针对城轨列车的滚动轴承故障诊断问题,提出了一种经验模态分解(E M D,E m p i r i c a l Mode Deco-mposition)与支持向量机(SVM,Support Vector Machine)相结合的故障诊断方法。对采集到的振动信号进行小波消噪,利用经验模态分解将振...针对城轨列车的滚动轴承故障诊断问题,提出了一种经验模态分解(E M D,E m p i r i c a l Mode Deco-mposition)与支持向量机(SVM,Support Vector Machine)相结合的故障诊断方法。对采集到的振动信号进行小波消噪,利用经验模态分解将振动信号分解为一组本征模态函数(IMF,Intrinsic Mode Functions),并计算其能量从而获得信号的特征向量。采用支持向量机实现了滚动轴承故障分类。实验结果表明,本文提出的方法能够准确有效地识别城轨列车滚动轴承的工作状态和故障类型。展开更多
将安全域的思想引入滚动轴承的状态监测中,综合利用局部均值分解(Local Mean Decomposition,LMD)、主成分分析(Principal Component Analysis,PCA)和最小二乘支持向量机(Least Square Support Vector Machine,LSSVM),进行了滚动轴承运...将安全域的思想引入滚动轴承的状态监测中,综合利用局部均值分解(Local Mean Decomposition,LMD)、主成分分析(Principal Component Analysis,PCA)和最小二乘支持向量机(Least Square Support Vector Machine,LSSVM),进行了滚动轴承运行状态的安全域估计以及正常和各种故障状态的辨识。首先,按一定的时间间隔将采集正常及各种故障状态的振动数据进行分段,每段数据进行LMD后获得各乘积函数分量;其次,基于各段数据的乘积函数分量,利用PCA提取出每段数据的T2和SPE统计量控制限值作为滚动轴承的状态特征量;最后,利用二分类的LSSVM进行滚动轴承运行状态的安全域估计,利用多分类LSSVM进行滚动轴承的正常以及滚动体、内圈、外圈故障四种状态的辨识。试验结果显示安全域估计和多种状态辨识的准确率均较高,验证了本文方法的有效性。展开更多
An approach to identify interpretable fuzzy models from data is proposed. Interpretability, which is one of the most important features of fuzzy models, is analyzed first. The number of fuzzy rules is determined by fu...An approach to identify interpretable fuzzy models from data is proposed. Interpretability, which is one of the most important features of fuzzy models, is analyzed first. The number of fuzzy rules is determined by fuzzy cluster validity indices. A modified fuzzy clustering algorithm,combined with the least square method, is used to identify the initial fuzzy model. An orthogonal least square algorithm and a method of merging similar fuzzy sets are then used to remove the redundancy of the fuzzy model and improve its interpretability. Next, in order to attain high accuracy, while preserving interpretability, a constrained Levenberg-Marquardt method is utilized to optimize the precision of the fuzzy model. Finally, the proposed approach is applied to a PH neutralization process, and the results show its validity.展开更多
文摘针对城轨列车的滚动轴承故障诊断问题,提出了一种经验模态分解(E M D,E m p i r i c a l Mode Deco-mposition)与支持向量机(SVM,Support Vector Machine)相结合的故障诊断方法。对采集到的振动信号进行小波消噪,利用经验模态分解将振动信号分解为一组本征模态函数(IMF,Intrinsic Mode Functions),并计算其能量从而获得信号的特征向量。采用支持向量机实现了滚动轴承故障分类。实验结果表明,本文提出的方法能够准确有效地识别城轨列车滚动轴承的工作状态和故障类型。
文摘将安全域的思想引入滚动轴承的状态监测中,综合利用局部均值分解(Local Mean Decomposition,LMD)、主成分分析(Principal Component Analysis,PCA)和最小二乘支持向量机(Least Square Support Vector Machine,LSSVM),进行了滚动轴承运行状态的安全域估计以及正常和各种故障状态的辨识。首先,按一定的时间间隔将采集正常及各种故障状态的振动数据进行分段,每段数据进行LMD后获得各乘积函数分量;其次,基于各段数据的乘积函数分量,利用PCA提取出每段数据的T2和SPE统计量控制限值作为滚动轴承的状态特征量;最后,利用二分类的LSSVM进行滚动轴承运行状态的安全域估计,利用多分类LSSVM进行滚动轴承的正常以及滚动体、内圈、外圈故障四种状态的辨识。试验结果显示安全域估计和多种状态辨识的准确率均较高,验证了本文方法的有效性。
基金国家自然科学基金，Scientific Research Foundation of Nanjing University of Science and Technology
文摘An approach to identify interpretable fuzzy models from data is proposed. Interpretability, which is one of the most important features of fuzzy models, is analyzed first. The number of fuzzy rules is determined by fuzzy cluster validity indices. A modified fuzzy clustering algorithm,combined with the least square method, is used to identify the initial fuzzy model. An orthogonal least square algorithm and a method of merging similar fuzzy sets are then used to remove the redundancy of the fuzzy model and improve its interpretability. Next, in order to attain high accuracy, while preserving interpretability, a constrained Levenberg-Marquardt method is utilized to optimize the precision of the fuzzy model. Finally, the proposed approach is applied to a PH neutralization process, and the results show its validity.
