基于遗传算法和BP神经网络的多联机阀类故障诊断
|
摘要
针对多联机系统(变制冷剂流量系统)阀类故障的诊断特征变量冗杂、诊断效率低的问题,提出一种复合诊断模型,利用遗传算法在原始特征集中搜索特征子集,与参数优化后的BP神经网络模型结合,对多联机阀类故障进行检测和诊断。本文从原始特征集中优化选择了带有18个特征变量的最优特征子集,用该模型对电子膨胀阀卡死、电子膨胀阀泄漏和四通阀故障3种故障进行检测,结果表明:该复合诊断模型对故障检测率提高,其中电子膨胀阀的卡死故障检测率提升8%,整体诊断正确率提高到99.27%;该复合诊断模型大大提高了诊断效率,使测试时间缩短了52.17%,表明该复合诊断模型具有较好的故障诊断效果。
Variable refrigerant flow(VRF) valve fault detection and diagnosis usually face the problems of too many features and low efficiency.Therefore,a high-efficiency hybrid model based on a genetic algorithm(GA) and back propagation neural network(BPNN) was proposed.In this hybrid model,the feature subset is extracted from the original feature set of the VRF using the GA,and then the parameter-optimized neural network is used to detect and diagnose VRF valve faults.In this study,the hybrid model was used to detect and diagnose faults with electronic expansion valve sticking,leaking,and a four-way valve.The results showed that the hybrid model proposed in this paper could effectively and reliably diagnose faults.The integrated correct rate of fault diagnosis reached a peak value of 99.27%.In particular,the correct rate of electronic expansion valve sticking fault diagnosis was improved by 8%.In addition,the hybrid model obviously improved the detection and diagnosis efficiency,decreasing the operating time by 52.17%.
Variable refrigerant flow(VRF) valve fault detection and diagnosis usually face the problems of too many features and low efficiency.Therefore,a high-efficiency hybrid model based on a genetic algorithm(GA) and back propagation neural network(BPNN) was proposed.In this hybrid model,the feature subset is extracted from the original feature set of the VRF using the GA,and then the parameter-optimized neural network is used to detect and diagnose VRF valve faults.In this study,the hybrid model was used to detect and diagnose faults with electronic expansion valve sticking,leaking,and a four-way valve.The results showed that the hybrid model proposed in this paper could effectively and reliably diagnose faults.The integrated correct rate of fault diagnosis reached a peak value of 99.27%.In particular,the correct rate of electronic expansion valve sticking fault diagnosis was improved by 8%.In addition,the hybrid model obviously improved the detection and diagnosis efficiency,decreasing the operating time by 52.17%.
引文
[1]石书彪,陈焕新,李冠男,等.基于改进BP网络的冷水机组故障诊断[J].制冷学报,2015,36(6):34-39.(SHI Shubiao,CHEN Huanxin,LI Guannan,et al.Research on fault diagnosis of chillers based on improved BP network[J].Journal of Refrigeration,2015,36(6):34-39.)
[2]王江宇,陈焕新,刘江岩,等.基于PCA-DT的多联机制冷剂充注量故障诊断[J].华中科技大学学报(自然科学版),2016,44(7):1-4.(WANG Jiangyu,CHEN Huanxin,LIU Jiangyan,et al.PCA-DT based refrigerant charge fault diagnosis for variable refrigerant flow system[J].Journal of Huazhong University of Science and Technology(Natural Science Edition),2016,44(7):1-4.)
[3]石书彪,陈焕新,李冠男,等.基于小波去噪和神经网络的冷水机组故障诊断[J].制冷学报,2016,37(1):12-17.(SHI Shubiao,CHEN Huanxin,LI Guannan,et al.Fault diagnosis of chillers based on network and wavelet denoising[J].Journal of Refrigeration,2016,37(1):12-17.)
[4]GUO Yabin,LI Guannan,CHEN Huanxin,et al.Modularized PCA method combined with expert-based multivariate decoupling for FDD in VRF systems including indoor unit faults[J].Applied Thermal Engineering,2017,115:744-755.
[5]GUO Yabin,LI Guannan,CHEN Huanxin,et al.An enhanced PCA method with Savitzky-Golay method for VRF system sensor fault detection and diagnosis[J].Energy&Buildings,2017,142:167-178.
[6]GOLDBERG D E.Genetic algorithms in search,optimization,and machine learning[M].Addison-Wesley Publishing Companly,Inc.,1989.
