基于DBN的不均衡样本驱动民航发动机故障诊断
|
摘要
在结合深度置信网络(DBN)、采样与集成技术的基础上,提出了基于不均衡样本驱动的民航发动机故障诊断模型。该模型通过分析民航发动机历史飞行数据,利用DBN提取性能参数中的内部特征,利用采样技术将不均衡样本均衡化,采用集成技术进行故障分类。将该模型应用到CFM56-7B系列发动机历史飞行数据,实验结果表明:与常用故障诊断方法相比,该模型的准确率高达0.996,AUC值高达0.948,可以有效处理民航发动机样本高维、不均衡问题。
Through combination of deep belief network(DBN),sampling and integration technology,a fault diagnosis model of civil aero-engine based on unbalanced sample driving was proposed.By analyzing the historical flight data of civil aero-engines,the model used DBN to extract the internal features of the performance parameters,then used the sampling technology to equalize the unbalanced samples,and finally adopted integrated technology for fault classification.The model was applied to historical flight data of CFM56-7 Bseries engines.Compared with common fault diagnosis methods,the experimental results showed that the model had higher accuracy of 0.996 and AUC value of 0.948,and can effectively deal with high-dimensional and unbalanced problems of civil aero-engine samples.
Through combination of deep belief network(DBN),sampling and integration technology,a fault diagnosis model of civil aero-engine based on unbalanced sample driving was proposed.By analyzing the historical flight data of civil aero-engines,the model used DBN to extract the internal features of the performance parameters,then used the sampling technology to equalize the unbalanced samples,and finally adopted integrated technology for fault classification.The model was applied to historical flight data of CFM56-7 Bseries engines.Compared with common fault diagnosis methods,the experimental results showed that the model had higher accuracy of 0.996 and AUC value of 0.948,and can effectively deal with high-dimensional and unbalanced problems of civil aero-engine samples.
引文
[1]李一波,张宗杰,蒋丽英.航空发动机故障诊断信息融合方法研究现状[J].航空发动机,2009,35(3):36-39.LI Yibo,ZHANG Zongjie,JIANG Liying.Research status of aeroengine fault diagnosis information fusion method[J].Aeroengine,2009,35(3):36-39.(in Chinese)
[2]郝英,孙健国,白杰.航空燃气涡轮发动机气路故障诊断现状与展望[J].航空动力学报,2003,18(6):753-760.HAO Ying,SUN Jianguo,BAI Jie.State of the art and prospect of aircraft engine fault diagnosis using gas path parameters[J].Journal of Aerospace Power,2003,18(6):753-760.(in Chinese)
[3]张经璞.航空发动机状态监控与典型故障分析[D].沈阳:沈阳航空航天大学,2017.ZHANG Jingpu.Aeroengine condition monitoring and typical failure analysis[D].Shenyang:Shenyang Aerospace U-niversity,2017.(in Chinese)
[4]崔文斌.航空发动机气路性能估计方法对比研究[D].南京:南京航空航天大学,2014.CUI Wenbin.Aeroengine gas path performance estimation method comparative study[D].Nanjing:Nanjing University of Aeronautics and Astronautics,2014.(in Chinese)
[5]ZHANG Jing,YANG Yingping,ZHANG Jinmin.A MEC-BP-AdaBoost neural network-based color correction algorithm for color image acquisition equipments[J].Optics,2016,127(2):776-780.
[6]MONJEZI M,BAHRAMIA.Prediction of blast-induced ground vibration using artificial neural networks[J].Tunnelling and Underground Space Technology,2011,26(1):46-50.
[7]李爱.航空发动机磨损故障智能诊断若干关键技术研究[D].南京:南京航空航天大学,2013.LI Ai.Some key technologies for intelligent diagnosis of aero engine wear failure[D].Nanjing:Nanjing University of Aeronautics and Astronautics,2013.(in Chinese)
[8]崔智全.民航发动机气路参数偏差值挖掘方法及其应用研究[D].哈尔滨:哈尔滨工业大学,2013.CUI Zhiquan.Research on the method of mining parameters deviation of civil aviation engine and its application[D].Harbin:Harbin Institute of Technology,2013.(in Chinese)
[9]SIMANI S.Residual generator fuzzy identification for automotive diesel engine fault diagnosis[J].International Journal of Applied Mathematics and Computer Science,2013,23(2):419-438.
