电子测量与仪器学报

张旭,黄亦翔,张旭东,刘成良,肖登宇,单增海.基于Kullback Leibler距离的起重机回转系统健康评估[J].电子测量与仪器学报,2021,35(2):25-32

基于Kullback Leibler距离的起重机回转系统健康评估

Kullback Leibler distance based health performance evaluation for rotary system of crane truck

DOI：

中文关键词: 回转系统拉普拉斯特征映射核密度估计 Kullback Leibler距离信号融合性能评估

英文关键词:rotary system Laplacian eigenmaps kernel density estimation Kullback Leibler distance signal fusion performance evaluation

基金项目:国家重点研发计划 (2017YFB1302004)、国家自然科学基金 (51975356)项目资助

作者	单位
张旭	1上海交通大学机械系统与振动国家重点实验室上海200240；
黄亦翔	1上海交通大学机械系统与振动国家重点实验室上海200240；
张旭东	1上海交通大学机械系统与振动国家重点实验室上海200240；
刘成良	1上海交通大学机械系统与振动国家重点实验室上海200240；
肖登宇	1上海交通大学机械系统与振动国家重点实验室上海200240；
单增海	2徐工重型机械有限公司高端工程机械智能制造国家重点实验室徐州221004

Author	Institution
Zhang Xu	1State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200240, China;
Huang Yixiang	1State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200241, China;
Zhang Xudong	1State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200242, China;
Liu Chengliang	1State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200243, China;
Xiao Dengyu	1State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200244, China;
Shan Zenghai	2Xuzhou Heavy Machinery Limited Company and State Key Laboratory of Advanced Manufacturing Machinery Intelligent Manufacturing, Xuzhou 221004, China

摘要点击次数: 1417

全文下载次数: 4

中文摘要:

针对实时工况下起重机回转系统整体健康状况难以评估的问题，研究基于拉普拉斯映射与Kullback Leibler距离结合的回转系统整体健康评估方法。在采集回转系统的多维信号后，使用随机森林和拉普拉斯映射对信号进行降噪降维，然后结合回转系统工作原理，利用高斯核密度估计表征回转系统健康性能，最后通过概率密度计算不同回转系统之间的Kullback Leibler距离，实现回转系统健康性能的评估。试验结果表明，该方法能避免数据中的噪声干扰，健康评估结果与专家评估结果相一致。

英文摘要:

Aiming at the problem that it is difficult to evaluate the overall health status of the crane rotary system under real time conditions, a health evaluation method for the rotary system combining Laplacian Eigenmaps and Kullback Leibler distance is proposed. After collecting the multi dimensional signal of rotary system, the Laplacian eigenmaps and Random Forest are used to reduce noise and dimensionality of the signal. Then combined with the working principle of the rotary system, the health performance of the rotary system is characterized by Gaussian kernel density estimation. The Kullback Leibler distance between different rotary system is calculated by probability density to characterize the health performance of the rotary system. The test results show that this method can avoid the noise interference of the original data and the health assessment results of the rotary system are consistent with the expert assessment results.

查看全文查看/发表评论下载PDF阅读器