Prediction of critical heat flux using ANFIS

The prediction of Critical Heat Flux (CHF) is essential for water cooled nuclear reactors since it is an important parameter for the economic efficiency and safety of nuclear power plants. Therefore, in this study using Adaptive Neuro-Fuzzy Inference System (ANFIS), a new flexible tool is developed to predict CHF. The process of training and testing in this model is done by using a set of available published field data. The CHF values predicted by the ANFIS model are acceptable compared with the other prediction methods. We improve the ANN model that is proposed by Vaziri et al. (2007) to avoid overfitting. The obtained new ANN test errors are compared with ANFIS model test errors, subsequently. It is found that the ANFIS model with root mean square (RMS) test errors of 4.79%, 5.04% and 11.39%, in fixed inlet conditions and local conditions and fixed outlet conditions, respectively, has superior performance in predicting the CHF than the test error obtained from MLP Neural Network in fixed inlet and outlet conditions, however, ANFIS also has acceptable result to predict CHF in fixed local conditions.     

Algorithm automation for nuclear power plant Loose Parts Monitoring System

Loose Parts Monitoring signals in the control room of the nuclear power plant come in through multiple channels and are presented as graphs on the display devices. It involves a lengthy and complicated process to determine the size, mass, speed, and impact location of the loose part when the signals are collected and processed. In this work, a simple and efficient model for determining the impact location of the loose part using the Least-Sum-of-Square-Errors (LSSEs) method combined with iteration has been developed based on the phase distortion of the impact signal envelopes. The signal peak point shifts to the right on the time axis when the sensor is located farther away from the impact location. This method provides a good estimation of the impact location and can be used as an alternative to existing calculations based on other attributes of the impacting signal. To automate the backend portion of the LPMS algorithm, interpolation was used for compensating the impact attenuation effect and log-log regression was also employed to determine the impacting part size and impact velocity, and the result turned out to be well in line with the manual calculations. The automated algorithm will improve the efficiency of the LPMS software.     

Identification of nuclear power plant transients using the Particle Swarm Optimization algorithm

In order to help nuclear power plant operator reduce his cognitive load and increase his available time to maintain the plant operating in a safe condition, transient identification systems have been devised to help operators identify possible plant transients and take fast and right corrective actions in due time. In the design of classification systems for identification of nuclear power plants transients, several artificial intelligence techniques, involving expert systems, neuro-fuzzy and genetic algorithms have been used. In this work we explore the ability of the Particle Swarm Optimization algorithm (PSO) as a tool for optimizing a distance-based discrimination transient classification method, giving also an innovative solution for searching the best set of prototypes for identification of transients. The Particle Swarm Optimization algorithm was successfully applied to the optimization of a nuclear power plant transient identification problem. Comparing the PSO to similar methods found in literature it has shown better results.     

Performance evaluation of PSO and GA in PWR core loading pattern optimization

The efficient operation and fuel management of PWRs are of utmost importance. Recently, genetic algorithm (GA) and particle swarm optimization (PSO) techniques have attracted considerable attention among various modern heuristic optimization techniques. GA is a powerful optimization technique, based upon the principles of natural selection and species evolution. GA is finding popularity as design tools because of its versatility, intuitiveness and ability to solve highly non-linear, mixed integer optimization problems. PSO refers to a relatively new family of algorithms and is mainly inspired by social behavior patterns of organisms that live within large group. This study addresses the application and performance comparison of PSO and GA optimization methods for nuclear fuel loading pattern problem. Flattening of power inside the reactor core of Bushehr nuclear power plant (WWER-1000 type) is chosen as an objective function to prove the validity of algorithms. In addition the performance of both optimization techniques in terms of convergence rate and computational time is compared. It is found that, from an evolutionary point of view, the performance of both GA and PSO is quite adequate. But, GA seems to arrive at its final parameter value in a fewer generations than the PSO. It is also noticed that, the computation time for implemented GA in this work is too high in comparison to PSO.     

