基于支持向量机和粒子群算法的多联机气液分离器插反故障诊断
|
摘要
本文通过多联机实验平台采集数据,选取合适的特征变量,利用支持向量机算法建立了多联机气液分离器插反故障诊断模型。采用粒子群算法优化该模型,通过测试集验证模型的分类准确率,并对两种模型下的故障诊断效果进行对比分析。结果表明,制冷工况下的故障诊断准确率高于制热工况下的准确率。模型优化前两种工况下的故障诊断准确率均高于96%,而优化后的准确率均高于97%,优化后制冷工况下的故障诊断准确率更是高达98.4%,可见优化后的模型性能稳步提升。
The data were collected through the variable refrigerant flow(VRF) experimental platform, and the suitable characteristic variables were selected. A VRF gas-liquid separator opposite-insertion fault diagnosis model using support vector machine algorithm was developed. The particle swarm optimization algorithm was used to optimize the model. The test set was used to verify the classification accuracy of the model, and the fault diagnosis effects of the two models were compared and analyzed. The results show that the accuracy of fault diagnosis under refrigeration condition is higher than that under heating condition. The accuracy of fault diagnosis under the two conditions is larger than 96% under support vector machine model. After using the particle swarm optimization algorithm, the accuracy is larger than 97% under these two conditions, and the accuracy of fault diagnosis under refrigeration conditions is up to 98.4%. The performance of the optimized model is steadily increased.
The data were collected through the variable refrigerant flow(VRF) experimental platform, and the suitable characteristic variables were selected. A VRF gas-liquid separator opposite-insertion fault diagnosis model using support vector machine algorithm was developed. The particle swarm optimization algorithm was used to optimize the model. The test set was used to verify the classification accuracy of the model, and the fault diagnosis effects of the two models were compared and analyzed. The results show that the accuracy of fault diagnosis under refrigeration condition is higher than that under heating condition. The accuracy of fault diagnosis under the two conditions is larger than 96% under support vector machine model. After using the particle swarm optimization algorithm, the accuracy is larger than 97% under these two conditions, and the accuracy of fault diagnosis under refrigeration conditions is up to 98.4%. The performance of the optimized model is steadily increased.
引文
[1]郭富军,顾中华,季秀成,等.大容量多联机用并联气液分离器的技术探讨[J].制冷与空调,2016,16(8):25-27.
[2]郑贤德.制冷原理与装置[M].北京:机械工业出版社,2000.
[3]HU Y,CHEN H,XIE J,et al.Chiller sensor fault detection using a self-Adaptive Principal Component Analysis method[J].Energy and Buildings,2012,54:252-258.
[4]XU X,XIAO F,WANG S.Enhanced chiller sensor fault detection,diagnosis and estimation using wavelet analysis and principal component analysis methods[J].Applied Thermal Engineering,2008,28(2):226-237.
[5]LIU J,HU Y,CHEN H,et al.A refrigerant charge fault detection method for variable refrigerant flow(VRF)air-conditioning systems[J].Applied Thermal Engineering,2016,107:284-293.
[6]禹法文,陈焕新,李绍斌,等.基于主元分析法的多联机系统压缩机排气温度传感器故障检测与诊断[J].制冷技术.2017,37(4):29-33.
[7]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.
[8]袁玥,陈焕新,石书彪,等.基于主成分分析和神经网络相结合的制冷剂充注量故障诊断[J].制冷技术,2017,37(6):45-50.
[9]GERDES M.Decision trees and genetic algorithms for condition monitoring forecasting of aircraft air conditioning[J].Expert Systems with Applications,2013,40(12):5021-5026.
[10]YAN K,SHEN W,MULUMBA T,et al.ARX model based fault detection and diagnosis for chillers using support vector machines[J].Energy and Buildings,2014,81:287-295.
[11]VAPNIK V N.The nature of statistical learning theory[M].New York:Springer Verlag,1995.
[12]梅飞,梅军,郑建勇,等.粒子群优化的KFCM及SVM诊断模型在断路器故障诊断中的应用[J].中国电机工程学报,2013,33(36):134-141.
[13]PASSERINI A,PONTIL M,FRASCONI P.New results on error correcting output codes of kernel machines[J].IEEE Transactions on Neural Networks,2004,15(1):45-54.
[14]王健峰.基于改进网格搜索法SVM参数优化的说话人识别研究[D].哈尔滨:哈尔滨工程大学,2012.
[15]CHEN P W,WANG J Y,LEE H.Model selection of SVMs using GA approach[C].2004 IEEE International Joint Conference on Neural Networks,Piscataway,USA,2004:2035-2040.
