基于传感量化融合的往复式压缩机故障诊断
|
摘要
往复式压缩机的机械组成部件复杂,机械零件之间的关联耦合性强,容易产生故障,为了提高往复式压缩机的故障检测能力,提出一种基于传感量化融合的往复式压缩机故障诊断方法。采用振动传感器、磁力传感器以及加速度传感器进行往复式压缩机工况数据采集,对采集的压缩机机械振动数据进行多传感量化融合处理,提取压缩机的机械振动特征信息,采用关联属性特征分解和故障特征挖掘方法,实现压缩机的故障状态监测和识别。仿真结果表明,采用该方法进行压缩机故障诊断的准确性较好,实时诊断能力较强,在压缩机等机械故障智能诊断检测中具有较好应用价值。
The mechanical components of reciprocating compressor are complex,the coupling between mechanical parts is strong,which is easy to cause trouble. In order to improve the fault detection ability of reciprocating compressor,a method for fault diagnosis of reciprocating compressor based on sensor quantization fusion is proposed,which uses vibration sensor,magnetic force sensor and acceleration sensor to collect data of reciprocating compressor. The mechanical vibration data of the compressor are processed by multi-sensor quantization fusion,and the mechanical vibration feature information of the compressor is extracted,and the associated attribute feature decomposition and fault feature mining method are adopted. The simulation results show that the method has good accuracy and real-time diagnosis ability. It has good application value in intelligent diagnosis and detection of mechanical faults such as compressors.
The mechanical components of reciprocating compressor are complex,the coupling between mechanical parts is strong,which is easy to cause trouble. In order to improve the fault detection ability of reciprocating compressor,a method for fault diagnosis of reciprocating compressor based on sensor quantization fusion is proposed,which uses vibration sensor,magnetic force sensor and acceleration sensor to collect data of reciprocating compressor. The mechanical vibration data of the compressor are processed by multi-sensor quantization fusion,and the mechanical vibration feature information of the compressor is extracted,and the associated attribute feature decomposition and fault feature mining method are adopted. The simulation results show that the method has good accuracy and real-time diagnosis ability. It has good application value in intelligent diagnosis and detection of mechanical faults such as compressors.
引文
[1]袁永,段奇智,张毅,等.油井数据采集及高效DLL函数数据传输性能实现[J].计算机与数字工程,2013,41(10):1628-1631,1635.
[2]杨俊,周丙寅,张毅,等.基于递归图分析的压缩机故障诊断方法研究[J].计算机与数字工程,2013,41(6):984-986.
[3]张毅,周丙寅,胡光波.井下直线电机泵故障检测仪硬件系统设计[J].计算机与数字工程,2012,40(11):162-166.
[4]张传锦,李璐璐.基于模糊C均值聚类的无线传感器网络节点定位算法[J].电子设计工程,2016,24(8):58-60,63.
[5]张毅,盛会平,胡光波.基于相空间重构和K-L变换的压缩机故障诊断[J].压缩机技术,2011(4):19-21.
[6]高志春,陈冠玮,胡光波,等.倾斜因子K均值优化数据聚类及故障诊断研究[J].计算机与数字工程,2014,42(1):14-18.
[7]刘聪,李颖晖,吴辰,等.基于鲁棒自适应滑模观测器的多故障重构[J].控制与决策,2016,31(7):1219-1224.
[8]赵威.强海水混响背景下水中兵器攻击目标检测研究[J].智能计算机与应用,2016,6(2):51-54.
[9]邱世卉.小波神经网络在模拟电路故障诊断中的应用研究[J].科学技术与工程,2012,12(30):8042-8046.
[10]罗洁思,于德介,彭富强.齿轮箱故障振动信号的阶比多尺度形态学解调[J].机械工程学报,2010,46(11):114-120,128.
[11]褚福磊,彭志科,冯志鹏,等.机械故障诊断中的现代信号处理方法[M].北京:科学出版社,2009.
[12]李兵,徐榕,贾春宁,等.基于自适应形态提升小波与改进非负矩阵分解的发动机故障诊断方法[J].兵工学报,2013,34(3):353-360.
[2]杨俊,周丙寅,张毅,等.基于递归图分析的压缩机故障诊断方法研究[J].计算机与数字工程,2013,41(6):984-986.
[3]张毅,周丙寅,胡光波.井下直线电机泵故障检测仪硬件系统设计[J].计算机与数字工程,2012,40(11):162-166.
[4]张传锦,李璐璐.基于模糊C均值聚类的无线传感器网络节点定位算法[J].电子设计工程,2016,24(8):58-60,63.
[5]张毅,盛会平,胡光波.基于相空间重构和K-L变换的压缩机故障诊断[J].压缩机技术,2011(4):19-21.
[6]高志春,陈冠玮,胡光波,等.倾斜因子K均值优化数据聚类及故障诊断研究[J].计算机与数字工程,2014,42(1):14-18.
[7]刘聪,李颖晖,吴辰,等.基于鲁棒自适应滑模观测器的多故障重构[J].控制与决策,2016,31(7):1219-1224.
[8]赵威.强海水混响背景下水中兵器攻击目标检测研究[J].智能计算机与应用,2016,6(2):51-54.
[9]邱世卉.小波神经网络在模拟电路故障诊断中的应用研究[J].科学技术与工程,2012,12(30):8042-8046.
[10]罗洁思,于德介,彭富强.齿轮箱故障振动信号的阶比多尺度形态学解调[J].机械工程学报,2010,46(11):114-120,128.
[11]褚福磊,彭志科,冯志鹏,等.机械故障诊断中的现代信号处理方法[M].北京:科学出版社,2009.
[12]李兵,徐榕,贾春宁,等.基于自适应形态提升小波与改进非负矩阵分解的发动机故障诊断方法[J].兵工学报,2013,34(3):353-360.