WO2021254190A1 - 一种核电站高精度高保真实时仿真和行为预测方法及装置 - Google Patents

一种核电站高精度高保真实时仿真和行为预测方法及装置 Download PDF

Info

Publication number
WO2021254190A1
WO2021254190A1 PCT/CN2021/098564 CN2021098564W WO2021254190A1 WO 2021254190 A1 WO2021254190 A1 WO 2021254190A1 CN 2021098564 W CN2021098564 W CN 2021098564W WO 2021254190 A1 WO2021254190 A1 WO 2021254190A1
Authority
WO
WIPO (PCT)
Prior art keywords
correction
nuclear power
power plant
parameters
prediction
Prior art date
Application number
PCT/CN2021/098564
Other languages
English (en)
French (fr)
Inventor
胡珀
Original Assignee
上海交通大学
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 上海交通大学 filed Critical 上海交通大学
Priority to US17/638,189 priority Critical patent/US20220405446A1/en
Publication of WO2021254190A1 publication Critical patent/WO2021254190A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/20Design optimisation, verification or simulation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00Computer-aided design [CAD]
    • G06F30/20Design optimisation, verification or simulation
    • G06F30/27Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • GPHYSICS
    • G21NUCLEAR PHYSICS; NUCLEAR ENGINEERING
    • G21DNUCLEAR POWER PLANT
    • G21D3/00Control of nuclear power plant
    • G21D3/001Computer implemented control
    • G21D3/002Core design; core simulations; core optimisation
    • GPHYSICS
    • G21NUCLEAR PHYSICS; NUCLEAR ENGINEERING
    • G21DNUCLEAR POWER PLANT
    • G21D3/00Control of nuclear power plant
    • G21D3/001Computer implemented control
    • GPHYSICS
    • G21NUCLEAR PHYSICS; NUCLEAR ENGINEERING
    • G21DNUCLEAR POWER PLANT
    • G21D3/00Control of nuclear power plant
    • G21D3/04Safety arrangements
    • G21D3/06Safety arrangements responsive to faults within the plant
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/02Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
    • GPHYSICS
    • G21NUCLEAR PHYSICS; NUCLEAR ENGINEERING
    • G21DNUCLEAR POWER PLANT
    • G21D3/00Control of nuclear power plant
    • G21D3/08Regulation of any parameters in the plant
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02EREDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E30/00Energy generation of nuclear origin

