张旭东;张进杰;茆志伟;
ZHANG Xudong;ZHANG Jinjie;MAO Zhiwei;Beijing Key Laboratory of Health Monitoring Control and Fault Self-recovery for High-end Machinery Beijing University of Chemical Technology;Compressor Health and Intelligent Monitoring Center of National Key Laboratory of Compressor Technology,Beijing University of Chemical Technology;

• 1:北京化工大学高端机械装备健康监控与自愈化北京市重点实验室
• 2:北京化工大学压缩机技术国家重点实验室压缩机健康智能监控中心

摘要(Abstract)：

往复压缩机的故障诊断一直以来都是研究工作的重点问题,对其关键运动部件的监测诊断更是研究的热点之一。当往复压缩机发生运动部件磨损、撞缸等故障时,活塞杆的运行状态会发生改变,进而引起活塞杆轴心轨迹的变化。因此,提出了一种基于活塞杆轴心轨迹的往复压缩机智能诊断方法。首先,文章利用改进的离散点轮廓包络方法提取活塞杆轴心轨迹特征,同时提取活塞杆信号的时、频域特征;然后利用ReliefF方法计算轴心轨迹特征与时、频域特征的特征权重,选取大于各自权重均值的特征分别组成轴心轨迹敏感特征集和时频域敏感特征集;最后,提取2个特征集的Related-Similar(RS)特征,将其融合后作为BP神经网络的训练特征集训练故障诊断模型。利用往复压缩机磨损故障和撞缸故障的数据对模型进行验证,结果表明,模型能较好地识别这两种故障,并且故障恶化时的识别准确率均达到了99%以上。
The fault diagnosis of reciprocating compressors has always been the focus of research,and the monitoring and diagnosis of its core moving parts is one of the research hotspots.When the moving parts of the reciprocating compressor are worn out and collide with the cylinder,the operating state of the piston rod will change,which in turn will cause the change of the axial trajectory of the piston rod.Therefore,An intelligent diagnosis method for reciprocating compressors is proposed based on the axial trajectory of the piston rod.Firstly,in the present study,the improved discrete point contour envelope method was used to extract the piston rod axis trajectory features,and extract the piston rod signal time and frequency domain features as well;Secondly,the ReliefF method was used to calculate the feature weights of the axis trajectory feature and the time and frequency domain feature.Furthermore,the feature greater than the average of their respective weight was selected to form the axis trajectory sensitive feature set and the time-frequency domain sensitive feature set;Finally,the Related-Similar(RS) features of the two feature sets were extracted,and the fusion was used as the training feature set of the BP neural network to train the fault diagnosis model.The wear fault and the cylinder collision data of the reciprocating compressor were used to verify the model.The results show that the model could better identify these two faults,and the recognition accuracy rate when the fault deteriorates achieved more than 99%.

关键词(KeyWords)： 轴心轨迹;智能诊断;活塞杆;往复压缩机;特征融合
axis trajectory;intelligent diagnosis;piston rod;reciprocating compressor;feature fusion

Abstract:

Keywords:

基金项目(Foundation): 双一流建设专项经费资助项目(ZD1601);; 压缩机技术国家重点实验室(压缩机技术安徽省实验室)开放基金资助项目(SKL-YSJ201808,SKL-YSJ201911)

作者(Authors): 张旭东;张进杰;茆志伟;
ZHANG Xudong;ZHANG Jinjie;MAO Zhiwei;Beijing Key Laboratory of Health Monitoring Control and Fault Self-recovery for High-end Machinery Beijing University of Chemical Technology;Compressor Health and Intelligent Monitoring Center of National Key Laboratory of Compressor Technology,Beijing University of Chemical Technology;

