基于多智能体和人工神经网络的水电厂预知维护系统的研究  

PREDICTIVE MAINTENANCE FOR HYDROPOWER PLANT BASED ON MAS AND ANN

作　　者：傅闯[1] 叶鲁卿[2] 余刃[3] 刘永前[4] 陈木华 

机构地区：[1]浙江大学电气学院,浙江省杭州市310027 [2]华中科技大学,湖北省武汉市430074 [3]海军工程大学,湖北武汉430033 [4]华北电力大学,北京市昌平区102206 [5]珠江钢铁有限公司,广东省广州市510730

出　　处：《中国电机工程学报》2005年第6期81-87,共7页Proceedings of the CSEE

摘　　要：随着电力市场的发展,水电厂维护的自动化是提高水电厂整体经济效益的必然要求。在 ICMMS 框架下,提出了一种水电厂预知维护系统的多智能体模型。该模型由数据采、诊断与预诊断层以及维护决策层组成,从信号采集到维护决策的所有维护活动都集成到这个模型中。利用这个模型,建立了一个水电厂预知维护系统的原型系统,并应用 ANN 技术成功地解决了原型系统动态特性的在线监测、识别和故障诊断。As the development of the electrical power market, the maintenance automation has become an intrinsic need to increase the overall economic efficiency of hydropower plants. A Multi-Agent System (MAS) based model for the predictive maintenance system of hydropower plant within the framework of Intelligent Control-Maintenance-Management System (ICMMS) is proposed. All maintenance activities, from data collection through the recommendation of specific maintenance actions, are integrated into the system. In this model, the predictive maintenance system composed of four layers: Signal Collection, Data Processing, Diagnosis and Prognosis, and Maintenance Decision-Making. Using this model, a prototype of predictive maintenance for hydropower plant is established. Artificial Neural-Network (ANN) is successfully applied to monitor, identify and diagnosis the dynamic performance of the prototype system online.

关 键 词：维护系统 水电厂 人工神经网络 多智能体模型 系统动态特性 ICMMS 数据采集层 ANN技术 电力市场 经济效益 数据处理 信号采集 原型系统 在线监测 故障诊断 自动化 决策层 诊断层 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论] TV736[自动化与计算机技术—计算机科学与技术]