Application of FBOLES—a prototype expert system for fault diagnosis in nuclear power plants

The basic concept of a frequency-based on-line expert system (FBOLES) approach for the on-line fault diagnoses of nuclear power plants has been previously presented in our companion papers. This paper reports on the status of the protoype software development and the real time on-line experiment results. The main steam and feedwater condensate system (MSFCS, namely, the secondary loop) of a nuclear power plant (950 MW, three loops) simulated by the Tsinghua simulator has been selected as a target system at the present stage of development. The knowledge bases for MSFCS have been initially constructed. A total of 62 signals from the simulator have been selected as the on-line evidence for diagnosis. Thirty-three fault experiments were performed in which 21 were detected accurately (only one candidate) by FBOLES immediately after the first abnormal signals were received and the other 12 were detected accurately within 0·5 to 3 min as the development of abnormality. These experiments include not only the failures of pumps, valves, pipes, etc., of MSFCS itself, but also the failures outside MSFCS. Three of them involve non-initiating events. As a software package, FBOLES can perform either the on-line diagnosis where the signals are input from the simulator directly or the off-line diagnosis that either repeats the on-line diagnosis in a selectable time scale by using the data received on-line and stored on disk or allows users to input signals from a keyboard. Also, the integrated information base, including the modular mini knowledge bases and other necessary data, can be edited and assembled by users easily and compiled by FBOLES into coded format.     

A model-based approach to on-line process disturbance management: The application

A model-based methodology for developing a real-time expert system for on-line process disturbance management has been presented in the companion paper (Reliab. Engng Sys. Safety, Vol. 28, pp. 265–305). The methodology includes diverse functional aspects required for effective process disturbance management: intelligent process monitoring and alarming, sensor failure diagnosis, hardware (except sensors) failure diagnosis, and corrective measure synthesis.The application of the methodology to a target process—the main feedwater system of a pressurized water reactor (PWR) nuclear plant employing a complex control scheme—is presented in this paper. The performance tests of the real-time expert system, MOAS II, developed by the application of the methodology demonstrate that the expert system successfully carries out its intended functions: early detection of occurring disturbance, correct diagnosis of the disturbance cause, and presentation of optimal control advice to the operator. Therefore, the model-based technique lends itself to the development of a valuable operator aid for on-line process disturbance management.     

Comment: Toward the practical use of expert system technique for process disturbance management

A methodology is proposed which can be used to design real-time expert systems for on-line process disturbance management. This methodology encompasses diverse functional aspects that are required for an effective process disturbance management: (1) intelligent process monitoring and alarming, (2) on-line sensor data validation and sensor failure diagnosis, (3) on-line hardware (besides sensors) failure diagnosis, and (4) real-time corrective measure synthesis. Accomplishment of these functions is made possible through the integrated application of the various models: goal-tree success-tree, process monitor tree, sensor failure diagnosis, and hardware failure diagnosis models. This paper presents and discusses the various models along with the overall algorithm of the methodology. The application of the methodology to a target process, a typical main feedwater system of a nuclear power plant which employs a complex control mechanism, will be presented in a companion paper.     

核电厂管道振动原因分析及对策

管道是核电厂主要的组成部份。核电厂管道的振动往往引起管道的振动疲劳,长期积累致使管道开裂,严重时核电厂被迫停堆检修,甚至造成灾难性事故。为了减少此类事件的发生,本文总结了诱发核电厂管道振动的主要原因,有旋转设备的振动、水锤、流体脉动、气蚀、气液两相流、风载荷、地震载荷和人为误差等几种,并列举了相关事件案例,提出了常见的整改方案。本文旨在为核电厂管道的设计、建造、维护与整改等工作提供必要的参考依据。     

Expert systems for emergency alarms analysis during accident situations in nuclear reactors