[7]姚文俊.基于遗传算法的故障诊断的研究[J].网络新媒体技术,2004,25(3):85-87.(YAO Wenjun.The study of fault diagnosis based on genetic algorithm[J].Microcomputer Applications,2004,25(3):85-87.)
[8]赵云,刘惟一.基于遗传算法的特征选择方法[J].计算机工程与应用,2004,40(15):52-54.(ZHAO Yun,LIU Weiyi.Research on feature selection using genetic algorithms[J].Computer Engineering and Applications,2004,40(15):52-54.)
[9]王世卿,曹彦.基于遗传算法和支持向量机的特征选择研究[J].计算机工程与设计,2010,31(18):4088-4092.(WANG Shiqing,CAO Yan.GA-SVM-based feature subset selection algorithm[J].Computer Engineering and Design,2010,31(18):4088-4092.)
[10]韩华,谷波,康嘉.基于遗传算法和支持矢量机参数优化的制冷机组故障检测与诊断研究[J].机械工程学报,2011,47(16):120-126.(HAN Hua,GU Bo,KANG Jia.Chiller fault detection and diagnosis based on genetic algorithm and support vector machine with parameter tuning[J].Journal of Mechanical Engineering,2011,47(16):120-126.)
[11]HAN Hua,GU Bo,HONG Yingchun,et al.Automated FDD of multiple-simultaneous faults(MSF)and the application to building chillers[J].Energy&Buildings,2011,43(9):2524-2532.
[12]段侯峰.基于遗传算法优化BP神经网络的变压器故障诊断[D].北京:北京交通大学,2008.(DUAN Houfeng.Transformer fault diagnosis based on BP neural network optimized by genetic algorithm[D].Beijing:Beijing Jiaotong University,2008.)
[13]苗君明,佟刚,杨者青.基于遗传算法的神经网络优化[J].沈阳航空航天大学学报,2005,22(3):30-32.(MIAO Junming,TONG Gang,YANG Zheqing.Artificial neural networks optimizing on genetic algorithm[J].Journal of Shenyang Institute of Aeronautical Engineering,2005,22(3):30-32.)
[14]袁圃,毛剑琳,向凤红,等.改进的基于遗传优化BP神经网络的电网故障诊断[J].电力系统及其自动化学报,2017,29(1):118-122.(YUAN Pu,MAO Jianlin,XIANG Fenghong,et al.Grid fault diagnosis based on improved genetic optimization BP neural network[J].Proceedings of the CSU-EPSA,2017,29(1):118-122.)
[15]周开利.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2005.(ZHOU Kaili.Design of neural network model and its MATLAB simulation program[M].Beijing:Tsinghua University Press,2005.)
[16]ZHONG Qiu,YANG Liping,TAO Ye,et al.An optimized crossflow plate-fin membrane-based total heat exchanger[J].Energy&Buildings,2015,86:550-556.
[17]施彦,韩力群,廉小亲.神经网络设计方法与实例分析[M].北京:北京邮电大学出版社,2009.(SHI Yan,HAN Liqun,LIAN Xiaoqin.Neural network design method and case analysis[M].Beijing:Beijing University of Posts and Telecommunications Press,2009.)
[18]虞和济,陈长征,张省.基于神经网络的智能诊断[J].振动工程学报,2000,13(2):202-209.(YU Heji,CHEN Changzheng,ZHANG Xing.Intelligent diagnosis based on neural networks[J].Journal of Vibration Engineering,2000,13(2):202-209.)
[19]刘亚兵,朱伟,刘玉龙,等.电子膨胀阀常见故障分析[J].制冷与空调(北京),2013,13(7):29-32.(LIU Yabing,ZHU Wei,LIU Yulong,et al.Common malfunction analysis of electronic expansion valve[J].Refrigeration and Air-conditioning,2013,13(7):29-32.)
[2]王江宇,陈焕新,刘江岩,等.基于PCA-DT的多联机制冷剂充注量故障诊断[J].华中科技大学学报(自然科学版),2016,44(7):1-4.(WANG Jiangyu,CHEN Huanxin,LIU Jiangyan,et al.PCA-DT based refrigerant charge fault diagnosis for variable refrigerant flow system[J].Journal of Huazhong University of Science and Technology(Natural Science Edition),2016,44(7):1-4.)
[3]石书彪,陈焕新,李冠男,等.基于小波去噪和神经网络的冷水机组故障诊断[J].制冷学报,2016,37(1):12-17.(SHI Shubiao,CHEN Huanxin,LI Guannan,et al.Fault diagnosis of chillers based on network and wavelet denoising[J].Journal of Refrigeration,2016,37(1):12-17.)
