基于粗糙集的故障诊断方法

Approach for fault detection and diagnosis based on rough set

利用粗糙集理论对决策表进行约简以自动获取过程工业生产系统中的故障知识,从信息熵的角度分析系统知识不确定性的变化,提出了一种基于粗糙集理论的故障诊断新方法,研究了粗糙集理论在故障诊断中的适用性,在前向推理和反向推理的基础上,给出了针对故障点建立决策表以及利用粗糙集约简所获得的诊断规则进行正、反向故障诊断的步骤,讨论了这种故障诊断方法的诊断性能及其在计算上的复杂度.通过这种方法能够进行故障的寻找和定位,实例分析的结果说明了利用粗糙集进行知识发现及建立智能故障诊断系统的可行性和有效性.

Some work has been done for dealing with Fault Detection and Diagnosis (FDD) based on Rough Set, but in those cases Rough Set was just regarded as a tool for data cleaning, or for assisting other methods or for detecting whether a system has fault but usually cannot tell where it happened. To solve this problem, a new approach for FDD based on Rough Set is proposed. The applicability and computational complexity of this approach is discussed. Knowledge about a process control systems faults is obtained automatically by Rough Set value reduction, and an entropy-based criterion is used to measure its uncertainty. Methods of forward and backward fault diagnosis and how to build up decision tables for each fault source are given. The feasibility of forming a knowledge discovering and intelligent decision-making system for FDD based on Rough Set Theory is discussed through a case study.