参数的优化值，所述优化参数模型根据自适应矩估计算法预先构建；
    参数优化模块，用于基于各所述待优化参数的优化值判断所述优化函数是否收敛，若 收敛，则确定各所述待优化参数的优化值为各所述待优化参数的目标优化值；及
    方案更新模块，用于根据所述待优化参数的目标优化值更新所述初始设计方案。
  8. 根据权利要求7所述的装置，其特征在于，所述函数生成模块还用于：根据所述初始设计方案确定所述目标优化对象的优化目标；基于所述优化目标确定各所述待优化参数的优化权重；及根据各所述待优化参数与各所述待优化参数的优化权重生成优化函数。
  9. 根据权利要求7所述的装置，其特征在于，所述函数求解模块还用于：根据所述初始设计方案确定各所述待优化参数的标准值；将各所述标准值作为自适应矩估计算法的输入值进行迭代更新计算，得到各所述标准值的迭代更新值；及若各所述迭代更新值满足更新结束条件，则根据各所述迭代更新值确定各所述待优化参数的优化值。
  10. 根据权利要求9所述的装置，其特征在于，所述函数求解模块还用于：根据所述初始设计方案确定各所述待优化参数的约束条件；及将各所述迭代更新值与对应的待优化参数的约束条件进行比较，若各所述迭代更新值均满足对应的待优化参数的约束条件，则根据各所述迭代更新值与各所述待优化参数的标准值确定各所述待优化参数的优化值。
  11. 根据权利要求9所述的装置，其特征在于，所述函数求解模块还用于：根据所述初始设计方案确定各所述待优化参数的初始值；及对各所述初始值进行归一化处理，得到与各初始值对应的各所述待优化参数的标准值。
  12. 根据权利要求7至11任意一项所述的装置，其特征在于，所述核反应堆参数优化装置还包括：分析模块，用于获取所述目标优化对象的基本参数，所述基本参数包括各所述待优化参数；根据所述基本参数对所述目标优化对象进行建模，得到所述目标优化对象的分析模型；及将各所述待优化参数的优化值输入至所述分析模型中，得到各所述基本参数的优化值，对各所述基本参数的优化值进行记录。
  13. 一种计算机设备，包括存储器和处理器，所述存储器存储有计算机程序，其特征在于，所述处理器执行所述计算机程序时实现权利要求1至6中任一项所述核反应堆多参数优化方法的步骤。
  14. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现权利要求1至6中任一项所述核反应堆多参数优化方法的步骤。
  15. 一种计算机程序产品，包括计算机程序，其特征在于，该计算机程序被处理器执行时实现权利要求1至6中任一项所述核反应堆多参数优化方法的步骤。
PCT/CN2023/074349 2022-09-21 2023-02-03 核反应堆多参数优化方法、装置、计算机设备和存储介质 WO2024060480A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211149834.XA CN116029409A (zh) 2022-09-21 2022-09-21 核反应堆多参数优化方法、装置、计算机设备和存储介质
CN202211149834.X 2022-09-21

Publications (1)

Publication Number Publication Date
WO2024060480A1 true WO2024060480A1 (zh) 2024-03-28

Family

ID=86078357

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/074349 WO2024060480A1 (zh) 2022-09-21 2023-02-03 核反应堆多参数优化方法、装置、计算机设备和存储介质

Country Status (2)

Country Link
CN (1) CN116029409A (zh)
WO (1) WO2024060480A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108875207A (zh) * 2018-06-15 2018-11-23 岭东核电有限公司 一种核反应堆优化设计方法及系统
CN110795857A (zh) * 2019-11-06 2020-02-14 哈尔滨工程大学 一种浮动核电站二回路主要设备体积优化方法
US20220058312A1 (en) * 2018-12-07 2022-02-24 Nippon Telegraph And Telephone Corporation Estimation apparatus, optimization apparatus, estimation method, optimization method, and program
CN114444383A (zh) * 2021-12-31 2022-05-06 岭东核电有限公司 核反应堆设计方案优化方法、装置、计算机设备和介质
CN114547983A (zh) * 2022-02-28 2022-05-27 哈尔滨工程大学 一种基于改进的多种群遗传算法的反应堆运行优化方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108875207A (zh) * 2018-06-15 2018-11-23 岭东核电有限公司 一种核反应堆优化设计方法及系统
US20220058312A1 (en) * 2018-12-07 2022-02-24 Nippon Telegraph And Telephone Corporation Estimation apparatus, optimization apparatus, estimation method, optimization method, and program
CN110795857A (zh) * 2019-11-06 2020-02-14 哈尔滨工程大学 一种浮动核电站二回路主要设备体积优化方法
CN114444383A (zh) * 2021-12-31 2022-05-06 岭东核电有限公司 核反应堆设计方案优化方法、装置、计算机设备和介质
CN114547983A (zh) * 2022-02-28 2022-05-27 哈尔滨工程大学 一种基于改进的多种群遗传算法的反应堆运行优化方法

Also Published As

Publication number Publication date
CN116029409A (zh) 2023-04-28

Similar Documents

Publication Publication Date Title
Chen et al. ReGAN: A pipelined ReRAM-based accelerator for generative adversarial networks
US11928600B2 (en) Sequence-to-sequence prediction using a neural network model
WO2022105108A1 (zh) 一种网络数据分类方法、装置、设备及可读存储介质
CN111597698A (zh) 一种基于深度学习的多精度优化算法实现气动优化设计的方法
WO2023124414A1 (zh) 核反应堆设计方案优化方法、装置、计算机设备和介质
CN111291193B (zh) 一种知识图谱在零次学习上的运用方法
US20170011143A1 (en) Search and poll method for solving multi-fidelity optimization problems
CN107908900A (zh) 一种基于凸模型不确定性的连续体结构非概率可靠性拓扑优化方法
CN108462180B (zh) 一种基于vine copula函数确定概率最优潮流的方法
Chu et al. Reliability based optimization with metaheuristic algorithms and Latin hypercube sampling based surrogate models
CN113486963A (zh) 一种密度自适应的点云端到端采样方法
Liu et al. GNNSampler: Bridging the gap between sampling algorithms of GNN and hardware
Amini et al. Generalizable floorplanner through corner block list representation and hypergraph embedding
Geng et al. Differentiable programming of isometric tensor networks
Chahine et al. The influence of metamodeling techniques on the multidisciplinary design optimization of a radial compressor impeller
Heiß et al. Multilevel CNNs for Parametric PDEs
WO2024060480A1 (zh) 核反应堆多参数优化方法、装置、计算机设备和存储介质
Bu et al. Feedback gradient descent: Efficient and stable optimization with orthogonality for DNNs
Kapsoulis et al. The use of Kernel PCA in evolutionary optimization for computationally demanding engineering applications
CN116959600A (zh) 分子状态预测方法、装置和存储介质
CN113127648B (zh) 数据验证方法和装置、电子设备、计算机可读介质
Xia et al. Efficient synthesis of compact deep neural networks
CN112949154B (zh) 并行异步粒子群优化方法、系统及电子设备
US20230042464A1 (en) Methods and systems for of generating an instantaneous quote of any part without toolpathing
US20220390918A1 (en) Methods and systems for selection of manufacturing orientation using machine learning

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23866785

Country of ref document: EP

Kind code of ref document: A1