多维度关联维数的电梯故障诊断  

Fault Diagnosis of Elevator by Using Multi-Dimension Correlation Dimensions

作　　者：周彬彬[1] 刘晓梅[1] 

机构地区：[1]华侨大学机电及自动化学院,福建厦门361021

出　　处：《机电工程技术》2014年第9期5-8,共4页Mechanical & Electrical Engineering Technology

基　　金：福建省自然科学基金资助项目(编号:2012J01213)

摘　　要：研究发现,通过低信噪比的实测数据得到的单一关联维数识别电梯的运行状态,是不全面的,易出现误判。这里提出以多维度关联维数联合判据作为识别依据,并以最小二乘支持向量机为识别方法。结果表明:多维度关联维数联合判据能够反映更加丰富的电梯动力学特性,识别准确度较高。The study found that using the single correlation dimension calculated from the vibration signal of elevator which is low signal-to-noise ratio, recognizes the running states of elevator. The resolution is not comprehensive enough and prone to miscarriage of justice. In this paper,we make the combined criterion of correlation dimension to multiple dimensions as recognition basis,and with the least square support vector machine method. The results show that the combined criterion reflects dynamic characteristic of elevator richer,and the recognition accuracy is relatively high.

关 键 词：电梯 故障诊断 关联维数 最小二乘支持向量机 信噪比 

分 类 号：TU857[建筑科学]