基于BP神经网络的核电厂主动容错控制方法研究

针对核电厂中的传感器故障,采用改进的BP神经网络算法对传感器进行神经网络训练,建立各种运行状态下的动态模型库,并应用BP神经网络对系统进行实时检测。当传感器发生故障时,采用控制率重构的方法进行容错控制。在核动力装置模拟器上以稳压器为对象进行了仿真实验验证,结果表明该方法对于核电厂中的传感器故障进行容错控制是有效的。     

Calculation of the power peaking factor in a nuclear reactor using support vector regression models

Local power density (LPD) at the hottest part of a hot nuclear fuel rod should be estimated accurately to confirm that the rod does not melt. The power peaking factor (PPF) is defined as the highest LPD divided by the average power density in the reactor core. In this paper, the PPF is calculated by support vector regression (SVR) models using numerous measured signals from the reactor cooling system. SVR models are regression analysis models using a kernel function for artificial neural networks. Their neural network weights are found by solving a quadratic programming problem under linear constraints. SVR models are trained using a training data set and then verified against another test data set. The proposed SVR models were applied to the first fuel cycle of the Yonggwang nuclear power plant unit 3. The root mean square errors of the SVR model, with and without in-core neutron flux sensor signal inputs, were 0.1113% and 0.0968%, respectively. This level of errors is sufficiently low for use in LPD monitoring.     

Two novel procedures for aggregating randomized model ensemble outcomes for robust signal reconstruction in nuclear power plants monitoring systems

Detecting anomalies in sensors and reconstructing the correct values of the measured signals is of paramount importance for the safe and reliable operation of nuclear power plants. Auto-associative regression models can be used for the signal reconstruction task but in real applications the number of sensors signals may be too large to be handled effectively by one single model. In these cases, one may resort to an ensemble of reconstruction models, each one handling a small group of sensor signals; the outcomes of the individual models are then combined to produce the final reconstruction. In this work, three methods for aggregating the outcomes of a feature-randomized ensemble of Principal Components Analysis (PCA)-based regression models are analyzed and applied to two case studies concerning the reconstruction of 215 signals monitored at a Finnish nuclear Pressurized Water Reactor (PWR) and 920 simulated signals of the Swedish Forsmark-3 Boiling Water Reactor (BWR). Based on the insights gained, two novel aggregation procedures are developed for optimal signal reconstruction.     

核电厂主螺栓超声检测与信号分析

依据RSE-M标准需要定期对核电厂反应堆压力容器(RPV)主螺栓进行超声检测,为了保证主螺栓螺纹区及光杆区不同深度刻槽的超声检测灵敏度,本文对检测工艺进行声场仿真计算,分析与判断数据采集中的相关信号与非相关信号,并重点分析裂纹信号的特征,验证了超声工艺的可靠性。结合现场实施案例,通过45°横波端角反射率高的特性,综合其他检测方法如涡流和渗透检测对缺陷性质进行判定,可有效确定异常信号。     

核动力装置运行数据的特征提取方法研究

随着传感器技术的发展,核动力装置能采集和监测的运行参数越来越多,这不仅加大了操纵员的负担,而且提升了监测系统的负载。考虑到大多数参数之间具有相关性且部分参数是冗余参数,其中的有效信息可用少数参数表达,因此提出了运用机器学习方法稀疏自动编码器对核动力装置的运行参数进行特征提取,然后将提取的特征数据应用到状态监测中。结果表明,在测试样本数据中分别包含单一正常工况数据和多种正常工况数据情况下,经过特征提取后的数据不仅能提升状态监测的精度,而且还能减少计算资源,这对提升核动力装置的安全性具有重要的指导意义。     

Application of Adaptive Neuro-Fuzzy Inference System for Prediction of Neutron Yield of IR-IECF Facility in High Voltages

This paper presents a soft computing based artificial intelligent technique, adaptive neuro-fuzzy inference system (ANFIS) to predict the neutron production rate (NPR) of IR-IECF device in wide discharge current and voltage ranges. A hybrid learning algorithm consists of back-propagation and least-squares estimation is used for training the ANFIS model. The performance of the proposed ANFIS model is tested using the experimental data using four performance measures: correlation coefficient, mean absolute error, mean relative error percentage (MRE%) and root mean square error. The obtained results show that the proposed ANFIS model has achieved good agreement with the experimental results. In comparison to the experimental data the proposed ANFIS model has MRE% <1.53 and 2.85 % for training and testing data respectively. Therefore, this model can be used as an efficient tool to predict the NPR in the IR-IECF device.     

