摘要
往复压缩机的故障诊断技术能够为工业生产提供有效保障,针对传统方法诊断准确率不高的问题,提出了一种基于振动信号时频图像灰度共生矩阵-方向梯度直方图(GLCM-HOG)特征融合的往复压缩机故障诊断方法。首先,采用小波变换的方法处理往复压缩机的振动信号,生成时频图像;其次,利用灰度共生矩阵(GLCM)和方向梯度直方图(HOG)的方法提取时频图像特征,融合构建GLCM-HOG特征;最后,将融合特征输入支持向量机(SVM)进行分类,以判别往复压缩机的运行状态。实验结果表明,所提方法对设备的状态识别准确率可以达到92.33%,能够实现往复压缩机的准确诊断。
The fault diagnosis technology of reciprocating compressor can provide an effective guarantee for industrial production. Due to the low recognition accuracy of the traditional method, a fault diagnosis method of reciprocating compressor based on the time-frequency image(gray level co-occurrence matrix-histogram of oriented gradient, GLCM-HOG) features fusion of vibration signal was proposed. Firstly, the vibration signals of reciprocating compressor were processed by wavelet transform to generate time-frequency images. Secondly, GLCM features and HOG features were respectively extracted from the time-frequency images and fused. Finally, the GLCM-HOG features were input into support vector machine(SVM) to determine the state of the reciprocating compressor. The experimental results show that the accuracy rate can reach 92.33%, and the proposed method can accurately realize fault diagnosis for reciprocating compressor.
作者
李辉
茆志伟
张进杰
江志农
黄翼飞
LI Hui;MAO Zhi-wei;ZHANG Jin-jie;JIANG Zhi-nong;HUANG Yi-fei(Beijing Key Lab of Health Monitoring Control and Fault Self-recovery for High-end Machinery,Beijing University of Chemical Technology,Beijing 100029,China;Anhui Provincial Lab of Compressor Technology,State Key Lab of Compressor Technology,Hefei 230031,China;Beijing Bohua Anchuang Technology Co.,Ltd.,Beijing 101399,China)
出处
《科学技术与工程》
北大核心
2021年第10期4030-4035,共6页
Science Technology and Engineering
基金
压缩机技术安徽省实验室开放基金(SKL-YSJ201811)
北京化工大学双一流建设专项经费(ZD1601)。
关键词
往复压缩机
振动信号
时频图像
特征提取
故障诊断
reciprocating compressor
vibration signal
time-frequency image
feature extraction
fault diagnosis
作者简介
第一作者:李辉(1998-),男,汉族,江西抚州人,硕士研究生。研究方向:设备故障诊断。E-mail:lihui13135@163.com;通信作者:茆志伟(1990-),男,汉族,安徽亳州人,博士,助理研究员。研究方向:设备故障诊断。E-mail:maozw1990@126.com。