[10]赵光权,葛强强,刘小勇,等.基于DBN的故障特征提取及诊断方法研究[J].仪器仪表学报,2016,37(9):1946-1953.ZHAO Guangquan,GE Qiangqiang,LIU Xiaoyong,et al.Fault feature extraction and diagnosis based on DBN[J].Chinese Journal of Scientific Instrument,2016,37(9):1946-1953.(in Chinese)
[11]GHOSH A,MAJUMDAR S K.Modeling blast furnace productivity using support vector machines[J].International Journal of Advanced Manufacturing Technology,2011,52(9/10/11/12):989-1003.
[12]崔建国,吴灿,董世良,等.主元分析法和模糊积分的航空发动机气路状态监测[J].火力与指挥控制,2014,39(10):130-134.CUI Jianguo,WU Can,DONG Shiliang,et al.Analysis of aero-engine gas path conditions using principal component analysis and fuzzy integral[J].Fire Control and Command Control,2014,39(10):130-134.(in Chinese)
[13]夏丽莎,杨玉英,方华京.基于EasyEnsemble的化工过程故障诊断性能改进[J].控制理论与应用,2017,34(2):49-53.XIA Lisha,YANG Yuying,FANG Huajing.Performance improvement of fault diagnosis in chemical process based on EasyEnsemble[J].Journal of Control Theory and Applications,2017,34(2):49-53.(in Chinese)
[14]何玲.面向故障诊断的异构特征融合与在线不均衡分类研究[D].河南新乡:河南师范大学,2017.XIANG Ling.Research on heterogeneous features fusion and online imbalance classification for bearing fault diagnosis[D].Xinxiang Henan:Henan Normal University,2017.(in Chinese)
[15]陶新民,郝思媛,张冬雪,等.不均衡数据分类算法的综述[J].重庆邮电大学学报(自然科学版),2013,25(1):101-110,121.TAO Xinmin,HAO Siyuan,ZHANG Dongxue,et al.Overview of classification algorithms for unbalanced data[J].Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2013,25(1):101-110,121.(in Chinese)
[16]LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(14539):436-444.
[17]HINTON G E.Training products of experts by minimizing contrastive divergence[J].Neural Computation,2002,14(8):1771-1800.
[18]VERBIEST N,RAMENTOL E,CORNELIS C,et al.Preprocessing noisy imbalanced datasets using SMOTE enhanced with fuzzy rough prototype selection[J].Applied Soft Computing Journal,2014,22:511-517.
[19]杨宏晖,王芸,孙进才,等.融合样本选择与特征选择的AdaBoost支持向量机集成算法[J].西安交通大学学报,2014,48(12):63-68.YANG Honghui,WANG Yun,SUN Jincai,et al.AdaBoost support vector machines integration algorithm for fusion sample selection and feature selection[J].Journal of Xian Jiaotong University,2014,48(12):63-68.(in Chinese)
[20]从威.非均衡分类的集成学习应用研究[D].南京:南京信息工程大学,2017.CONG Wei.Non-equilibrium classification of integrated learning applications[D].Nanjing:Nanjing University of Information Science and Technology,2017.(in Chinese)
[21]殷锴,钟诗胜,那媛,等.基于BP神经网络的航空发动机故障检测技术研究[J].航空发动机,2017,43(1):53-57.YIN Kai,ZHONG Shisheng,NA Yuan,et al.Analysis of aeroengine fault detection based on BP neural network[J].Aeroengine,2017,43(1):53-57.(in Chinese)
[2]郝英,孙健国,白杰.航空燃气涡轮发动机气路故障诊断现状与展望[J].航空动力学报,2003,18(6):753-760.HAO Ying,SUN Jianguo,BAI Jie.State of the art and prospect of aircraft engine fault diagnosis using gas path parameters[J].Journal of Aerospace Power,2003,18(6):753-760.(in Chinese)
[3]张经璞.航空发动机状态监控与典型故障分析[D].沈阳:沈阳航空航天大学,2017.ZHANG Jingpu.Aeroengine condition monitoring and typical failure analysis[D].Shenyang:Shenyang Aerospace U-niversity,2017.(in Chinese)
[4]崔文斌.航空发动机气路性能估计方法对比研究[D].南京:南京航空航天大学,2014.CUI Wenbin.Aeroengine gas path performance estimation method comparative study[D].Nanjing:Nanjing University of Aeronautics and Astronautics,2014.(in Chinese)
[5]ZHANG Jing,YANG Yingping,ZHANG Jinmin.A MEC-BP-AdaBoost neural network-based color correction algorithm for color image acquisition equipments[J].Optics,2016,127(2):776-780.