Definitions

  • the invention relates to a nuclear power plant simulation and behavior prediction method and system, in particular to a nuclear power plant simulation and behavior prediction method and device with high precision and high fidelity.
  • the existing nuclear power plant simulator is mainly based on professional software such as thermal-hydraulic system programs to establish a calculation model for the main equipment and pipelines of the primary and secondary circuits of the nuclear power plant, as well as the control system.
  • the design parameters of the reactor or the actual reactor technical parameters are used as input variables. , To calculate the system response of nuclear power plants under different working conditions, to provide reference and guidance for design optimization and actual control.
  • simulation calculation software simulation machine
  • simulation calculation software generally adopts mature and classic professional software recognized in the industry in the early stage of nuclear power plant service, and then compiles calculation cards for the design and operating parameters of the power plant, and then after initial debugging and verification, it can be officially delivered to the user.
  • the relevant parameters of the calculation card can be adjusted according to the specific conditions of the operation of the power station to obtain the calculation results of different operating states.
  • the purpose of the present invention is to provide a high-precision and high-fidelity simulation and behavior prediction method and device for nuclear power plants in order to overcome the above-mentioned defects in the prior art.
  • a high-precision and high-fidelity simulation and behavior prediction method for nuclear power plants includes the following steps:
  • step (3) includes two types of correction modes:
  • the first type of correction mode the prediction model used to predict all prediction parameters in the nuclear power plant simulator remains unchanged, and the input parameters of the prediction model are modified;
  • the second type of revision mode revise part of the prediction model in the nuclear power plant simulator, the remaining prediction model itself is not revised, but the input parameters of the remaining prediction model are revised.
  • the specific correction steps in step (3) include:
  • step (32) When the next correction cycle is reached, the k groups of correction schemes with the top k positions of the prediction accuracy in the previous correction cycle are selected respectively, and the correction in step (31) is repeated for the k groups of correction schemes respectively;
  • step (33) Repeat step (32) until the predicted parameters infinitely approach the operating parameters and reach the specified accuracy, select the optimal correction plan, and complete the correction of the nuclear power plant simulator.
  • the specific correction mode of the first type of correction mode is:
  • the first p predicted parameters are physical quantities that can be directly obtained by physical nuclear power plants
  • the remaining np predicted parameters are physical quantities that cannot be directly obtained by physical nuclear power plants
  • EXSR0 For the set of all input parameters that do not correspond to any Sj in the EX, the correction of the input parameters is completed.
  • the specific method for concurrently multiple correction schemes in the first type of correction mode is: the input parameter correction value total set EXSRZ1 is used as a set of correction schemes, and N is randomly generated based on the input parameter correction value total set EXSRZ1 and the input parameter set EX.
  • the group input parameter correction value expansion set EXSRZ1' forms N groups of correction schemes;
  • the specific correction mode of the second type of correction mode is:
  • the first p predicted parameters are physical quantities that can be directly obtained by physical nuclear power plants
  • the remaining np predicted parameters are physical quantities that cannot be directly obtained by physical nuclear power plants
  • the input parameter EXSj′ corresponding to Sj′ and the correction of the prediction model are specifically as follows: for Sj′, adopt a pattern recognition method based on artificial intelligence, use Sj′ to infinitely approach RSj′ without a target, and directly modify EXSj′ to obtain a set of correction values EXSRbj′, and at the same time replace the prediction model obtained by Sj′ with an artificial intelligence recognition model, which directly obtains the prediction result according to EXSRbj′;
  • the correction of the input parameter EXSj corresponding to Sj" is specifically: for Sj", the correction value set EXSRaj" of EXSj" is determined according to the error between Sj" and RSj";
  • EXSRZ2 (EXSR0',EXSRb1',EXSRb2',...,EXSRbp',EXSRa1",EXSRa2",...,EXSRaq"), where EXSR0'is all Sj in EX that is not related to any Sj
  • the specific method for concurrently multiple correction schemes in the second type of correction mode is: the input parameter correction value total set EXSRZ2 is used as a set of correction schemes, and N is randomly generated based on the input parameter correction value total set EXSRZ2 and the input parameter set EX.
  • the group input parameter correction value expansion set EXSRZ2' forms N groups of correction schemes;
  • a high-precision and high-fidelity simulation and behavior prediction device for a nuclear power plant includes a memory and a processor.
  • the memory is used to store a computer program. Methods.
  • the present invention has the following advantages:
  • the present invention innovatively makes the nuclear power plant simulator run in parallel with the physical nuclear power plant, and connects the operating parameters of the physical nuclear power plant to the nuclear power plant simulator in real time, and performs real-time comparison with the predicted parameters of the nuclear power plant simulator.
  • the support of large-scale computer technology Using large-scale concurrent/parallel parameter search and correction and artificial intelligence-based pattern recognition and correction algorithms, real-time adjustment of the predictive model of the power plant simulator and the input parameters of the predictive model, so that the simulation system can predict in real time during long-term operation and comparison and correction.
  • the parameters are gradually approaching the results of operating parameters of physical nuclear power plants.
  • This new simulation calculation method greatly exceeds the operating effects of existing simulators in terms of parameter authenticity and predicted reliability.
  • the method of the present invention can be used to accurately predict the behavior of the nuclear power plant system and diagnose the cause of failure under normal operation, maintenance, and accident conditions, and provide a more reliable guarantee for the safe and economical operation of the nuclear power plant.
  • Fig. 1 is a schematic diagram of the operation of the simulation and behavior prediction method of a nuclear power plant with high accuracy and high fidelity according to the present invention.
  • a high-precision and high-fidelity simulation and behavior prediction method for nuclear power plants includes the following steps:
  • the predicted parameters output by the nuclear power plant simulator include, but are not limited to, the thermal hydraulics, nuclear physical parameters and design parameters such as circulation, materials, operation control and safety of the nuclear power plant.
  • Thermal hydraulic parameters such as the primary and secondary circuit pressure, flow, inlet and outlet temperature
  • Physical parameters such as fuel enrichment, geometric dimensions of fuel rods, components and core components, fuel cycle period and component layout design, core structure materials, control rod materials and geometric structures, design parameters for start-up reactors, normal operation Temperature and pressure, as well as the pressure and temperature of the safety equipment and materials, the relevant threshold conditions of the safety equipment, and so on.
