粗糙集数据挖掘及其在汽轮机故障诊断中的应用

针对当前专家系统知识获取瓶颈的难题,提出了基于粗糙集数据挖掘的汽轮机故障预报及诊断方法。将汽轮机故障历史数据首先进行模糊化及离散化处理,然后构建故障诊断决策表,以决策表作为主要工具,即“知识库”,采用粗糙集数据挖掘方法直接从决策表中提取出潜在的诊断规则,为汽轮机提供有效的故障诊断。提出了基于粗集的分类规则学习和约简算法,实现了基于粗糙集数据挖掘的汽轮机故障预报及诊断系统,其诊断正确率达到了88%。实验表明该方法可行,对汽轮机故障预报及诊断系统的设计具有借鉴意义和深入研究的价值。

A Novel Approach for Fault Diagnosis of Steam Turbine Based on Rough Set Data Mining Theory

A novel approach for fault forecast and diagnosis of steam turbine based on rough set data mining theory is brought forward,aiming at overcoming shortages of some current knowledge attaining methods.The historical fault data of steam turbine is processed with fuzzy and scatter method.The processed data is used to structure the fault diagnosis decisionmaking table which is treated as "knowledge database".This paper introduces rough sets data mining method to take potential diagnosis rule from the fault diagnosis decisionmaking table of steam turbine.These rules can offer effective fault diagnosis service for steam turbine.The algorithm for classified rule learning and reducing is brought forward,and an experimental system for fault forecast and diagnosis of steam turbine based on rough set data mining theory is implemented.Their diagnosising precision is above 88%.Experiments prove that it is feasible to use the method to develop a system for fault forecast and diagnosis of steam turbine,which is valuable for further study in more depth.