摘要
模糊自适应共振理论(fuzzy adaptive resonance theory,简称Fuzzy ART)已被广泛应用于机械设备实时监控和故障诊断。Fuzzy ART采用只允许一个获胜节点学习的硬竞争学习机制,导致系统极易产生误判。针对此问题,将Yu范数相似度准则、生物侧抑制理论与Fuzzy ART相结合,建立了允许多个获胜节点学习的软竞争ART(简称Soft-ART)算法。为了提高故障诊断精度,运用Yu范数相似度测度改进了基于距离测度的特征参数选择方法。利用轴承故障诊断数据对特征选择算法及Soft-ART算法进行了检验,并与FCM,BP及Fuzzy ART算法进行了对比。结果表明,该Soft-ART算法具有更高的诊断精度,同时说明了特征选择算法的有效性。
Adaptive resonance theory(ART)is widely used in real time monitoring and fault diagnosis of mechanical equipment.Traditional ART adopts hard competitive learning mechanism always leads to erroneous when only one winning node is allowed to be learned.In the light of this problem,the Yu′s norm similarity criterion,the lateral inhibition theory and fuzzy ART are combined to establish a soft-competitive learning ART(Soft-ART)mode,which allows multiple winning nodes to be learned.To improve the diagnosis success rate,an improved feature selection technique based on Yu′s similarity criterion is also proposed.Moreover,the feature selection technique and proposed Soft-ART mode are tested by bearing fault data.Compared with FCM,BP and Fuzzy ART,the Soft-ART has a higher diagnostic precision.
作者
李清蕾
万小金
徐增丙
王凯
赵乾坤
LI Qinglei;WAN Xiaojin;XU Zengbing;WANG Kai;ZHAO Qiankun(Hubei Key Laboratory of Advanced Technology for Automotive Components,Wuhan University of Technology Wuhan,430070,China;Hubei Collaborative Innovation Center for Automotive Components Technology,Wuhan University of Technology Wuhan,430070,China;College of Machinery and Automation,Wuhan University of Science and Technology Wuhan,430070,China)
出处
《振动．测试与诊断》
EI
CSCD
北大核心
2018年第6期1199-1204,1294,共7页
Journal of Vibration,Measurement & Diagnosis
基金
国家自然科学基金资助项目(51405353
51575417)
关键词
故障诊断
自适应共振理论
软竞争学习
特征选择
fault diagnosis
adaptive resonance theory
soft competitive learning
feature selection