  • some of the parameters can be directly measured by the physical nuclear power plant (that is, the operating parameters of the physical nuclear power plant described above), and some cannot be measured.
  • the purpose of the present invention is to make the predicted parameters output by the nuclear power plant simulator and the actual state of the physical nuclear power plant ( Including the above-mentioned measurable physical nuclear power plant operating parameters and some non-measurable operating parameters) can be kept parallel and consistent.
  • Step (3) includes two types of correction modes:
  • the first type of correction mode the prediction model used to predict all prediction parameters in the nuclear power plant simulator remains unchanged, and the input parameters of the prediction model are modified;
  • the second type of revision mode revise part of the prediction model in the nuclear power plant simulator, the remaining prediction model itself is not revised, but the input parameters of the remaining prediction model are revised.
  • Step (3) The specific correction steps include:
  • step (32) When the next correction cycle is reached, the k groups of correction schemes with the top k positions of the prediction accuracy in the previous correction cycle are selected respectively, and the correction in step (31) is repeated for the k groups of correction schemes respectively;
  • step (33) Repeat step (32) until the predicted parameters infinitely approach the operating parameters and reach the specified accuracy, select the optimal correction plan, and complete the correction of the nuclear power plant simulator.
  • the specific correction methods of the first type of correction mode are:
  • the first p predicted parameters are physical quantities that can be directly obtained by physical nuclear power plants
  • the remaining np predicted parameters are physical quantities that cannot be directly obtained by physical nuclear power plants
  • EX (ex1, ex2,..., ext)
  • ext the t-th input parameter
  • t 1, 2,..., t
  • t represents the total number of prediction parameters
  • the operating parameter set R (r1, r2,..., rn) of the physical nuclear power plant
  • the physical quantities represented by each element in the set R correspond to the set X one-to-one
  • the first p operating parameters are the operation of the physical nuclear power plant directly obtained Parameters
  • the rest are given values
  • the corresponding predicted parameters output by the nuclear power plant simulator at the previous moment can be selected as given values
  • the given value can be 0 at the initial moment
  • the classification of the set X can be based on the traditional "phenomena sorting table" method of nuclear engineering, starting from the system-equipment-phenomenon multi-level classification, and then under the physical phenomenon, thermal engineering hydraulics, nuclear physics, materials, Specific categories such as control, operation, fuel cycle, safety, etc. are collected.
  • the specific method of concurrent multiple correction schemes in the first type of correction mode is: the input parameter correction value total set EXSRZ1 is used as a set of correction schemes, and N groups of input parameters are randomly generated based on the input parameter correction value total set EXSRZ1 and the input parameter set EX.
  • the first p predicted parameters are physical quantities that can be directly obtained by physical nuclear power plants
  • the remaining np predicted parameters are physical quantities that cannot be directly obtained by physical nuclear power plants
  • EX (ex1, ex2,..., ext)
  • ext the t-th input parameter
  • t 1, 2,..., t
  • t represents the total number of prediction parameters
  • the operating parameter set R (r1, r2,..., rn) of the physical nuclear power plant
  • the physical quantities represented by each element in the set R correspond to the set X one-to-one
  • the first p operating parameters are the operation of the physical nuclear power plant directly obtained Parameters, the rest are given values
  • the set X is divided into m subsets S1, S2,...Sm
  • the set R is divided into m subsets RS1, RS2,..., RSm correspondingly
  • the subset Sj is recorded as Sj′
  • the rest are recorded as Sj′′
  • Sj′ corresponds to Enter part of the input parameters in the input parameter set, denote this part of the input parameters as EXSj′, the input parameter corresponding to Sj′′ as EXSj′′, the operating parameter corresponding to Sj′ as RSj′, and the operating parameter corresponding to Sj′′ as RSj "Furthermore
  • the input parameter EXSj' corresponding to Sj' and the prediction model are corrected by artificial intelligence-based pattern recognition methods, and the input parameter EX
  • the input parameter EXSj′ corresponding to Sj′ and the correction of the prediction model are specifically as follows: For Sj′, the artificial intelligence-based pattern recognition method is adopted to infinitely approach RSj′ without target with Sj′, and EXSj′ is directly modified to obtain the set of correction values EXSRbj′.
  • the prediction model obtained by Sj' is replaced with an artificial intelligence recognition model, which directly obtains the prediction result according to EXSRbj';
  • EXSR0' is the set of all input parameters in EX that do not correspond to any Sj
  • p is the total number of input parameter subsets corrected by artificial intelligence-based pattern recognition methods
  • the specific method of concurrent multiple correction schemes in the second type of correction mode is: the input parameter correction value total set EXSRZ2 is used as a set of correction schemes, and N groups of input parameters are randomly generated based on the input parameter correction value total set EXSRZ2 and the input parameter set EX.
  • Step (3) The specific implementation process is as follows: referring to Figure 1, at the start time t1 of the first correction cycle, compare the prediction parameters and the operating parameters, so as to concurrently use 2 types of correction modes, each of which has N+1 Correction scheme, run 2(N+1) correction schemes in parallel to obtain 2(N+1) sets of prediction parameters, reach the start time t2 of the second correction cycle, select the k with the top k of the prediction accuracy in the previous correction cycle Group correction schemes. Under each group of correction schemes, 2 types of correction modes are concurrently used again.
  • Each correction mode has N+1 correction schemes, so that 2k (N+1) correction schemes are run in parallel in the second correction cycle Obtain 2k(N+1) sets of prediction parameters, and repeat the process until the prediction results reach the specified accuracy to stop the correction, and select the correction scheme with the best accuracy as the optimal scheme, which is used for the prediction of the nuclear power plant simulator.
  • Step (3) After completing the correction of the nuclear power plant simulator, it also includes the cause diagnosis calculation of the specific behavior results of the nuclear power plant, that is, the combination of specific measurement parameters of the nuclear power plant (such as the output parameters of the accident transient) as the target R, through the above (3 In the step in ), use the obtained optimized prediction model to determine the prediction parameter combination X that is closest to the target R, and the corresponding input parameter combination EX is the diagnosed power station state (cause of the accident).
  • the cause diagnosis calculation of the specific behavior results of the nuclear power plant that is, the combination of specific measurement parameters of the nuclear power plant (such as the output parameters of the accident transient) as the target R, through the above (3 In the step in ), use the obtained optimized prediction model to determine the prediction parameter combination X that is closest to the target R, and the corresponding input parameter combination EX is the diagnosed power station state (cause of the accident).
  • a high-precision and high-fidelity simulation and behavior prediction device for a nuclear power plant includes a memory and a processor.
  • the memory is used to store a computer program. Methods.

