摘要
针对轴承故障检测算法特征分辨性较低、准确度较低等问题,提出一种融合Morlet小波和遗传算法优化的多模态核方法轴承故障检测算法.该算法首先针对原始轴承故障信号提取多个尺度和多个位移条件下的Morlet小波变换特征,然后设计一个多模态核方法,包含线性核函数与径向基(RBF)核函数,最后在支持向量机(SVM)训练过程中采用遗传算法(GA)优化多模态核的参数,使用最优化多模态核进行轴承故障检测.在UoCn的智能维护中心数据集上分别测试了滚珠故障、内圈裂纹故障和外圈裂纹故障的检测,并对单一核与多模态核间的错误率与效率进行对比.实验结果表明,改进算法能获得鲁棒的轴承故障检测特征,且多模态核在GA的优化下能快速收敛,获得最优化结果,通过牺牲少量的时间效率而极大提升了轴承故障检测准确率.
The author proposed a bearing fault detection algorithm based on Morlet wavelet and multi- mode kernel optimized by genetic algorithm. Firstly, the algorithm extracted the characteristics of Morlet wavelet transform under conditions of multi-scale and multiple displacement for the fault signal of original bearing. Secondly, the author designed a multi-mode kernel method, including linear kernel and radical basis function （RBF） kernel. Finally, the genetic algorithm （GA） was used to optimize parameters of multi-mode kernel in the support vector machine （SVM） training process, and the optimizing multi-mode kernel for bearing fault detection was carried out. The ball fault, inner ring crack fault and outer ring crack fault were tested on the data set of UoCn intelligent maintenance center, and the error rate and efficiency of single-mode kernel and multi-mode kernel were compared. The experimental results show that the improved algorithm can get the robust features for bearing fault detection, and the multi-mode kernel can converge quickly and get optimal results under the optimization of GA, the accuracy of hearing fault detection is greatly improved by sacrificing a small amount of time efficiency.
出处
《吉林大学学报（理学版）》
CAS
CSCD
北大核心
2018年第1期101-108,共8页
Journal of Jilin University:Science Edition
基金
国家自然科学基金青年基金(批准号:51307003)
关键词
轴承故障检测
Morlet小波变换
多模态核方法
遗传算法
支持向量机
hearing fault detection
Morlet wavelet transform
multi-mode kernel method
genetic algorithm （GA）
support vector machine （SVM）
作者简介
杨琦（1983-），男，汉族，硕士，实验师，从事计算机辅助设计与制造、机械制造技术和创新创业教育的研究，E-mail：80310279@qq．com．