CPR1000核电机组延伸运行优化控制

延伸运行（SO）是压水堆核电机组灵活运行的重要手段,研究如何提升机组SO模式下的安全性和经济性具有重要意义。针对某中国改进型三环路压水堆（CPR1000）核电机组某次SO模式下一回路平均温度、堆芯热功率、堆芯轴向功率偏差和温度调节棒棒位等重要参数存在波动的案例,研究表明波动的主要原因是由于该CPR1000核电机组的汽轮机高压调节阀运行在流量特性曲线的陡峭区,导致阀门开度在外部扰动影响下产生波动,并诱发主蒸汽流量、一回路平均温度等重要参数的波动。结合该核电机组设备的运行特性,提出优化高压调节阀流量特性曲线和优化主蒸汽流量限值等策略来提高机组SO期间安全性和经济性。数台CPR1000核电机组采用SO模式的工程实践案例验证了该策略的有效性。      

核动力二回路系统优化设计

二回路系统是船舶核动力装置的重要组成部分,其重量和尺寸是影响核动力装置合理布置的重要因素。随着船用核动力装置大功率、高推进速度的发展趋势,二回路系统重量和体积进一步增加,对核动力设备的设计安装带来困难,并严重影响船舶的机动性。本工作建立了二回路系统的数学模型,开发了相应的计算程序,并对影响二回路重量的设计参数进行了敏感性分析。以二回路重量最小为目标和在给定的约束条件下,采用混合粒子群算法对二回路系统进行了优化设计。研究结果显示,采用优化方案后,二回路系统重量减小了7%。最后对计算结果进行了分析,指明了二回路系统优化设计的方向。     

Comparison of computational performance of GA and PSO optimization techniques when designing similar systems – Typical PWR core case

This paper compares the performance of two optimization techniques, particle swarm optimization (PSO) and genetic algorithm (GA) applied to the design a typical reduced scale two loop Pressurized Water Reactor (PWR) core, at full power in single phase forced circulation flow. This comparison aims at analyzing the performance in reaching the global optimum, considering that both heuristics are based on population search methods, that is, methods whose population (candidate solution set) evolve from one generation to the next using a combination of deterministic and probabilistic rules. The simulated PWR, similar to ANGRA 1 power plant, was used as a case example to compare the performance of PSO and GA. Results from simulations indicated that PSO is more adequate to solve this kind of problem.     

Particle Swarm Optimization applied to the nuclear reload problem of a Pressurized Water Reactor

The concept of Swarm Intelligence is based on the ability of individuals to learn with their own experience in a group as well as to take advantage of the performance of other individuals, which are social–collaborative aspects of intelligence. In 1995, Kennedy and Eberhart presented the Particle Swarm Optimization (PSO), a Computational Intelligence metaheuristic technique. Since then, some PSO models for discrete search spaces have been developed for combinatorial optimization, although none of them presented satisfactory results to optimize a combinatorial problem such as the Nuclear Reactor Reload Problem (NRRP). In this sense, we have developed the Particle Swarm Optimization with Random Keys (PSORK) to optimize combinatorial problems. PSORK has been tested for benchmarks to validate its performance and to be compared to other techniques such as Ant Systems and Genetic Algorithms, and in order to analyze parameters to be applied to the NRRP. We also describe and discuss its performance and applications to the NRRP with a survey of the research and development of techniques to optimize the reloading operation of Angra 1 nuclear power plant, located at the Southeast of Brazil.     

A neuro-fuzzy controller for axial power distribution an nuclear reactors

A neuro-fuzzy control algorithm is applied for the core power distribution in a pressurized water reactor. The inputs of the neural fuzzy system are composed of data from each region of the reactor core. Rule outputs consist of linear combinations of their inputs (first-order Sugeno-Takagi type). The consequent and antecedent parameters of the fuzzy rules are updated by the backpropagation method. The reactor model used for computer simulations is a two-point xenon oscillation model based on the nonlinear xenon and iodine balance equations and the one group, one-dimensional neutron diffusion equation having nonlinear power reactivity feedback. The reactor core is axially divided into two regions, and each region has one input and one output and is coupled with the other region. The interaction between the regions of the reactor core is treated by a decoupling scheme. This proposed control method exhibits very fast response to a step or a ramp change of target axial offset without any residual flux oscillations between the upper and lower halves of the reactor core.     

Optimization of refueling cycle length by an enhanced PSO with novel mutation operator

In this paper, a new method for optimizing the fuel arrangement in a WWER-1000 reactor core during refueling cycle is presented. Finding the best configuration corresponding to the desired pattern, an enhanced PSO with a Novel Mutation operator is applied. WIMS and PARCS (Purdue Advanced Reactor Core Simulator) codes are used to calculate the neutronics cross sections and multiplication factor of core with corresponded power peaking factors (PPFs) during burn up cycles, respectively. Cross sections and burn up during cycle length were calculated by WIMS code, then core parameters were calculated by PARCS and finally hybridization of intelligent PSO (Particle Swarm Optimization) method and novel mutation were used to obtain optimal arrangement. The purposed algorithm is based on increasing burn up value and refueling cycle length and by keeping power peaking factor in safe margins. In this way, neutronic parameters of the reactor during operation cycle from BOC (Begin Of Cycle) to EOC (End Of Cycle), were calculated. Implementation of this algorithm has been done in MATLAB. In this case, Bushehr WWER-1000 NPP reactor was studied. The comparison between results and Final Safety Analysis Report (FSAR) data shows good agreement.     