Abstract

一种核电站高精度高保真实时仿真和行为预测方法及装置。方法包括步骤:(1)基于相同的设计参数构造核电站仿真机和物理核电站;(2)平行运行核电站仿真机和物理核电站,实时获取核电站仿真机输出的预测参数和物理核电站的运行参数;(3)将表征同一物理量的预测参数和运行参数进行一一比对,采用大规模并发-并行的参数搜索修正算法和基于人工智能的模式识别修正算法对核电站仿真机中的预测模型以及预测模型输入参数进行修正,直至预测参数达到指定精度;(4)根据设定工况运行核电站仿真机获取预测参数,完成物理核电站系统的行为预测。与现有技术相比,该方法具有预测准确性高、参数真实性高等优点。

Description

一种核电站高精度高保真实时仿真和行为预测方法及装置 技术领域
本发明涉及核电站仿真和行为预测方法及系统,尤其是涉及一种核电站高精度高保真实时仿真和行为预测方法及装置。
背景技术
现有核电站仿真机,主要是基于热工水力系统程序等专业软件对核电站一回路和二回路的主要设备和管线以及控制系统建立计算模型,将反应堆的设计参数或者实际反应堆的技术参数作为输入变量,来计算核电站在不同工作状态下的系统反应,为设计优化以及实际操控提供参考和指导。
现有的各型核电站大都按照自身的设计特点和实际施工现状度身定制了一套仿真计算软件(仿真机)作为操控员训练以及实际操控预演等使用。目前,仿真计算软件一般是在核电站服役前期即采用业界公认的成熟经典的专业软件,然后针对本电站的设计,运行参数编制计算卡,再经过初始的调试和验证,即可正式交付使用方使用。虽然在使用过程中,可以根据电站运行的具体情况来调整计算卡的相关参数,以获得不同运行状态的计算结果。考虑到核电站系统实际是一个庞大的现代工业系统,涉及的参数成千上万,一旦投运后,由于核电站带有辐射的特性,许多的参数无法再实时的获取,即使获取了部分参数,也无法完全推演出所有关键参数相对初始设计参数的变化。这样,运行一段时期后,仿真机的预测,特别是预测的精度会由于关键参数缺失的缘故渐渐偏离实际的结果。其次,采用附带严重事故计算模块的仿真计算软件,可以计算预测核电站在发生严重事故时,事故发展进程及相关的后果。然而,由于真实条件下的严重事故往往发生在核电站运行一段时候后,仿真机计算的准确性仍然受上述参数不确定性的影响,更重要的是,严重事故的系统计算或者预测,往往是没有系统级的试验验证的,这也导致其预测结果可能失真。
需要注意的是,上述“参数不确定性”以及“严重事故预测未经过实际验证”的问题,和计算程序和计算方法本身的精确性和适用性并不冲突,即使后二者改进的极致完美,也无法完全解决前者的问题,即仅仅采用高精度的计算方法和计算程序来进行核电站仿真和行为预测,由于输入参数和验证修正的缺陷,仍然会导致预测结果的误差。
发明内容
本发明的目的就是为了克服上述现有技术存在的缺陷而提供一种核电站高精度高保真实时仿真和行为预测方法及装置。
本发明的目的可以通过以下技术方案来实现:
一种核电站高精度高保真实时仿真和行为预测方法,该方法包括如下步骤:
(1)基于相同的设计参数构造核电站仿真机和物理核电站;
(2)平行运行核电站仿真机和物理核电站,实时获取核电站仿真机输出的预测参数和物理核电站的运行参数;
(3)将表征同一物理量的预测参数和运行参数进行一一比对,采用大规模并发-并行的参数搜索修正算法和基于人工智能的模式识别修正算法对核电站仿真机中的预测模型以及预测模型输入参数进行修正,直至预测参数无限逼近运行参数而达到指定精度,完成核电站仿真机的修正;
(4)将给定的物理核电站系统的起始运行工况输入至修正后的核电站仿真机,运行核电站仿真机获取预测参数,完成物理核电站系统的行为预测。
优选地,步骤(3)包括两类修正模式:
第一类修正模式:核电站仿真机中用于预测所有预测参数的预测模型均保持不变,对预测模型的输入参数进行修正;
第二类修正模式:对核电站仿真机中部分预测模型进行修正,剩余预测模型本身不修正,但对剩余预测模型的输入参数进行修正。
优选地,步骤(3)具体修正步骤包括:
(31)在初始修正周期中,两类修正模式同时并发进行,且在每一类修正模式下并发多个修正方案,进而核电站仿真机按照多个修正方案并行运行得到各修正方案下的预测参数;
(32)到达下一修正周期,分别选择上一修正周期中预测精度前k位的k组修正方案,分别对k组修正方案重复进行步骤(31)中的修正;
(33)重复执行步骤(32)直至预测参数无限逼近运行参数而达到指定精度,选取最优修正方案,完成核电站仿真机的修正。
优选地,第一类修正模式的具体修正方式为:
首先,获取核电站仿真机当前输出的预测参数集合X=(x1,x2,…,xn),其 中xi表示第i个预测参数,i=1,2,…,n,n表示预测参数的总个数,其中,前p个预测参数为物理核电站可直接获取的物理量,其余n-p个预测参数为物理核电站不可直接获取的物理量,X=f(EX),其中,EX为输入参数集合,f为预测模型,EX=(ex1,ex2,…,ext),ext表示第t个输入参数,t=1,2,…,t,t表示预测参数的总个数,对应地,获取物理核电站的运行参数集合R=(r1,r2,…,rn),集合R中各元素表征的物理量与集合X一一对应,前p个运行参数为直接获取的物理核电站的运行参数,其余为给定值;
然后,将集合X分为m个子集S1、S2、…Sm,同时对应将集合R分为m个子集为RS1、RS2、…、RSm,一一比对Sj和RSj,j=1,2,…,m,其中,Sj对应输入参数集合中的部分输入参数,将该部分输入参数记作EXSj,采用参数搜索修正算法对输入参数集合EX进行修正,而所有预测模型不做修正。
优选地,输入参数集合EX修正方式为:根据Sj与RSj的误差来确定EXSj的修正值集合EXSRaj,并构成输入参数修正值总集合EXSRZ1=(EXSR0,EXSRa1,EXSRa2,…,EXSRam),其中EXSR0为在EX中所有未与任意一个Sj对应的输入参数的集合,完成输入参数的修正。
优选地,第一类修正模式下并发多个修正方案的具体方式为:将输入参数修正值总集合EXSRZ1作为一组修正方案,同时基于输入参数修正值总集合EXSRZ1和输入参数集合EX随机产生N组输入参数修正值扩展集合EXSRZ1′形成N组修正方案;
EXSRZ1′组成方式:生成N组随机数列ROMn,每个随机数列含有t个随机数romt,romt的随机变化范围为(0,z),z为过修正系数,z取值为1~2,令输入参数修正值exsrt∈EXSRZ1,选取一组随机数列ROMt,则对应的输入参数修正值扩展集合EXSRZ1′中的任一修正值exsrz1t=romt*exsrt,生成一组EXSRZ1′,采用N组随机数列进行上述操作得到N组输入参数修正值扩展集合EXSRZ1′。
优选地,第二类修正模式的具体修正方式为:
首先,获取核电站仿真机当前输出的预测参数集合X=(x1,x2,…,xn),其中xi表示第i个预测参数,i=1,2,…,n,n表示预测参数的总个数,其中,前p个预测参数为物理核电站可直接获取的物理量,其余n-p个预测参数为物理核电站不可直接获取的物理量,X=f(EX),其中,EX为输入参数集合,f为预测模型,EX=(ex1,ex2,…,ext),ext表示第t个输入参数,t=1,2,…,t,t表示预测 参数的总个数,对应地,获取物理核电站的运行参数集合R=(r1,r2,…,rn),集合R中各元素表征的物理量与集合X一一对应,前p个运行参数为直接获取的物理核电站的运行参数,其余为给定值;
然后,将集合X分为m个子集S1、S2、…Sm,同时对应将集合R分为m个子集为RS1、RS2、…、RSm,一一比对Sj和RSj,j=1,2,…,m,若在连续多步的时间步进中,Sj和RSj的对比误差维持不变或不断增大的子集Sj记作Sj′,其余记作Sj″,Sj′对应输入参数集合中的部分输入参数,将该部分输入参数记作EXSj′,Sj″对应的输入参数记作EXSj″,Sj′对应的运行参数记作RSj′,Sj″对应的运行参数记作RSj″,进而,对于Sj′对应的输入参数EXSj′及预测模型采用基于人工智能的模式识别方法进行修正,对于Sj″对应的输入参数EXSj″采用参数搜索修正算法进行修正,而Sj″对应的预测模型不做修正,最终完成输入参数集合EX的修正以及部分预测模型的修正。
优选地,Sj′对应的输入参数EXSj′及预测模型的修正具体为:对于Sj′,采用基于人工智能的模式识别方法,以Sj′无限逼近RSj′无目标,直接修正EXSj′得到修正值集合EXSRbj′,同时将得到Sj′的预测模型替换为人工智能识别模型,该人工智能识别模型根据EXSRbj′直接得到预测结果;
Sj″对应的输入参数EXSj″的修正具体为:对于Sj″,根据Sj″与RSj″的误差来确定EXSj″的修正值集合EXSRaj″;
最终构成输入参数修正值总集合EXSRZ2=(EXSR0′,EXSRb1′,EXSRb2′,…,EXSRbp′,EXSRa1″,EXSRa2″,…,EXSRaq″),其中EXSR0′为在EX中所有未与任意一个Sj对应的输入参数的集合,p为采用基于人工智能的模式识别方法进行修正的输入参数子集总个数,q为采用采用参数搜索修正算法进行修正的输入参数子集总个数,p+q=m。
优选地,第二类修正模式下并发多个修正方案的具体方式为:将输入参数修正值总集合EXSRZ2作为一组修正方案,同时基于输入参数修正值总集合EXSRZ2和输入参数集合EX随机产生N组输入参数修正值扩展集合EXSRZ2′形成N组修正方案;
EXSRZ2′组成方式:生成N组随机数列ROMn,每个随机数列含有t个随机数romt,romt的随机变化范围为(0,z),z为过修正系数,z取值为1~2,令输入参数修正值exsrt∈EXSRZ2,选取一组随机数列ROMt,则对应的输入参数修正值扩 展集合EXSRZ2′中的任一修正值exsrz2t=romt*exsrt,生成一组EXSRZ2′,采用N组随机数列进行上述操作得到N组输入参数修正值扩展集合EXSRZ2′。
一种核电站高精度高保真实时仿真和行为预测装置,该装置包括存储器和处理器,所述的存储器用于存储计算机程序,所述的处理器用于当执行所述的计算机程序时实上述所述的方法。
与现有技术相比,本发明具有如下优点:
(1)本发明创新的使核电站仿真机与物理核电站平行运行,并实时将物理核电站的运行参数接入核电站仿真机,与核电站仿真机的预测参数进行实时比对,在大型计算机技术支持下,采用大规模并发/并行的参数搜索修正和基于人工智能的模式识别修正算法,实时调整电站仿真机的预测模型和预测模型的输入参数,使仿真系统在长期运行和比对修正中,其实时预测参数逐步逼近物理核电站的运行参数结果,这一新的仿真计算方法,在参数真实性和预测可靠性上,都大大超过现有的仿真机运行效果。
(2)本发明方法可用于在正常运行,检修维护,以及事故条件下,准确预测核电站系统行为和诊断故障原因,为核电站安全经济的运行提供更可靠的保障。
附图说明
图1为本发明核电站高精度高保真实时仿真和行为预测方法的运行示意图。
具体实施方式
下面结合附图和具体实施例对本发明进行详细说明。注意,以下的实施方式的说明只是实质上的例示,本发明并不意在对其适用物或其用途进行限定,且本发明并不限定于以下的实施方式。
实施例
如图1所示,一种核电站高精度高保真实时仿真和行为预测方法,该方法包括如下步骤:
(1)基于相同的设计参数构造核电站仿真机和物理核电站;
(2)平行运行核电站仿真机和物理核电站,实时获取核电站仿真机输出的预测参数和物理核电站的运行参数;
(3)将表征同一物理量的预测参数和运行参数进行一一比对,采用大规模并 发-并行的参数搜索修正算法和基于人工智能的模式识别修正算法对核电站仿真机中的预测模型以及预测模型输入参数进行修正,直至预测参数无限逼近运行参数而达到指定精度,完成核电站仿真机的修正;
(4)将给定的物理核电站系统的起始运行工况输入至修正后的核电站仿真机,运行核电站仿真机获取预测参数,完成物理核电站系统的行为预测。
核电站仿真机输出的预测参数包含但不限于核电站的热工水力、核物理参数及循环、材料、运行控制以及安全等设计参数,热工水力参数如一、二回路压力,流量,进出口温度,核物理参数如燃料富集度,燃料棒,组件和队芯构件的几何尺寸,燃料循环周期和组件排布设计,堆芯结构材料,控制棒材料和几何结构,启动堆的设计参数,正常运行的温度压力,以及安全设备的压力和温度以及材料,投入安全设施的相关阈值条件等等。其中,部分参数是可以通过物理核电站直接测量得到的(即上述物理核电站的运行参数),部分是无法进行测量的,本发明修正的目的是使得核电站仿真机输出的预测参数和物理核电站实际状态(包括上述可测量的物理核电站的运行参数以及部分不可测量的运行参数)能保持平行一致。
步骤(3)包括两类修正模式:
第一类修正模式:核电站仿真机中用于预测所有预测参数的预测模型均保持不变,对预测模型的输入参数进行修正;
第二类修正模式:对核电站仿真机中部分预测模型进行修正,剩余预测模型本身不修正,但对剩余预测模型的输入参数进行修正。
步骤(3)具体修正步骤包括:
(31)在初始修正周期中,两类修正模式同时并发进行,且在每一类修正模式下并发多个修正方案,进而核电站仿真机按照多个修正方案并行运行得到该修正方案下的预测参数;
(32)到达下一修正周期,分别选择上一修正周期中预测精度前k位的k组修正方案,分别对k组修正方案重复进行步骤(31)中的修正;
(33)重复执行步骤(32)直至预测参数无限逼近运行参数而达到指定精度,选取最优修正方案,完成核电站仿真机的修正。
第一类修正模式的具体修正方式为:
首先,获取核电站仿真机当前输出的预测参数集合X=(x1,x2,…,xn),其中xi表示第i个预测参数,i=1,2,…,n,n表示预测参数的总个数,其中,前p 个预测参数为物理核电站可直接获取的物理量,其余n-p个预测参数为物理核电站不可直接获取的物理量,X=f(EX),其中,EX为输入参数集合,f为预测模型,EX=(ex1,ex2,…,ext),ext表示第t个输入参数,t=1,2,…,t,t表示预测参数的总个数,
对应地,获取物理核电站的运行参数集合R=(r1,r2,…,rn),集合R中各元素表征的物理量与集合X一一对应,前p个运行参数为直接获取的物理核电站的运行参数,其余为给定值,可以选用上一时刻核电站仿真机输出的对应的预测参数作为给定值,在起始时刻,给定值可为0;
然后,将集合X分为m个子集S1、S2、…Sm,同时对应将集合R分为m个子集为RS1、RS2、…、RSm,一一比对Sj和RSj,j=1,2,…,m,其中,Sj对应输入参数集合中的部分输入参数,将该部分输入参数记作EXSj,采用参数搜索修正算法对输入参数集合EX进行修正,而所有预测模型不做修正。其中,对集合X的归类可按核工程传统的“现象排序表”方法,从系统-设备-现象多级分类入手,在物理现象下再按学科门类进行热工水力,核物理,材料,控制,运行,燃料循环,安全等具体类别归集。
其中,输入参数集合EX修正方式为:根据Sj与RSj的误差来确定EXSj的修正值集合EXSRaj,并构成输入参数修正值总集合EXSRZ1=(EXSR0,EXSRa1,EXSRa2,…,EXSRam),其中EXSR0为在EX中所有未与任意一个Sj对应的输入参数的集合,完成输入参数的修正。第一类修正模式下并发多个修正方案的具体方式为:将输入参数修正值总集合EXSRZ1作为一组修正方案,同时基于输入参数修正值总集合EXSRZ1和输入参数集合EX随机产生N组输入参数修正值扩展集合EXSRZ1′形成N组修正方案,EXSRZ1′组成方式:生成N组随机数列ROMn,每个随机数列含有t个随机数romt,romt的随机变化范围为(0,z),z为过修正系数,z取值为1~2,令输入参数修正值exsrt∈EXSRZ1,选取一组随机数列ROMt,则对应的输入参数修正值扩展集合EXSRZ1′中的任一修正值exsrz1t=romt*exsrt,生成一组EXSRZ1′,采用N组随机数列进行上述操作得到N组输入参数修正值扩展集合EXSRZ1′,由此并发N+1组修正方案。
第二类修正模式的具体修正方式为:
首先,获取核电站仿真机当前输出的预测参数集合X=(x1,x2,…,xn),其中xi表示第i个预测参数,i=1,2,…,n,n表示预测参数的总个数,其中,前p 个预测参数为物理核电站可直接获取的物理量,其余n-p个预测参数为物理核电站不可直接获取的物理量,X=f(EX),其中,EX为输入参数集合,f为预测模型,EX=(ex1,ex2,…,ext),ext表示第t个输入参数,t=1,2,…,t,t表示预测参数的总个数,
对应地,获取物理核电站的运行参数集合R=(r1,r2,…,rn),集合R中各元素表征的物理量与集合X一一对应,前p个运行参数为直接获取的物理核电站的运行参数,其余为给定值;
然后,同时上述方案,将集合X分为m个子集S1、S2、…Sm,同时对应将集合R分为m个子集为RS1、RS2、…、RSm,一一比对Sj和RSj,j=1,2,…,m,若在连续多步的时间步进中,Sj和RSj的对比误差维持不变或不断增大的子集Sj记作Sj′,其余记作Sj″,Sj′对应输入参数集合中的部分输入参数,将该部分输入参数记作EXSj′,Sj″对应的输入参数记作EXSj″,Sj′对应的运行参数记作RSj′,Sj″对应的运行参数记作RSj″,进而,对于Sj′对应的输入参数EXSj′及预测模型采用基于人工智能的模式识别方法进行修正,对于Sj″对应的输入参数EXSj″采用参数搜索修正算法进行修正,而Sj″对应的预测模型不做修正,最终完成输入参数集合EX的修正以及部分预测模型的修正。
Sj′对应的输入参数EXSj′及预测模型的修正具体为:对于Sj′,采用基于人工智能的模式识别方法,以Sj′无限逼近RSj′无目标,直接修正EXSj′得到修正值集合EXSRbj′,同时将得到Sj′的预测模型替换为人工智能识别模型,该人工智能识别模型根据EXSRbj′直接得到预测结果;Sj″对应的输入参数EXSj″的修正具体为:对于Sj″,根据Sj″与RSj″的误差来确定EXSj″的修正值集合EXSRaj″;最终构成输入参数修正值总集合EXSRZ2=(EXSR0′,EXSRb1′,EXSRb2′,…,EXSRbp′,EXSRa1″,EXSRa2″,…,EXSRaq″),其中EXSR0′为在EX中所有未与任意一个Sj对应的输入参数的集合,p为采用基于人工智能的模式识别方法进行修正的输入参数子集总个数,q为采用采用参数搜索修正算法进行修正的输入参数子集总个数,p+q=m。第二类修正模式下并发多个修正方案的具体方式为:将输入参数修正值总集合EXSRZ2作为一组修正方案,同时基于输入参数修正值总集合EXSRZ2和输入参数集合EX随机产生N组输入参数修正值扩展集合EXSRZ2′形成N组修正方案,EXSRZ2′组成方式:生成N组随机数列ROMn,每个随机数列含有t个随机数romt,romt的随机变化范围为(0,z),z为过修正系数,z取值为 1~2,令输入参数修正值exsrt∈EXSRZ2,选取一组随机数列ROMt,则对应的输入参数修正值扩展集合EXSRZ2′中的任一修正值exsrz2t=romt*exsrt,生成一组EXSRZ2′,采用N组随机数列进行上述操作得到N组输入参数修正值扩展集合EXSRZ2′,由此并发N+1组修正方案。
步骤(3)具体实施过程为:参照图1,在第一个修正周期的起始时刻t1,比对预测参数和运行参数,从而并发2类修正模式,每种修正模式下有N+1中修正方案,并行运行2(N+1)种修正方案得到2(N+1)组预测参数,到达第二个修正周期的起始时刻t2,选择上一修正周期中预测精度前k位的k组修正方案,在每组修正方案下,再次并发2类修正模式,每种修正模式下有N+1中修正方案,从而在第二个修正周期中并行运行2k(N+1)种修正方案得到2k(N+1)组预测参数,以此类推重复执行下去直至预测结果达到指定精度停止修正,选取具有最优精度的修正方案作为最优方案,从而用于核电站仿真机的预测。
步骤(3)完成核电站仿真机的修正后,还包括对核电站的特定行为结果进行原因诊断计算,即以核电站特定测量参数(例如事故瞬态时的输出参数)组合为目标R,通过上述(3)中的步骤,利用已获得优化预测模型,确定最接近目标R的预测参数组合X,其对应的输入参数组合EX即是诊断的电站状态(事故原因)。
一种核电站高精度高保真实时仿真和行为预测装置,该装置包括存储器和处理器,所述的存储器用于存储计算机程序,所述的处理器用于当执行所述的计算机程序时实上述所述的方法。
上述实施方式仅为例举,不表示对本发明范围的限定。这些实施方式还能以其它各种方式来实施,且能在不脱离本发明技术思想的范围内作各种省略、置换、变更。

