基于Gabor小波变换和多核支持向量机的电梯导靴故障诊断方法  

Elevator Boot Fault Diagnosis Method Based on Gabor Wavelet Transform and Multi-core Support Vector Machine

作　　者：朱晓玲 李琨[1] 张长胜[1] 杜付鑫[2] ZHU Xiao-ling;LI Kun;ZHANG Chang-sheng;DU Fu-xin(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650504,China;School of Mechanical Engineering,Shandong University,Jinan 250061,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,昆明650504 [2]山东大学机械工程学院,济南250061

出　　处：《计算机科学》2020年第12期258-261,共4页Computer Science

基　　金：国家自然科学基金(51705289)。

摘　　要：电梯导靴作为电梯轿厢的重要组成部分,对电梯的安全问题具有直接的影响。为了对电梯导靴故障进行更加准确的综合诊断,提出了一种基于Gabor小波变换和多核支持向量机的诊断方法。首先,通过加速度传感器采集设备主体的振动信号,并利用经验模态分解得到固有模态函数分量。然后,采用Gabor滤波器对低频分量进行滤波去噪,以使提取低频率上数据的特征。最后,采用权重的方式将局部和全局的核函数进行线性相加,组成多核支持向量机对数据进行分类。实验结果验证了所提方法的有效性,相比基于小波变换-最小二乘支持向量机的故障诊断方法,所提方法的故障诊断准确率提高了约5%,达到了87.6%。As an important part of the elevator car,the elevator boot has a direct impact on the safety of the elevator.In order to make a more accurate comprehensive diagnosis of the elevator boot failure,a diagnosis method based on Gabor wavelet transform and multi-core support vector machine is proposed.First,the vibration signal of the main body of the device is collected by an acceleration sensor,and the eigenmode function component is obtained by empirical mode decomposition.Then,a Gabor filter is used to filter and denoise the low frequency components to achieve the feature enhancement of the extracted data at low frequencies.Finally,the local and global kernel functions are linearly added using weights to form a multi-core support vector machine to classify the data.Experimental results verify the effectiveness of the proposed method.Compared with the fault diagnosis method based on wavelet transform and least squares support vector machine,the fault diagnosis accuracy of the proposed method is improved by about 5%,reaching 87.6%.

关 键 词：电梯导靴 故障诊断 GABOR小波 多核支持向量机 经验模态分解 

分 类 号：TU857[建筑科学]