Expert system development is an important application of artificial intelligence. During the last few years, many successful expert systems have been developed in various fields like medical diagnosis, geological exploration, office management, etc. Expert systems is a computer software which solves reasonably complex problems where normally one needs an expert in that field to solve them.Recently efforts are being made in developing expert systems to support the operating staff in nuclear reactors. Nuclear power plant is one of the most complex engineering systems and safe and reliable operation is of primary importance. In spite of many automatic and redundant safety systems there are some occasions when the operating staff have to analyse the alarms and take further safety actions. Few of the severe accidents like Three Mile Island in USA and Chernobyl in USSR are attributed to the errors made by the operating staff and/or management. Nuclear engineers or systems analysts who may be expert in analysing an accident situation and advise corrective safety actions may not be readily available during the accident situations in the nuclear power plants. It is possible to model such expert knowledge in expert systems and this can be applied in diagnosing an accident situation like the loss of coolant accident (LOCA) and act as an additional confirmatory aid to the operating staff.Two small expert systems examples have been developed and are explained in this paper. One identifies a spurious LOCA alarm in a heavy water research reactor. The second example identifies the type of medium/small leakage (LOCA) in a coolant circuit of a PWR and suggests the subsequent safety actions. Both the examples have been developed using the expert systems shell VP-expert. They are off-line usable and user interactive. We do not propose expert system application for very fast response safety actions like reactor scram. These two small expert system examples are essentially to support the feasibility study in their applications during accident situations in nuclear power plants.     

From LESSEPS to the workstation for reliability engineers

Three Mile Island and Chernobyl in the nuclear industry, Challenger, in the space industry, Seveso and Bhopal in the chemical industry—all these accidents show how difficult it is to forecast all likely accident scenarios that may occur in complex systems. This was, however, the objective of the probabilistic safety assessment (PSA) performed by EDF at the Paluel nuclear power plant. The full computerization of this study led to the LESSEPS project, aimed at automating three different steps: generation of reliability models—based on the use of expert systems, qualitative and quantitative processing of these models using computer codes, and overall management of PSA studies. This paper presents the results obtained and the gradual transformation of this first generation of tools into a workstation aimed at integrating reliability studies at all stages of an industrial process.     

System reliability and system resilience

1 Introduction With the development of new technology,engineering systems are becoming more complex in structure and possessing more advanced functions.Customers are setting higher quality requirements for new products.Reliability must be considered in all aspects of the product life cycle.Inadequate reliability considerations may cause civil aviation disasters,nuclear power plant accidents,spacecraft launch failures,power system shutdowns,and other major accidents.Since the emergence of the reliability discipline in the 1950s,reliability theory has been developing rapidly,which has played an irreplaceable role in promoting the progress of major industries such as aviation,aerospace,and nuclear energy.It has also greatly improved the quality of daily necessities such as computers,appliances,and automobiles.The capability of manufacturing high-end equipment with high reliability and long life has become an important strategic indicator of a country's global strength and competitiveness.     

Application of genetic algorithms to fault diagnosis in nuclear power plants

A nuclear power plant (NPP) is a complex and highly reliable special system. Without expert knowledge, fault confirmation in the NPP can be prevented by illusive and real-time signals. A new method of fault diagnosis, based on genetic algorithms (GAs) has been developed to resolve this problem. This NPP fault diagnosis method combines GAs and classical probability with an expert knowledge base. By assessing the state of the NPP, the GA colony undergoes a transformation that produces an individual adapted to the NPP's condition. Experiments performed on the 950 MW full size simulator at the Beijing NPP simulation training center show that this method has comparative adaptability to diagnose signals and faults changed with time, imperfect expert knowledge, illusive signals and other phenomena.     

Severe accidents in the energy sector: comparative perspective

This paper addresses one of the controversial issues in the current comparative studies of the environmental and health impacts of energy systems, i.e. the treatment of severe accidents. The work covers technical aspects of severe accidents and thus primarily reflects an engineering perspective on the energy-related risk issues, though some social implications are also touched upon. The assessment concerns fossil energy sources (coal, oil and gas), nuclear power and hydro power. The scope is not limited to the power production (conversion) step of these energy chains but, whenever applicable, also includes exploration, extraction, transports, processing, storage and waste disposal. With the exception of the nuclear chain the focus of the work has been on the evaluation of the historical experience of accidents. The basis used for this evaluation is a comprehensive database ENSAD (Energy-related Severe Accident Database), established by the Paul Scherrer Institut (PSI). For hypothetical nuclear accidents the probabilistic technique has also been employed and extended to cover the assessment of economic consequences of such accidents. The broader picture obtained by coverage of full energy chains leads on the world-wide basis to aggregated immediate fatality rates being much higher for the fossil chains than what one would expect if only power plants were considered. Generally, the immediate fatality rates are for all considered energy carriers significantly higher for the non-OECD countries than for OECD countries. In the case of hydro and nuclear the difference is in fact dramatic. The presentation of results is not limited to the aggregated values specific for each energy chain. Also frequency-consequence curves are provided. They reflect implicitly the ranking based on the aggregated values but include also such information as the observed or predicted chain-specific maximum extents of damages. This perspective on severe accidents may lead to different system rankings, depending on the individual risk aversion.     