Claims (10)

  1. 一种核电站高精度高保真实时仿真和行为预测方法,其特征在于,该方法包括如下步骤:
    (1)基于相同的设计参数构造核电站仿真机和物理核电站;
    (2)平行运行核电站仿真机和物理核电站,实时获取核电站仿真机输出的预测参数和物理核电站的运行参数;
    (3)将表征同一物理量的预测参数和运行参数进行一一比对,采用大规模并发-并行的参数搜索修正算法和基于人工智能的模式识别修正算法对核电站仿真机中的预测模型以及预测模型输入参数进行修正,直至预测参数无限逼近运行参数而达到指定精度,完成核电站仿真机的修正;
    (4)将给定的物理核电站系统的起始运行工况输入至修正后的核电站仿真机,运行核电站仿真机获取预测参数,完成物理核电站系统的行为预测。
  2. 根据权利要求1所述的一种核电站高精度高保真实时仿真和行为预测方法,其特征在于,步骤(3)包括两类修正模式:
    第一类修正模式:核电站仿真机中用于预测所有预测参数的预测模型均保持不变,对预测模型的输入参数进行修正;
    第二类修正模式:对核电站仿真机中部分预测模型进行修正,剩余预测模型本身不修正,但对剩余预测模型的输入参数进行修正。
  3. 根据权利要求2所述的一种核电站高精度高保真实时仿真和行为预测方法,其特征在于,步骤(3)具体修正步骤包括:
    (31)在初始修正周期中,两类修正模式同时并发进行,且在每一类修正模式下并发多个修正方案,进而核电站仿真机按照多个修正方案并行运行得到各修正方案下的预测参数;
    (32)到达下一修正周期,分别选择上一修正周期中预测精度前k位的k组修正方案,分别对k组修正方案重复进行步骤(31)中的修正;
    (33)重复执行步骤(32)直至预测参数无限逼近运行参数而达到指定精度,选取最优修正方案,完成核电站仿真机的修正。
  4. 根据权利要求3所述的一种核电站高精度高保真实时仿真和行为预测方法,其特征在于,第一类修正模式的具体修正方式为:
    首先,获取核电站仿真机当前输出的预测参数集合X=(x1,x2,…,xn),其中xi表示第i个预测参数,i=1,2,…,n,n表示预测参数的总个数,其中,前p个预测参数为物理核电站可直接获取的物理量,其余n-p个预测参数为物理核电站不可直接获取的物理量,X=f(EX),其中,EX为输入参数集合,f为预测模型,EX=(ex1,ex2,…,ext),ext表示第t个输入参数,t=1,2,…,t,t表示预测参数的总个数,对应地,获取物理核电站的运行参数集合R=(r1,r2,…,rn),集合R中各元素表征的物理量与集合X一一对应,前p个运行参数为直接获取的物理核电站的运行参数,其余为给定值;
    然后,将集合X分为m个子集S1、S2、…Sm,同时对应将集合R分为m个子集为RS1、RS2、…、RSm,一一比对Sj和RSj,j=1,2,…,m,其中,Sj对应输入参数集合中的部分输入参数,将该部分输入参数记作EXSj,采用参数搜索修正算法对输入参数集合EX进行修正,而所有预测模型不做修正。
  5. 根据权利要求4所述的一种核电站高精度高保真实时仿真和行为预测方法,其特征在于,输入参数集合EX修正方式为:根据Sj与RSj的误差来确定EXSj的修正值集合EXSRaj,并构成输入参数修正值总集合EXSRZ1=(EXSR0,EXSRa1,EXSRa2,…,EXSRam),其中EXSR0为在EX中所有未与任意一个Sj对应的输入参数的集合,完成输入参数的修正。
  6. 根据权利要求5所述的一种核电站高精度高保真实时仿真和行为预测方法,其特征在于,第一类修正模式下并发多个修正方案的具体方式为:将输入参数修正值总集合EXSRZ1作为一组修正方案,同时基于输入参数修正值总集合EXSRZ1和输入参数集合EX随机产生N组输入参数修正值扩展集合EXSRZ1′形成N组修正方案;
    EXSRZ1′组成方式:生成N组随机数列ROMn,每个随机数列含有t个随机数romt,romt的随机变化范围为(0,z),z为过修正系数,z取值为1~2,令输入参数修正值exsrt∈EXSRZ1,选取一组随机数列ROMt,则对应的输入参数修正值扩展集合EXSRZ1′中的任一修正值exsrz1t=romt*exsrt,生成一组EXSRZ1′,采用N组随机数列进行上述操作得到N组输入参数修正值扩展集合EXSRZ1′。
  7. 根据权利要求3所述的一种核电站高精度高保真实时仿真和行为预测方法,其特征在于,第二类修正模式的具体修正方式为:
    首先,获取核电站仿真机当前输出的预测参数集合X=(x1,x2,…,xn),其 中xi表示第i个预测参数,i=1,2,…,n,n表示预测参数的总个数,其中,前p个预测参数为物理核电站可直接获取的物理量,其余n-p个预测参数为物理核电站不可直接获取的物理量,X=f(EX),其中,EX为输入参数集合,f为预测模型,EX=(ex1,ex2,…,ext),ext表示第t个输入参数,t=1,2,…,t,t表示预测参数的总个数,对应地,获取物理核电站的运行参数集合R=(r1,r2,…,rn),集合R中各元素表征的物理量与集合X一一对应,前p个运行参数为直接获取的物理核电站的运行参数,其余为给定值;
    然后,将集合X分为m个子集S1、S2、…Sm,同时对应将集合R分为m个子集为RS1、RS2、…、RSm,一一比对Sj和RSj,j=1,2,…,m,若在连续多步的时间步进中,Sj和RSj的对比误差维持不变或不断增大的子集Sj记作Sj′,其余记作Sj″,Sj′对应输入参数集合中的部分输入参数,将该部分输入参数记作EXSj′,Sj″对应的输入参数记作EXSj″,Sj′对应的运行参数记作RSj′,Sj″对应的运行参数记作RSj″,进而,对于Sj′对应的输入参数EXSj′及预测模型采用基于人工智能的模式识别方法进行修正,对于Sj″对应的输入参数EXSj″采用参数搜索修正算法进行修正,而Sj″对应的预测模型不做修正,最终完成输入参数集合EX的修正以及部分预测模型的修正。
  8. 根据权利要求7所述的一种核电站高精度高保真实时仿真和行为预测方法,其特征在于,
    Sj′对应的输入参数EXSj′及预测模型的修正具体为:对于Sj′,采用基于人工智能的模式识别方法,以Sj′无限逼近RSj′无目标,直接修正EXSj′得到修正值集合EXSRbj′,同时将得到Sj′的预测模型替换为人工智能识别模型,该人工智能识别模型根据EXSRbj′直接得到预测结果;
    Sj″对应的输入参数EXSj″的修正具体为:对于Sj″,根据Sj″与RSj″的误差来确定EXSj″的修正值集合EXSRaj″;
    最终构成输入参数修正值总集合EXSRZ2=(EXSR0′,EXSRb1′,EXSRb2′,…,EXSRbp′,EXSRa1″,EXSRa2″,…,EXSRaq″),其中EXSR0′为在EX中所有未与任意一个Sj对应的输入参数的集合,p为采用基于人工智能的模式识别方法进行修正的输入参数子集总个数,q为采用采用参数搜索修正算法进行修正的输入参数子集总个数,p+q=m。
  9. 根据权利要求8所述的一种核电站高精度高保真实时仿真和行为预测方法, 其特征在于,第二类修正模式下并发多个修正方案的具体方式为:将输入参数修正值总集合EXSRZ2作为一组修正方案,同时基于输入参数修正值总集合EXSRZ2和输入参数集合EX随机产生N组输入参数修正值扩展集合EXSRZ2′形成N组修正方案;
    EXSRZ2′组成方式:生成N组随机数列ROMn,每个随机数列含有t个随机数romt,romt的随机变化范围为(0,z),z为过修正系数,z取值为1~2,令输入参数修正值exsrt∈EXSRZ2,选取一组随机数列ROMt,则对应的输入参数修正值扩展集合EXSRZ2′中的任一修正值exsrz2t=romt*exsrt,生成一组EXSRZ2′,采用N组随机数列进行上述操作得到N组输入参数修正值扩展集合EXSRZ2′。
  10. 一种核电站高精度高保真实时仿真和行为预测装置,其特征在于,该装置包括存储器和处理器,所述的存储器用于存储计算机程序,所述的处理器用于当执行所述的计算机程序时实现如权利要求1~9任意一项所述的方法。
PCT/CN2021/098564 2020-06-16 2021-06-07 一种核电站高精度高保真实时仿真和行为预测方法及装置 WO2021254190A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/638,189 US20220405446A1 (en) 2020-06-16 2021-06-07 High-precision high-fidelity real-time simulation and behavior prediction method and device for nuclear power station

