摘要
故障诊断是人工智能的一个重要研究内容．分析了现有故障诊断方法（基于规则、基于模型、基于人工神经网、基于案例）的各自特点和局限性．提出了集成现有故障诊断方法（规则、模型、人工神经网、案例）的故障诊断系统及其系统结构．从知识获取和表示、推理和诊断、机器学习方面，说明该新系统能结合现有故障诊断方法的互补性并克服存在的局限性，并且能提高故障诊断的智能性及效率．
Failure diagnosis is one of the important research areas of artificial intelligence. This paper analyses the characteristics and limitations of the exisiting failure diagnosis approaches (rule based, model based, based on artificial neural network, case based). A synthetic intelligent system for failure diagnosis is presented, which synthesizes the existing failure diagnosis approaches. From the descriptions of system structure, knowledge acquisition and representation, inference and diagnosis, machine learning, it is shown that the new system can combine the complementary of the existing failure diagnosis approaches and overcome their limitations, and improve the intelligence and efficiency of failure diagnosis.
出处
《上海交通大学学报》
EI
CAS
CSCD
北大核心
1998年第6期14-18,共5页
Journal of Shanghai Jiaotong University
基金
国家自然科学基金
关键词
故障诊断
人工神经网络
集成型智能系统
failure diagnosis
artificial neural network
case based reasoning
assumption based truth maintenance system(ATMS)
