摘要
基于知识的故障诊断系统不需要对象的精确数学模型,具有很强的生命力,其诊断能力与知识库中知识的深浅、容量和精度成正向关系。讨论了基于知识的故障诊断系统所用的各种深层知识,并认为:系统的深层知识是基于系统结构的功能模型和行为模型,它们既可以用定性方式,也可以用定量方式描述。SDG(符号定向图)方法基于深层知识模型进行推理,是一种完备的揭示系统潜在故障的有效方法。
The fault diagnosis system based on knowledge doesn＇ t need accurate mathematical model and so has strong activity. Its diagnosing capability is determined by the deepness, quantity and accuracy of the knowledge included in its knowledge base. All kinds of deep knowledge are discussed in detail. That the deep knowledge is functional and behavior models based on the structure of the diagnosed system is pointed out. It can be described in quantitative or qualitative mode. Based on deep knowledge, SDG（ Signed Directed Graph ） inference is a self-contained method to effectively diagnosis potential system failures.
出处
《化工自动化及仪表》
EI
CAS
2005年第4期8-11,共4页
Control and Instruments in Chemical Industry
基金
国家"863"计划项目(2003AA412310)
关键词
故障诊断
数学模型
深层知识
定量与定性
SDG
fault diagnosis
mathematical model
deep knowledge
quantitative and qualitative
SDG