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010548243.4A CN111797511B (zh) 2020-06-16 2020-06-16 一种核电站高精度高保真实时仿真和行为预测方法及装置
CN202010548243.4 2020-06-16

Publications (1)

Publication Number Publication Date
WO2021254190A1 true WO2021254190A1 (zh) 2021-12-23

Family

ID=72803527

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/098564 WO2021254190A1 (zh) 2020-06-16 2021-06-07 一种核电站高精度高保真实时仿真和行为预测方法及装置

Country Status (3)

Country Link
US (1) US20220405446A1 (zh)
CN (1) CN111797511B (zh)
WO (1) WO2021254190A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111797511B (zh) * 2020-06-16 2023-07-14 上海交通大学 一种核电站高精度高保真实时仿真和行为预测方法及装置
CN113420459B (zh) * 2021-07-16 2022-09-02 利晟(杭州)科技有限公司 一种基于大延时算法的污水处理系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020052673A1 (en) * 2000-11-01 2002-05-02 Korea Advanced Institute Of Science And Technology Digital online active test plant protection system in a nuclear power plant and method thereof
CN104299660A (zh) * 2013-07-15 2015-01-21 中广核工程有限公司 基于核电站的仿真测试方法和系统
CN105223932A (zh) * 2015-10-21 2016-01-06 中广核工程有限公司 核电站安全预警方法、系统以及核电站仿真技术平台
CN107885097A (zh) * 2017-10-24 2018-04-06 中广核核电运营有限公司 一种核电站模拟仪控系统dcs改造闭环验证系统及方法
CN111797511A (zh) * 2020-06-16 2020-10-20 上海交通大学 一种核电站高精度高保真实时仿真和行为预测方法及装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8712742B2 (en) * 2011-07-05 2014-04-29 Renesas Mobile Corporation Methods, devices and computer program products providing for establishing a model for emulating a physical quantity which depends on at least one input parameter, and use thereof
CN109426655B (zh) * 2017-08-22 2021-10-15 合肥捷达微电子有限公司 数据分析方法、装置、电子设备及计算机可读存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020052673A1 (en) * 2000-11-01 2002-05-02 Korea Advanced Institute Of Science And Technology Digital online active test plant protection system in a nuclear power plant and method thereof
CN104299660A (zh) * 2013-07-15 2015-01-21 中广核工程有限公司 基于核电站的仿真测试方法和系统
CN105223932A (zh) * 2015-10-21 2016-01-06 中广核工程有限公司 核电站安全预警方法、系统以及核电站仿真技术平台
CN107885097A (zh) * 2017-10-24 2018-04-06 中广核核电运营有限公司 一种核电站模拟仪控系统dcs改造闭环验证系统及方法
CN111797511A (zh) * 2020-06-16 2020-10-20 上海交通大学 一种核电站高精度高保真实时仿真和行为预测方法及装置

Also Published As

Publication number Publication date
CN111797511B (zh) 2023-07-14
US20220405446A1 (en) 2022-12-22
CN111797511A (zh) 2020-10-20

Similar Documents

Publication Publication Date Title
WO2021254190A1 (zh) 一种核电站高精度高保真实时仿真和行为预测方法及装置
US20100080334A1 (en) Method and apparatus for verifying performance of control system of nuclear power plant
US6862329B1 (en) In-cycle shuffle
CN107609286A (zh) 一种数学模型验模工具
JP2007183268A (ja) 原子炉運転に関する作動限界までのマージンを判定する方法
CN112163380A (zh) 基于数值模拟的神经网络预测炉膛氧气浓度系统及方法
CN1106137A (zh) 锈蚀分析系统和方法
CN107885967A (zh) 一种回归模型超参数优化方法
JP2011141475A (ja) 初期値生成装置及び初期値生成方法
Cai et al. Automated modelling of building energy systems with mode-based control algorithms in Modelica
CN113094976A (zh) 一种压水堆核电厂蒸汽发生器数据同化方法及系统
CN110688152B (zh) 一种结合软件开发质量信息的软件可靠性定量评估方法
CN106782703A (zh) 一种核电站一回路冷却剂泄漏的软测量方法
CN112507516B (zh) 一种基于可靠性的电气设备预防性维修优化方法及装置
JP2021039024A (ja) 炉心計算方法、炉心計算プログラムおよび炉心計算装置
CN107947181A (zh) 一种基于类热启动环境的解耦的全线性化最优潮流模型
Whyte et al. Design of a deep learning surrogate model for the prediction of FHR design parameters
CN113420498B (zh) 常减压装置的ai建模方法
Scott Component Monitoring Strategies for iPWR Plant Systems during Operational Transients
CN117634306A (zh) 一种干式电抗器状态评估方法、系统、设备及储存介质
Mazurok et al. Analysis of existing thermal-hydraulic analysis methodologies in the framework of resource extension of reactor pressure vessels
Ahmed et al. Development of virtual sensor networks to support accident monitoring systems
Ohara et al. Industrial data-driven plant optimization modeling
Del Nevo et al. The design of PSB-VVER experiments relevant to accident management
CN116705367A (zh) 一种用于核电厂自启停系统的中断点设置方法

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: 21826196

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21826196

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 24/05/2023)

122 Ep: pct application non-entry in european phase

Ref document number: 21826196

Country of ref document: EP

Kind code of ref document: A1