基于PSO-FC优化KPCA的特征提取及行星齿轮磨损损伤程度识别
|
摘要
行星齿轮传动系统发生故障时,其信号传递中相互耦合,呈现非线性的特性,使得行星齿轮的故障类型及损伤程度难以识别。借鉴模式识别中Fisher准则(FC)判别函数,构建核函数尺度参数优化的数学模型,应用改进的粒子群优化方法对其寻优,充分改善核主元分析法(KPCA)对于非线性问题的分析性能,将其应用于行星齿轮的磨损损伤程度的识别和诊断中。实例分析结果表明,基于PSO-FC智能优化后的KPCA改善了特征空间内数据分布结构,在行星齿轮的磨损损伤程度识别中取得了较好的尺度聚类效果,可以有效地解决复杂机械传动中损伤边界模糊、损伤程度难以识别的问题。
When the planetary gear transmission system fails,its signal transmission is coupled witheach other,and the nonlinear characteristic is presented,which makes the fault type and damage degree ofthe planetary gear to be difficultly recognized. The optimization mathematical model of the kernel functionscale parameter is constructed by means of Fisher criterion(FC)discriminate function in pattern recognition,and the improved particle swarm optimization method is applied to the optimization to fully improve the analy-sis performance of the kernel principal component analysis(KPCA)for nonlinear problem. It is applied to theidentification and diagnosis of wear damage degree of planetary gear. The results of example analysis show thatthe intelligently optimized KPCA based on PSO-FC have improve the structure distribution of data in the fea-ture space and achieved the good scale clustering effect in planetary gear wear damage degree recognition. Itcan effectively solve the identify problems of complex fuzzy damage boundary and damage degree in the me-chanical transmission.
When the planetary gear transmission system fails,its signal transmission is coupled witheach other,and the nonlinear characteristic is presented,which makes the fault type and damage degree ofthe planetary gear to be difficultly recognized. The optimization mathematical model of the kernel functionscale parameter is constructed by means of Fisher criterion(FC)discriminate function in pattern recognition,and the improved particle swarm optimization method is applied to the optimization to fully improve the analy-sis performance of the kernel principal component analysis(KPCA)for nonlinear problem. It is applied to theidentification and diagnosis of wear damage degree of planetary gear. The results of example analysis show thatthe intelligently optimized KPCA based on PSO-FC have improve the structure distribution of data in the fea-ture space and achieved the good scale clustering effect in planetary gear wear damage degree recognition. Itcan effectively solve the identify problems of complex fuzzy damage boundary and damage degree in the me-chanical transmission.
引文
[1]孙灿飞,王友仁.直升机行星传动轮系故障诊断研究进展[J].航空学报,2017,38(7):1-13.
[2]LEI Yaguo,LIN Jing,ZUO M J,et al.Condition monitoring and fault diagnosis of planetary gearboxes:a review[J].Measurement,2014,48:292-305.
[3]LIANG Xihui,ZUO M J,FENG Zhipeng.Dynamic modeling of gearbox faults:a review[J].Mechanical Systems and Signal Processing,2018,98:852-876.
[4]KHAZAEE M,AHMADI H,OMID H,et al.An appropriate approach for condition monitoring of planetary gearbox based on fast Fourier transform and least-square support vector machine[J].International Journal of Multidisciplinary Sciences and Engineering,2012,3:22-26.
[5]LIU Z L,QU J,ZUO M J,et al.Fault level diagnosis for planetary gearboxes using hybrid kernel feature selection and kernel Fisher discriminant analysis[J].International Journal of Advanced Manufacturing Technology,2013,67:1217-1230.
[6]邵晴.粒子群算法研究及其工程应用案例[D].长春:吉林大学,2017:14.
[7]魏秀业.基于粒子群优化的齿轮箱故障诊断研究[D].太原:中北大学,2009:5-6,23,27.
[8]VO H X,DURLOFSKY L J.Regularized kernel PCA for the efficient parameterization of complex geological models[J].Journal of Computational Physics,2016,322:859-881.
[9]赵宇明,熊慧霖,周越,等.模式识别[M].上海:上海交通大学出版社,2013:13-15,73-75.
[2]LEI Yaguo,LIN Jing,ZUO M J,et al.Condition monitoring and fault diagnosis of planetary gearboxes:a review[J].Measurement,2014,48:292-305.
[3]LIANG Xihui,ZUO M J,FENG Zhipeng.Dynamic modeling of gearbox faults:a review[J].Mechanical Systems and Signal Processing,2018,98:852-876.
[4]KHAZAEE M,AHMADI H,OMID H,et al.An appropriate approach for condition monitoring of planetary gearbox based on fast Fourier transform and least-square support vector machine[J].International Journal of Multidisciplinary Sciences and Engineering,2012,3:22-26.
[5]LIU Z L,QU J,ZUO M J,et al.Fault level diagnosis for planetary gearboxes using hybrid kernel feature selection and kernel Fisher discriminant analysis[J].International Journal of Advanced Manufacturing Technology,2013,67:1217-1230.
[6]邵晴.粒子群算法研究及其工程应用案例[D].长春:吉林大学,2017:14.
[7]魏秀业.基于粒子群优化的齿轮箱故障诊断研究[D].太原:中北大学,2009:5-6,23,27.
[8]VO H X,DURLOFSKY L J.Regularized kernel PCA for the efficient parameterization of complex geological models[J].Journal of Computational Physics,2016,322:859-881.
[9]赵宇明,熊慧霖,周越,等.模式识别[M].上海:上海交通大学出版社,2013:13-15,73-75.