Comparisons between the various types of neural networks with the data of wide range operational conditions of the Borssele NPP

This paper addresses a trend monitoring in operating nuclear power plant by use of two types of Recurrent Neural Networks (RNN). The interesting feature of the RNN is intrinsic dynamic memory that reflects the current output as well as the previous inputs and outputs are gradually quenched. The first one Elman type of RNN which has a feed-back from hidden layer to the input layer neurons while in the Jordan type, from the outputs of the neural net to the inputs of the neural net. In this paper the theoretical assessment of the both RNNs is given. Both topological structures including Back Propagation (BP) neural network were implemented to the Borssele NPP. Learning achieved from 30% to 100% nominal power at the starting period of the new core 30 September 2001. After learning period the reactor operation is followed by the neural network. Paper will present the reactor system, the real time data collection and the merits of the three types of the neural network applied while in the learning and continuous processing of the changing of the operational conditions.     

压水堆核电站堆芯集中参数模型的微机仿真

阐述了PWR核电站堆芯的模型化问题,提适用于微机仿真的核电站堆芯的物理数学模型,将核电站堆芯分为三大块分别建立模型,中子动力学模块,反应性反馈模块,堆芯热力学模块,建立系统传递函数,运用MATLA仿真,得到良好结果。     

核电站反应堆冷却剂系统主管道安装焊接

以秦山核电二期工程为例,论述了核电站反应堆冷却剂系统主管道安装焊接技术及质量控制要点,并对反应堆冷却剂系统主管道的安装顺序、安装技术要求、焊接质量检验方法以及焊接变形的控制等方面给予了详细的阐述,对核电站反应堆冷却剂系统主管道安装焊接及质量控制具有借鉴作用。     

船舶核动力装置安全目标的初步研究

安全目标是核电厂进行安全评价的重要基础和判定准则,对安全评价工作具有非常重要的影响.目前,核电厂安全目标的认识和制定已经经历了较长的时间,形成了以国际原子能机构(IAEA)和美国核管会(NRC)为主的两大体系.文章概要地介绍了两个组织所确定的定性和定量安全目标,以及我国核电厂安全目标的发展和应用现状.最后,在吸收上述经...     

核电站实物保护系统集成模式浅析

实物保护系统是对核电站及核设施的重要设备和核材料实施保卫,使其在任何情况下,重要设备遭受破坏和核材料丢失的危险减至最小。早期实物保护系统涉及的各子系统相互独立,无法形成整个系统的真正集成,导致资源浪费和投资成本的增加。本文研究了实物保护系统的不同集成模式,建立了基于对象的子系统相互平等互连的模式进行集成的模型,并着重研究了该集成模型的体系结构。     

压水堆核电厂实时传输重要安全参数的规范化初步研究

核电厂实时安全参数传输和交换对于核电厂日常管理和应急响应都有重要的意义.基于相关法规标准要求和应急响应需要,结合各机组类型的具体参数,并考虑参数的可获得性,提出了相对统一的PWR核电厂实时传输安全重要机组参数和实时环境监测参数,为核电厂安全相关参数传输标准化工作提供了一定的技术基础.     

On-line neuro-expert monitoring system for Borssele Nuclear Power Plant

A new method for an on-line monitoring system for the nuclear power plants has been developed utilizing the neural networks and the expert system. The integration of them is expected to enhance a substantial potential of the functionality as operators support.

The recurrent neural network and the feed-forward neural network with adaptive learning are selected for the plant modeling and anomaly detection because of the high capability of modeling for dynamic behavior. The expert system is used as a decision agent, which works on the information space of both the neural networks and the human operators. The information of other sensory signals is also fed to the expert system, together with the outputs that the neural networks generate from the measured plant signals. The expert system can treat almost all known correlation between plant status patterns and operation modes as a priori set of rules.

From the off-line test at Borssele Nuclear Power Plant (PWR 480 MWe) in the Netherlands, it was shown that the neuro-expert system successfully monitored the plant status. The expert system worked satisfactorily in diagnosing the system status by using the outputs of the neural networks and a priori knowledge base from the PWR simulator. The electric power coefficient is simultaneously monitored from the measured reactive and active electric power signals.     