Estimation method for parameters of overlapping nuclear pulse signal

Identification of nuclear pulse signal is of importance in radioactive measurements,especially in recognizing adjacent overlapping nuclear pulses.In this article,we propose an estimation method for parameters of typical overlapping nuclear pulse signals.First,the nuclear pulses are regarded as individual genes and the norm is set as the fitness function.Second,the global optimal solution is found by searching the population of genetic algorithm,so as to estimate the parameters of nuclear pulse.With high precision,this method can identify parameters of overlapping nuclear pulses in the Sallen-Key Gaussian signal decomposition experiments.This pulse recognition method is of great significance to improve the precision of radioactive measurement and is suitable for serious overlap of nuclear pluses.     

Simulation of an hypothetical out-of-phase instability case in boiling water reactor by RELAP5/PARCS coupled codes

A very complex type of power instability occurring in boiling water reactor (BWR) consists of out-of-phase regional oscillations, in which normally subcritical neutronic modes are excited by thermal-hydraulic feedback mechanisms. The out-of-phase mode of oscillation is a very challenging type of instability and its study is relevant because of the safety implications related to the capability to promptly detect any such inadvertent occurrence by in-core neutron detectors, thus triggering the necessary countermeasures in terms of selected rod insertion or even reactor shutdown. In this work, simulations of out-of-phase instabilities in a BWR obtained by assuming an hypothetical continuous control rod bank withdrawal are being presented. The RELAP5/Mod3.3 thermal-hydraulic system code coupled with the PARCS/2.4 3D neutron kinetic code has been used to simulate the instability phenomenon. Data from a real BWR nuclear power plant (NPP) have been used as reference conditions and reactor parameters. Simulated neutronic power signals from local power range monitors (LPRM) have been used to detect and study the local power oscillations. The decay ratio (DR) and the natural frequency (NF) of the power oscillations (typical parameters used to evaluate the instabilities) have been used in the analysis. The results are discussed also making use of two-dimensional plots depicting relative core power distribution during the transient, in order to clearly illustrate the out-of-phase behavior.     

Swarm intelligence of artificial bees applied to In-Core Fuel Management Optimization

Artificial Bee Colony (ABC) algorithm is a relatively new member of swarm intelligence. ABC tries to simulate the intelligent behavior of real honey bees in food foraging and can be used for solving continuous optimization and multi-dimensional numeric problems. This paper introduces the Artificial Bee Colony with Random Keys (ABCRK), a modified ABC algorithm for solving combinatorial problems such as the In-Core Fuel Management Optimization (ICFMO). The ICFMO is a hard combinatorial optimization problem in Nuclear Engineering which during many years has been solved by expert knowledge. It aims at getting the best arrangement of fuel in the nuclear reactor core that leads to a maximization of the operating time. As a consequence, the operation cost decreases and money is saved. In this study, ABCRK is used for optimizing the ICFMO problem of a Brazilian “2-loop” Pressurized Water Reactor (PWR) Nuclear Power Plant (NPP) and the results obtained with the proposed algorithm are compared with those obtained by Genetic Algorithms (GA) and Particle Swarm Optimization (PSO). The results show that the performance of the ABCRK algorithm is better than or similar to that of other population-based algorithms, with the advantage of employing fewer control parameters.     

一种用于旋转设备运行状态无线监测的智能无线振动传感器设计

为提高已投入运行核动力装置旋转设备的运行数据采集和状态监测能力,需要解决安装传感器和敷设配套线缆困难的问题。本文采用现场可编程门阵列（FPGA）作为主控单元,设计了一种基于Zigbee物联网通信技术的智能无线振动传感器,并给出了其电路构成、工作原理,以及嵌入式控制软件的工作流程。通过对此传感器进行性能测试,结果表明该传感器功耗低,实现了对振动信号的连续采集、智能分析与上传。该无线传感器安装简单,无需敷设供电和信号线缆,可应用于构建核动力装置旋转设备的状态监测系统。