船舶核动力装置蒸汽发生器故障诊断系统研究  

DEFAULT DIAGNOSING SYSTEM OF STEAM GENERATOR FOR NUCLEAR POWER PLANT

作　　者：史觊 孙建华 付明玉 边信黔[1] 

机构地区：[1]哈尔滨工程大学动力与核能工程学院,黑龙江哈尔滨150001 [2]七院七一九研究所,湖北武汉430064

出　　处：《哈尔滨工程大学学报》2001年第3期1-4,8,共5页Journal of Harbin Engineering University

摘　　要：根据蒸汽发生器的结构特点与工作特点 ,从理论上分析了导致常见故障的各种原因 ,并结合现场专家的直觉经验 ,建立了蒸汽发生器的故障知识库 ,同时将Kohonen算法应用于模糊神经网络的故障诊断系统 .在故障诊断过程中 ,根据自身的联想特点 ,将模糊运算引入神经网络中 ,有效地解决了知识的不确定性导致诊断的不确定性的问题 .该诊断系统具有元教师的自组织、自学习功能 ,并且聚类能力强。All kinds of reasons are analysed in theory and default repository is established,according to structure and work characteristic of steam generator combined with local experts instinct experiences.At the same time ,Kohonen algorithm is used for default diagnosis system based on fuzzy neural networks.Fuzzy arithmetic is inducted into neural network to solve the problem that knowledge uncertainty induces diagnosis uncertainty,according to its self_association in the course of default diagnosis.The system is provided with non_supervise,self_organizing,self_learning,and has strong and fast cluster ability.

关 键 词：神经网络 蒸汽发生器 模糊计算 故障诊断 船舶核动力装置 Kohonen算法 

分 类 号：U644.15[交通运输工程—船舶及航道工程] TP277[交通运输工程—船舶与海洋工程]