[4]GUO Yabin,LI Guannan,CHEN Huanxin,et al.Modularized PCA method combined with expert-based multivariate decoupling for FDD in VRF systems including indoor unit faults[J].Applied Thermal Engineering,2017,115:744-755.
[5]GUO Yabin,LI Guannan,CHEN Huanxin,et al.An enhanced PCA method with Savitzky-Golay method for VRF system sensor fault detection and diagnosis[J].Energy&Buildings,2017,142:167-178.
[6]GOLDBERG D E.Genetic algorithms in search,optimization,and machine learning[M].Addison-Wesley Publishing Companly,Inc.,1989.
[7]姚文俊.基于遗传算法的故障诊断的研究[J].网络新媒体技术,2004,25(3):85-87.(YAO Wenjun.The study of fault diagnosis based on genetic algorithm[J].Microcomputer Applications,2004,25(3):85-87.)
[8]赵云,刘惟一.基于遗传算法的特征选择方法[J].计算机工程与应用,2004,40(15):52-54.(ZHAO Yun,LIU Weiyi.Research on feature selection using genetic algorithms[J].Computer Engineering and Applications,2004,40(15):52-54.)
[9]王世卿,曹彦.基于遗传算法和支持向量机的特征选择研究[J].计算机工程与设计,2010,31(18):4088-4092.(WANG Shiqing,CAO Yan.GA-SVM-based feature subset selection algorithm[J].Computer Engineering and Design,2010,31(18):4088-4092.)
[10]韩华,谷波,康嘉.基于遗传算法和支持矢量机参数优化的制冷机组故障检测与诊断研究[J].机械工程学报,2011,47(16):120-126.(HAN Hua,GU Bo,KANG Jia.Chiller fault detection and diagnosis based on genetic algorithm and support vector machine with parameter tuning[J].Journal of Mechanical Engineering,2011,47(16):120-126.)
[11]HAN Hua,GU Bo,HONG Yingchun,et al.Automated FDD of multiple-simultaneous faults(MSF)and the application to building chillers[J].Energy&Buildings,2011,43(9):2524-2532.
[12]段侯峰.基于遗传算法优化BP神经网络的变压器故障诊断[D].北京:北京交通大学,2008.(DUAN Houfeng.Transformer fault diagnosis based on BP neural network optimized by genetic algorithm[D].Beijing:Beijing Jiaotong University,2008.)
[13]苗君明,佟刚,杨者青.基于遗传算法的神经网络优化[J].沈阳航空航天大学学报,2005,22(3):30-32.(MIAO Junming,TONG Gang,YANG Zheqing.Artificial neural networks optimizing on genetic algorithm[J].Journal of Shenyang Institute of Aeronautical Engineering,2005,22(3):30-32.)
[14]袁圃,毛剑琳,向凤红,等.改进的基于遗传优化BP神经网络的电网故障诊断[J].电力系统及其自动化学报,2017,29(1):118-122.(YUAN Pu,MAO Jianlin,XIANG Fenghong,et al.Grid fault diagnosis based on improved genetic optimization BP neural network[J].Proceedings of the CSU-EPSA,2017,29(1):118-122.)
[15]周开利.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2005.(ZHOU Kaili.Design of neural network model and its MATLAB simulation program[M].Beijing:Tsinghua University Press,2005.)
[16]ZHONG Qiu,YANG Liping,TAO Ye,et al.An optimized crossflow plate-fin membrane-based total heat exchanger[J].Energy&Buildings,2015,86:550-556.
[17]施彦,韩力群,廉小亲.神经网络设计方法与实例分析[M].北京:北京邮电大学出版社,2009.(SHI Yan,HAN Liqun,LIAN Xiaoqin.Neural network design method and case analysis[M].Beijing:Beijing University of Posts and Telecommunications Press,2009.)
[18]虞和济,陈长征,张省.基于神经网络的智能诊断[J].振动工程学报,2000,13(2):202-209.(YU Heji,CHEN Changzheng,ZHANG Xing.Intelligent diagnosis based on neural networks[J].Journal of Vibration Engineering,2000,13(2):202-209.)
[19]刘亚兵,朱伟,刘玉龙,等.电子膨胀阀常见故障分析[J].制冷与空调(北京),2013,13(7):29-32.(LIU Yabing,ZHU Wei,LIU Yulong,et al.Common malfunction analysis of electronic expansion valve[J].Refrigeration and Air-conditioning,2013,13(7):29-32.)