Examination of issues related to the development and implementation of real-time operational safety monitoring tools in the nuclear power industry

In recent years, risk and reliability techniques have been increasingly used to optimize deterministic requirements and to improve the operational safety of nuclear power stations. This paper discusses the historical development and current status of implementation of real-time operational safety monitoring tools in the nuclear power industry worldwide. A safety monitor is defined as a PC-based risk management tool, based on a plant specific PSA, which can be used to manage plant safety during the day-to-day operation of a nuclear power plant by planning maintenance activities and providing advisory information to plant operational staff in order to avoid high risk plant configurations. As this technique has only been applied in a few plants worldwide, the technology is still evolving and there are several technical and implementation-related issues which still need to be resolved. This paper attempts to summarize all such issues and describe how they have been addressed in several different applications of this technology around the world.     

Development of a dynamical systems model of plant programmatic performance on nuclear power plant safety risk

Application of probabilistic risk assessment (PRA) techniques to model nuclear power plant accident sequences has provided a significant contribution to understanding the potential initiating events, equipment failures and operator errors that can lead to core damage accidents. Application of the lessons learned from these analyses has resulted in significant improvements in plant operation and safety. However, this approach has not been nearly as successful in addressing the impact of plant processes and management effectiveness on the risks of plant operation. The research described in this paper presents an alternative approach to addressing this issue. In this paper we propose a dynamical systems model that describes the interaction of important plant processes on nuclear safety risk. We discuss development of the mathematical model including the identification and interpretation of significant inter-process interactions. Next, we review the techniques applicable to analysis of nonlinear dynamical systems that are utilized in the characterization of the model. This is followed by a preliminary analysis of the model that demonstrates that its dynamical evolution displays features that have been observed at commercially operating plants. From this analysis, several significant insights are presented with respect to the effective control of nuclear safety risk. As an important example, analysis of the model dynamics indicates that significant benefits in effectively managing risk are obtained by integrating the plant operation and work management processes such that decisions are made utilizing a multidisciplinary and collaborative approach. We note that although the model was developed specifically to be applicable to nuclear power plants, many of the insights and conclusions obtained are likely applicable to other process industries.     

Safety of nuclear power plants

The safety of operating nuclear power plants of the CANDU type is described in this paper. The need for a systematic study on these types of heavy water reactors similar to the safety studies done on light water reactors is brought out in this paper. Some of the work done on station blackout, operational transients, small and large break loss of coolant accidents is reviewed. Recent nuclear power plant accidents, namely Three-Mile Island-2 and Chernobyl, seem to indicate that an understanding of man-machine interaction and human behaviour under stress is important for the safety aspects and more work needs to be done in these areas.     

真空冶金设备抽气装置专家系统及应用实例

介绍了专家系统的特点和应用,分析了大型真空冶金抽气装置的特性、故障多发原因以及排查中的困难,指出采用专家系统的可行性和实际意义,明确了在真空冶金抽气装置中建立专家系统的具体内容.以宝钢RH-KTB炉外精炼真空系统为例,给出了设备运行监测方案,建立了专家系统知识库,编制的软件可对设备的运行状态进行即时评价和故障预报,当真空系统出现故障时,采用逆向推理机制,从目标出发,寻找故障可能原因,并给出推理解释.专家系统对监测参数阈值的机器学习,提高了专家系统实际应用中的推理效率和准确性.专家系统软件经离线测试和现场在线应用达到预期的目标,可以推广应用.     

An expert system for finding fragility curves of building structural systems at the preliminary design stage

This research developed an expert system for determining seismic fragility curves of structural systems in a nuclear power plant or conventional building at the preliminary design stage. The resulting system simulates the performance of human experts in identifying the potential failure modes and their likelihood for a structure of interest. Induction technique is used for knowledge acquisition. The characteristics of structural systems are described by their attributes and their values.     

