粗糙集和遗传算法集成的故障诊断知识获取

Knowledge Acquisition for Fault Diagnosis Based on the Integration of Genetic Algorithm and Rough Set

在分析智能故障诊断方法的基础上,提出了粗糙集和遗传算法集成的策略,进而给出了该方法的知识获取模型.该模型首先将粗糙集理论引入到故障诊断特征提取中,用于解决实际故障诊断数据样本分类边界不确定问题,接下来采用优化能力较好的遗传算法进行故障规则获取.通过实例验证表明:在有效保持故障诊断分类结果的情况下,该方法可以提取出最能反映故障的特征.

An integrated strategy of rough set and genetic arithmetic was proposed on the base of analyzing the method of fault diagnosis, and the model for knowledge acquired of this strategy was established. This model introduced rough set theory into feature selection for fault diagnosis, which could solve the problem that the classification boundary of real fault diagnosis data sets is often ambiguous. Then genetic arithmetic was used for extraction the rules of fault diagnosis. By a fault diagnosis example, this paper validated the method. The result shows that this method can efficiently extract the main fault features while the fault classification result is invariable.