摘要
根据旋转机械实时故障诊断的实际需求,引入粗糙集理论中的决策模型,作为典型故障诊断规则的发现工具。并针对故障信号的非平稳性和诊断分析的实时性要求,采用小波包分析(WPA)作为现场数据的频域段特征的提取工具。并首次将小波包分析(WPA)与粗糙集理论的决策模型相结合,提出了适应于现代机械设备在线诊断的故障分析模型WRS。并通过实例,验证了全过程。
In this paper, the decision model in rough set theory is introduced as the rule generating tool for the typical faults for rotating mechanical devices, according to the real-time fau）t diagnosis for this kind of devices. To solve the non- stability of the fault signals, the Wavelet Packet Analysis （WPA） is employed as an effective direct abstracting tool for the frequency segments features of the field signal. And on this basis, the two theoretical tools-rough set and wavelet packet analysis-are integrated into a new fault analysis model especially fitting the on-line fault analysis and diagnosis for modern mechanical devices. Finally, a factual case is studied to prove the whole fault analysis and diagnosis process.
出处
《制造业自动化》
北大核心
2006年第12期23-26,共4页
Manufacturing Automation
基金
上海市高等学校科学技术发展基金(0401305)
关键词
粗糙集
小波包分析
故障诊断
规则生成
rough set
Wavelet Packet Analysis
fault diagnosis
rule generation