NAROAS: a neural network-based advanced operator support system for the assessment of systems reliability

We have developed and implemented a computerized reliability monitoring system for nuclear power plant applications, based on a neural network. The developed computer program is a new tool related to operator decision support systems, in case of component failures, for the determination of test and maintenance policies during normal operation or to follow an incident sequence in a nuclear power plant. The NAROAS (Neural Network Advanced Reliability Advisory System) computer system has been developed as a modularized integrated system in a C++ Builder environment, using a Hopfield neural network instead of fault trees, to follow and control the different system configurations, for interventions as quickly as possible at the plant. The observed results are comparable and similar to those of other computer system results. As shown, the application of this neural network contributes to the state of the art of risk monitoring systems by turning it easier to perform online reliability calculations in the context of probabilistic safety assessments of nuclear power plants.     

大亚湾核电站核岛冷水系统制冷机组运行分析

介绍了大亚湾核电站核岛冷水系统(DEG)的主要核心设备-制冷机组的功能原理及其维修情况;阐述了1DEG201GF制冷机组在运行过程中出现的叶轮故障问题与处理方法;根据维修经验给出了制冷机组的调试方案,并对制冷机组的运行维修的改进方案作了进一步的探讨.     

XPC: an on-line expert system for statistical process control

The majority of available microcomputer packages for statistical process control (SPC) are off-line programs which present information regarding quality in the form of control charts. The user has to interpret the charts to infer process and product quality. This paper describes XPC, an on-line expert system for SPC. The system produces mean and range charts and interprets them automatically. XPC consists of five main modules. The first module ascertains process parameters and constructs the charts. The second module performs capability analysis to ensure that these control charts are compatible with the process specifications. The third module interprets on-line data, detects possible out-of-control situations and suggests corrective actions. The fourth module updates the charts to improve process capability. The last module produces periodical reports. XPC is based on Leonardo, an expert system shell with a hybrid knowledge representation facility enabling the use of rules, rulesets, frames, procedures and classes     

核电厂检修热车间暖通空调控制的设计与实现

暖通空调系统是维持核电厂检修热车间室内环境、防止放射性释放的关键系统.为实现可靠运行、减少对人员操作和维护的需求,运用“暂停调节”、均衡受控设备启动次数和工作时间、输入和设备异常处理、纠正异常输出等措施,设计了暖通空调控制系统,并在可编程控制器上实现.该系统控制各作业区域的温度和备件贮存区域的温度和湿度,以及空调供水系统的供回水压差,经历了较长时间实际运行的考验.     

Application of core vector machines for on-line voltage security assessment using a decisiontree-based feature selection algorithm

This study presents a core vector machine (CVM)-based algorithm for on-line voltage security assessment of power systems. To classify the system security status, a CVM has been trained for each contingency. The proposed CVM-based security assessment algorithm has a very small training time and space in comparison with support vector machines (SVMs) and artificial neural networks (ANNs)-based algorithms. The proposed algorithm produces less support vectors (SVs). Therefore is faster than existing algorithms. One of the main points to apply a machine learning method is feature selection. In this study, a new decision tree (DT)-based feature selection algorithm has been presented. The proposed CVM algorithm has been applied to New England 39-bus power system. The simulation results show the effectiveness and the stability of the proposed method for on-line voltage security assessment. The effectiveness of the proposed feature selection algorithm has also been investigated. The proposed feature selection algorithm has been compared with different feature selection algorithms. The simulation results demonstrate the effectiveness of the proposed feature algorithm.     

A method for evaluating fault coverage using simulated fault injection for digitalized systems in nuclear power plants

The fault coverage for digital system in nuclear power plants is evaluated using a simulated fault injection method. Digital systems have numerous advantages, such as hardware elements share and hardware replication of the needed number of independent channels. However, the application of digital systems to safety-critical systems in nuclear power plants has been limited due to reliability concerns. In the reliability issues, fault coverage is one of the most important factors. In this study, we propose an evaluation method of the fault coverage for safety-critical digital systems in nuclear power plants. The system under assessment is a local coincidence logic processor for a digital plant protection system at Ulchin nuclear power plant units 5 and 6. The assessed system is simplified and then a simulated fault injection method is applied to evaluate the fault coverage of two fault detection mechanisms. From the simulated fault injection experiment, the fault detection coverage of the watchdog timer is 44.2% and that of the read only memory (ROM) checksum is 50.5%. Our experiments show that the fault coverage of a safety-critical digital system is effectively quantified using the simulated fault injection method.