参考文献(References)：

• [1]张雷.状态监测诊断系统在往复压缩机的诊断及应用[J].通用机械，2014(7)：60-63.ZHANG L.Diagnosis and application of condition monitoring and diagnosis system in reciprocating compressor[J].General Machinery，2014(7)：60-63.
• [2]唐友福，林峰，邹龙庆.基于LMD多尺度熵和LSSVM的往复压缩机故障诊断方法研究[J].压缩机技术，2018(4)：1-7.TANG Y F，LIN F，ZOU L Q.Research on the fault diagnosis method for reciprocating compressor based on LMD，MSE and LSSVM[J].Compressor Technology，2018(4)：1-7.
• [3]李晓博，江志农，佟艳宾，等.基于活塞杆沉降位移信号的活塞杆断裂故障诊断方法的研究[J].流体机械，2017，45(9)：45-48.LI X B，JIANG Z N，TONG Y B，et al.Research on fault diagnosis method of the piston rod fracture based on the piston rod displacement signal of reciprocating compressor[J].Fluid Machinery，2017，45(9)：45-48.
• [4]王庆锋，董良遇，张赟新，等.一种基于活塞杆动态能量指数的故障监测诊断方法[J].流体机械，2016，44(9)：47-52.WANG Q F，DONG L Y，ZHANG Y X，et al.Study on fault diagnosis methods based on dynamic energy index of piston rod[J].Fluid Machinery，2016，44(9)：47-52.
• [5]马晋，江志农，高金吉.基于活塞杆轴心位置轨迹的往复压缩机故障诊断技术研究[J].振动工程学报，2012，25(4)：453-459.MA J，JIANG Z N，GAO J J.A reciprocating compressor fault diagnosis method based on piston rod axis orbit[J].Journal of Vibration Engineering，2012，25(4)：453-459.
• [6]XIAO S，ZHANG H，LIU S，et al.Dynamic behavior analysis of reciprocating compressor with subsidence fault considering flexible piston rod[J].Journal of Mechanical Science and Technology，2018，32(9)：4103-4124.
• [7]ALMASI A.Piston rod load analysis of process reciprocating machines[J].Proceedings of the Institution of Mechanical Engineers，Part E：Journal of Process Mechanical Engineering，2010，224(1)：59-62.
• [8]JIANG Z N，ZHU L N，ZHANG J J，et al.Research on fault diagnosis method of piston rod based on harmonic wavelet and manifold learning[J].High Technology Letters，2018，24(3)：232-240.
• [9]李兴球，姜洪开，王瑞欣，等.基于迁移深度降噪自动编码器的飞机关键机械部件故障诊断方法[C]//第十三届全国振动理论及应用学术会议论文集，2019：253-258.LI X Q，JIANG H K，WANG R X，et al.Deep transfer denoising autoencoder for aircraft key mechanical component fault diagnosis[C]//Proceedings of the 13th National Conference on Vibration Theory and Application，2019：253-258.
• [10]杨洪柏，聂昂，张江安，等.基于原始振动信号的往复压缩机卷积神经网络故障诊断[J].机械设计与制造工程，2018，47(9)：67-70.YANG H B，NIE A，ZHANG J G，et al.The fault diagnosis of reciprocating compressor based on convolutional neural network with raw vibration signal[J].Mechanical Design and Manufacturing Engineering，2018，47(9)：67-70.
• [11]张谦，舒悦，王乐，等.往复压缩机故障诊断方法研究概述[J].流体机械，2018，46(3)：37-41.ZHANG Q，SHU Y，WANG L，et al.Research on fault diagnosis method of reciprocating compressors[J].Fluid Machinery，2018，46(3)：37-41.
• [12]陈涛，李光耀.平面离散点集的边界搜索算法[J].计算机仿真，2004(3)：21-23.CHEN T，LI G Y.A Boundary searching algorithm for planar scatter data points[J].Computer Simulation，2004(3)：21-23.
• [13]何小高，张庆，贾林山，等.变速重载设备齿轮箱轴承故障的改进阶次包络分析方法[J].西安交通大学学报，2019，53(8)：98-106.HE X G，ZHANG Q，JIA L S，et al.Improved order envelope analysis method for gear box bearing faults of variable speed and heavy load equipment[J].Journal of Xi'an Jiaotong University，2019，53(8)：98-106.
• [14]张进杰，祁桢，赵岩，等.基于小头瓦润滑EHD模型的变工况运行往复压缩机连杆动力学分析[J].流体机械，2020，48(3)：35-41.ZHANG J J，QI Z，ZHAO Y.Dynamic analysis of connecting rod of reciprocating compressor under variable working conditions based on EHD model of small-head lubrication[J].Fluid Machinery，2020，48(3)：35-41.
• [15]陈华，李戈，杨亚星，等.热泵空调系统中相变蓄热特性及系统性能试验研究[J].流体机械，2019，47(9)：72-77.CHEN H，LI G，YANG Y X，et al.Experimental study on phase change heat storage characteristics and system performance of heat pump air-conditioning system[J].Fluid Machinery，2019，47(9)：72-77.
• [16]李婷婷，黄翔，耿志超.送风方式对热通道封闭数据中心热环境影响的模拟研究[J].流体机械，2019，47(6)：62-67.LI T T，HUANG X，GENG Z C.Simulation research on effect of air supply method on thermal environment of hot aisle contained data center[J].Fluid Machinery，2019，47(6)：62-67.
• [17]马燕，臧润清，张秋玉.双蒸发管组冷风机重力再循环供液的试验研究[J].流体机械，2019，47(5)：65-69.MA Y，ZANG R Q，ZHANG Q Y.Experimental study on gravity-recirculation with air cooler of double evaporation tube groups[J].Fluid Machinery，2019，47(5)：65-69.
• [18]范金波，安佳鑫，王雨，等.NFC复合梨汁的配方筛选及贮藏品质变化研究[J].包装与食品机械，2020，38(1)：8-13.FAN J B，AN J X，WANG Y，et al.Preparation of NFC compound fruit and vegetable juice and its quality change during storage[J].Packaging and Food Machinery，2020，38(1)：8-13.
• [19]覃慧丽.气相色谱-串联质谱法测定茶叶中草甘膦残留量的不确定度评定[J].包装与食品机械，2019，37(3)：65-69.QIN H L.Analysis on determination uncertainty of glyphosate residue in tea by GC-MS method[J].Packaging and Food Machinery，2019，37(3)：65-69.
• [20]GUO L，LI N，JIA F，et al.A recurrent neural network based health indicator for remaining useful life prediction of bearings[J].Neurocomputing，2017，240(May31)：98-109.