福清核电厂应急撤离时间估算

本文介绍了环境保护部核与辐射安全中心主持开发的“核电周边人员应急撤离的虚拟现实模拟系统”(简称“撤离模拟系统”)及所采用的技术。结合福清核电厂厂址周围的人口分布、交通基础设施分布和天气状况,利用该系统模拟了不同撤离情景下,福清核电厂烟羽应急计划区内人员的撤离过程,估算了撤离时间,分析了影响撤离的主要因素。研究结果表明,福清核电厂在典型事故情景下,部分拥堵路段对撤离时间影响显著;同时,私家车的使用比例增加也会显著增加撤离时间。     

核电厂数字化仪控系统结构比较分析

采用比较方法,分别从核电厂的特殊性、系统分层原理、仪表性能等方面针对几个核电厂数字化仪控系统结构作了对比分析,并从中提出在核电厂设计和应用这类系统时需要注意的问题。     

压水堆核电厂气液态放射性流出物源项计算程序CPGale的开发北大核心CSCD

分析了压水堆核电厂运行状态下气液态放射性流出物的产生和排放途径,建立了压水堆核电厂运行状态下气液态放射性流出物源项的计算模型,开发了具有良好人机界面的计算程序CPGale,并采用国内在役压水堆核电厂的流出物源项实测值对程序进行了验证。结果表明,基于CPGale程序计算所得流出物源项相比实测值具有适度的保守性,可满足工程设计的需求。     

压水堆核电厂辐射监测系统的设计与改造

辐射监测系统是压水堆核电厂安全运行的重要保障,研究压水堆核电厂辐射监测系统的设计方法和原则,对于提高压水堆核电厂辐射监测系统的设计水平,减少改造风险至关重要.根据核电厂的法规和设计规范,结合大亚湾核电厂辐射监测系统的设计与改造经验,提出了压水堆核电厂辐射监测系统的一般设计原则和要求,并简要介绍了大亚湾核电厂辐射监测系统...     

核电站核岛物项质量控制信息化实现

根据核电站核岛物项质量管理模式,阐述了核电站核岛物项质量控制信息化实现的设计思路、实现方法和一些关键技术,说明了核岛物项质量控制方式可以提高核岛质量、保证核电站的安全、降低核电站建造和运营成本。     

Thermal hydraulic behaviors during loss of RHR system at mid-loop operation of Chinese 300 MWe PWR NPP

Thermal hydraulic behavior of nuclear power plant (NPP) is analyzed by using mechanistic computer code for loss of residual heat removal (RHR) system during mid-loop operation of Chinese 300 MWe two-loop pressurized water reactor is presented. In the absence of recovery of RHR or other accident management measures, the reactor core will be uncovered for a long term resulting in core heat-up, degradation and relocation to the lower plenum. The effectiveness of available mitigate measures, such as safety injection system, gravity feed from refueling water storage tank (RWST) and steam generator (SG) reflux-condensation, are investigated. Coolant injection is highly effective in halting the accident progression and make the core recovered. The cooling capability of SG reflux-condensation has a relationship with different availabilities of steam generators and decay heat power. 6 days after shutdown, 2SG operation can keep the water level at mid-line of hot leg. 12 days after shutdown, both 2SG operation and 1SG operation can keep the water level at mid-line of hot leg. The analyses also indicate that the cooling mechanism of safety injection system is more effective than gravity feed from RWST and SG reflux-condensation. Through confirming the success criteria of SG reflux-condensation, time windows can be devided. Then, event trees for loss of RHR system under mid-loop operation are built with considering the analysis results and abnormal procedure.     