[16]席裕庚,柴天佑,恽为民.遗传算法综述[J].控制理论与应用,1996,13(6):697-708.
[17]CZARNECKI W M,TABOR J.Two ellipsoid support vector machines[J].Expert Systems with Applications,2014,41(18):8211-8224.
[18]SURYANARAYANA C,SUDHEER C,MAHAMMONDV,et al.An integrated wavelet-support vector machine for groundwater level prediction in Visakhapatnam,India[J].Neurocomputing,2014,145:324-335.
[19]冯辉宗,彭丹,袁荣棣.基于PSO-SVM的发动机故障诊断研究[J].计算机测量与控制,2014,22(2):355-357.
[20]周鹏飞,贺群妮.多联机空调系统运行性能的影响因素分析[J].制冷技术,2012,32(3):62-65.
[21]刘佳慧,刘江岩,李绍斌,等.基于决策树算法的多联机气液分离器插反故障诊断[J].制冷学报,2017,38(5):1-6.
[22]SUN K,LI G,CHEN H,et al.A novel efficient SVM-based fault diagnosis method for multi-spl,it air conditioning system's refrigerant charge fault amount[J].Applied Thermal Engineering,2016,108:989-998.
[2]郑贤德.制冷原理与装置[M].北京:机械工业出版社,2000.
[3]HU Y,CHEN H,XIE J,et al.Chiller sensor fault detection using a self-Adaptive Principal Component Analysis method[J].Energy and Buildings,2012,54:252-258.
[4]XU X,XIAO F,WANG S.Enhanced chiller sensor fault detection,diagnosis and estimation using wavelet analysis and principal component analysis methods[J].Applied Thermal Engineering,2008,28(2):226-237.
[5]LIU J,HU Y,CHEN H,et al.A refrigerant charge fault detection method for variable refrigerant flow(VRF)air-conditioning systems[J].Applied Thermal Engineering,2016,107:284-293.
[6]禹法文,陈焕新,李绍斌,等.基于主元分析法的多联机系统压缩机排气温度传感器故障检测与诊断[J].制冷技术.2017,37(4):29-33.
[7]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.
[8]袁玥,陈焕新,石书彪,等.基于主成分分析和神经网络相结合的制冷剂充注量故障诊断[J].制冷技术,2017,37(6):45-50.
[9]GERDES M.Decision trees and genetic algorithms for condition monitoring forecasting of aircraft air conditioning[J].Expert Systems with Applications,2013,40(12):5021-5026.
[10]YAN K,SHEN W,MULUMBA T,et al.ARX model based fault detection and diagnosis for chillers using support vector machines[J].Energy and Buildings,2014,81:287-295.
[11]VAPNIK V N.The nature of statistical learning theory[M].New York:Springer Verlag,1995.
[12]梅飞,梅军,郑建勇,等.粒子群优化的KFCM及SVM诊断模型在断路器故障诊断中的应用[J].中国电机工程学报,2013,33(36):134-141.
[13]PASSERINI A,PONTIL M,FRASCONI P.New results on error correcting output codes of kernel machines[J].IEEE Transactions on Neural Networks,2004,15(1):45-54.
[14]王健峰.基于改进网格搜索法SVM参数优化的说话人识别研究[D].哈尔滨:哈尔滨工程大学,2012.
[15]CHEN P W,WANG J Y,LEE H.Model selection of SVMs using GA approach[C].2004 IEEE International Joint Conference on Neural Networks,Piscataway,USA,2004:2035-2040.
[16]席裕庚,柴天佑,恽为民.遗传算法综述[J].控制理论与应用,1996,13(6):697-708.
[17]CZARNECKI W M,TABOR J.Two ellipsoid support vector machines[J].Expert Systems with Applications,2014,41(18):8211-8224.
[18]SURYANARAYANA C,SUDHEER C,MAHAMMONDV,et al.An integrated wavelet-support vector machine for groundwater level prediction in Visakhapatnam,India[J].Neurocomputing,2014,145:324-335.
[19]冯辉宗,彭丹,袁荣棣.基于PSO-SVM的发动机故障诊断研究[J].计算机测量与控制,2014,22(2):355-357.
[20]周鹏飞,贺群妮.多联机空调系统运行性能的影响因素分析[J].制冷技术,2012,32(3):62-65.
[21]刘佳慧,刘江岩,李绍斌,等.基于决策树算法的多联机气液分离器插反故障诊断[J].制冷学报,2017,38(5):1-6.
[22]SUN K,LI G,CHEN H,et al.A novel efficient SVM-based fault diagnosis method for multi-spl,it air conditioning system's refrigerant charge fault amount[J].Applied Thermal Engineering,2016,108:989-998.