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

作　　者：张旭[1] 黄亦翔[1] 张旭东 刘成良[1] 肖登宇 单增海 Zhang Xu;Huang Yixiang;Zhang Xudong;Liu Chengliang;Xiao Dengyu;Shan Zenghai(State Key Laboratory of Mechanical System and Vibration,Shanghai Jiao Tong University,Shanghai 200240,China;Xuzhou Heavy Machinery Limited Company and State Key Laboratory of Advanced Manufacturing Machinery Intelligent Manufacturing,Xuzhou 221004,China)

机构地区：[1]上海交通大学机械系统与振动国家重点实验室,上海200240 [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

出　　处：《电子测量与仪器学报》2021年第2期25-32,共8页Journal of Electronic Measurement and Instrumentation

基　　金：国家重点研发计划(2017YFB1302004);国家自然科学基金(51975356)项目资助。

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。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.

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 

分 类 号：TH17[机械工程—机械制造及自动化] TN9[电子电信—信息与通信工程]