秦山核电厂反应堆燃料组件的流量平衡试验研究

本文描述了对我国第一台自己设计建造的三十万千瓦压水堆核电站采用的燃料组件之间的流量平衡进行了一系列的水力特性试验研究,合理地解决了燃料组件上方四种不同结构部件间的阻力匹配,把燃料组件之间的冷却剂流量偏差调整在1％以内。同时,通过实验改进了阻力塞部件的结构设计,确定了反应堆堆芯上栅格板的开孔尺寸,测定了各种不同形式燃料组件的出口阻力系数,为秦山核电厂反应堆的热工设计和结构设计提供了可靠的实验依据。     

核电站用贮气罐抗震分析

采用有限元法,对台山核电站SBO柴油发电机组用贮气罐进行了结构抗震计算分析。介绍了贮气罐结构的力学建模、载荷条件和地震响应谱分析方法,计算得到了结构的固有频率、振型和地震载荷下的响应,并根据RCCM规范对结构在重力、内压、地震等多种载荷组合下的应力进行评定。结果表明,贮气罐的结构强度满足规范要求。计算结果为贮气罐的抗震设计提供了依据。     

An interface redesign for the feed-water system of the advanced boiling water reactor in a nuclear power plant in Taiwan

A well-designed human-computer interface for the visual display unit in the control room of a complex environment can enhance operator efficiency and, thus, environmental safety. In fact, a cognitive gap often exists between an interface designer and an interface user. Therefore, the issue of the cognitive gap of interface design needs more improvement and investigation. This is an empirical study that presents the application of an ecological interface design (EID) using three cases and demonstrates that an EID framework can support operators in various complex situations. Specifically, it analyzes different levels of automation and emergency condition response at the Lungmen Nuclear Power Plant in Taiwan. A simulated feed-water system was developed involving two interface styles. This study uses the NASA Task Load Index to objectively evaluate the mental workload of the human operators and the Situation Awareness Rating Technique to subjectively assess operator understanding and response, and is a pilot study investigating EID display format use at nuclear power plants in Taiwan. Results suggest the EID-based interface has a remarkable advantage over the original interface in supporting operator performance in the areas of response time and accuracy rate under both normal and emergency situations and provide supporting evidence that an EID-based interface can effectively enhance monitoring tasks in a complex environment.     

Development and assessment of fire-related risk unavailability matrices to support the application of the maintenance rule in a PWR nuclear power plant

Two methods are presented which serve to incorporate the fire-related risk into the current practices in nuclear power plants with respect to the assessment of configurations. The development of these methods is restricted to the compulsory use of fire probabilistic safety assessment (PSA) models. The first method is a fire protection systems and key safety functions unavailability matrix which is developed to identify structures, systems, and components significant for fire-related risk. The second method is a fire zones and key safety functions (KSFs) fire risk matrix which is useful to identify fire zones which are candidates for risk management actions. Specific selection and quantification methodologies have been developed to obtain the matrices. The Monte Carlo method has been used to assess the uncertainty of the unavailability matrix. The analysis shows that the uncertainty is sufficiently bounded. The significant fire-related risk is localized in six KSF representative components and one fire protection system which should be included in the maintenance rule. The unavailability of fire protection systems does not significantly affect the risk. The fire risk matrix identifies the fire zones that contribute the most to the fire-related risk. These zones belong to the control building and electric penetrations building.     

Safety assessment for the ultimate heat sink (UHS) system with non-injection concept in nuclear power plants (NPPs)

Following the Fukushima accident, it is proposed to find a better safety system, which has a pool-type cooling system without coolant injections. Since the conventional piping-based injection systems have failed in treating the three major severe accidents, the artificial pool could be constructed to cover the failed reactor core systems in which the pool-like structure is constructed. Regarding this study, there were some previous studies about the ultimate heat sink (UHS). In this study, the system dynamics (SD) modeling is performed in the case of Fukushima Unit 1 accident. The basic events are obtained by the Boolean values as 0 and 1. The quantifications are obtained by the SD algorithm incorporated with the Vensim software. In the simulations work, there is a plateau region between the 25th and 45th years in the interested period. The nonlinear algorithm is applied for the UHS analysis which was not installed for the commercial use yet.