[6]MONJEZI M,BAHRAMIA.Prediction of blast-induced ground vibration using artificial neural networks[J].Tunnelling and Underground Space Technology,2011,26(1):46-50.
[7]李爱.航空发动机磨损故障智能诊断若干关键技术研究[D].南京:南京航空航天大学,2013.LI Ai.Some key technologies for intelligent diagnosis of aero engine wear failure[D].Nanjing:Nanjing University of Aeronautics and Astronautics,2013.(in Chinese)
[8]崔智全.民航发动机气路参数偏差值挖掘方法及其应用研究[D].哈尔滨:哈尔滨工业大学,2013.CUI Zhiquan.Research on the method of mining parameters deviation of civil aviation engine and its application[D].Harbin:Harbin Institute of Technology,2013.(in Chinese)
[9]SIMANI S.Residual generator fuzzy identification for automotive diesel engine fault diagnosis[J].International Journal of Applied Mathematics and Computer Science,2013,23(2):419-438.
[10]赵光权,葛强强,刘小勇,等.基于DBN的故障特征提取及诊断方法研究[J].仪器仪表学报,2016,37(9):1946-1953.ZHAO Guangquan,GE Qiangqiang,LIU Xiaoyong,et al.Fault feature extraction and diagnosis based on DBN[J].Chinese Journal of Scientific Instrument,2016,37(9):1946-1953.(in Chinese)
[11]GHOSH A,MAJUMDAR S K.Modeling blast furnace productivity using support vector machines[J].International Journal of Advanced Manufacturing Technology,2011,52(9/10/11/12):989-1003.
[12]崔建国,吴灿,董世良,等.主元分析法和模糊积分的航空发动机气路状态监测[J].火力与指挥控制,2014,39(10):130-134.CUI Jianguo,WU Can,DONG Shiliang,et al.Analysis of aero-engine gas path conditions using principal component analysis and fuzzy integral[J].Fire Control and Command Control,2014,39(10):130-134.(in Chinese)
[13]夏丽莎,杨玉英,方华京.基于EasyEnsemble的化工过程故障诊断性能改进[J].控制理论与应用,2017,34(2):49-53.XIA Lisha,YANG Yuying,FANG Huajing.Performance improvement of fault diagnosis in chemical process based on EasyEnsemble[J].Journal of Control Theory and Applications,2017,34(2):49-53.(in Chinese)
[14]何玲.面向故障诊断的异构特征融合与在线不均衡分类研究[D].河南新乡:河南师范大学,2017.XIANG Ling.Research on heterogeneous features fusion and online imbalance classification for bearing fault diagnosis[D].Xinxiang Henan:Henan Normal University,2017.(in Chinese)
[15]陶新民,郝思媛,张冬雪,等.不均衡数据分类算法的综述[J].重庆邮电大学学报(自然科学版),2013,25(1):101-110,121.TAO Xinmin,HAO Siyuan,ZHANG Dongxue,et al.Overview of classification algorithms for unbalanced data[J].Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2013,25(1):101-110,121.(in Chinese)
[16]LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(14539):436-444.
[17]HINTON G E.Training products of experts by minimizing contrastive divergence[J].Neural Computation,2002,14(8):1771-1800.
[18]VERBIEST N,RAMENTOL E,CORNELIS C,et al.Preprocessing noisy imbalanced datasets using SMOTE enhanced with fuzzy rough prototype selection[J].Applied Soft Computing Journal,2014,22:511-517.
[19]杨宏晖,王芸,孙进才,等.融合样本选择与特征选择的AdaBoost支持向量机集成算法[J].西安交通大学学报,2014,48(12):63-68.YANG Honghui,WANG Yun,SUN Jincai,et al.AdaBoost support vector machines integration algorithm for fusion sample selection and feature selection[J].Journal of Xian Jiaotong University,2014,48(12):63-68.(in Chinese)
[20]从威.非均衡分类的集成学习应用研究[D].南京:南京信息工程大学,2017.CONG Wei.Non-equilibrium classification of integrated learning applications[D].Nanjing:Nanjing University of Information Science and Technology,2017.(in Chinese)
[21]殷锴,钟诗胜,那媛,等.基于BP神经网络的航空发动机故障检测技术研究[J].航空发动机,2017,43(1):53-57.YIN Kai,ZHONG Shisheng,NA Yuan,et al.Analysis of aeroengine fault detection based on BP neural network[J].Aeroengine,2017,43(1):53-57.(in Chinese)