一种基于油液分析数据挖掘的航空发动机磨损故障诊断知识获取方法
|
摘要
针对航空发动机磨损故障诊断自动化及智能化程度不高的问题,提出一种基于油液数据挖掘的航空发动机磨损故障诊断知识获取方法。该方法利用自组织神经网络对原始多维特征数据进行特征融合,得到融合值;利用Parzen窗法制定融合值的界限值,将样本划分为正常、警告和异常3种状态;利用Weka软件对油液数据进行规则提取。该方法能够从油液光谱数据中识别出不同磨损状态信息,并提取出知识规则用于构建航空发动机磨损诊断系统的知识库,实现了基于润滑油光谱磨损数据的航空发动机故障诊断的自动化与智能化。应用某型飞机发动机实际油液光谱数据对提出的磨损故障诊断知识获取方法进行验证,结果表明:经特征融合得到的融合值能够准确反映航空发动机的劣化趋势;利用融合值的界限值划分样本状态,再进行规则提取时具有很高的识别率。
Aimed at the problem of low automation and intellectualization of aeroengine wear fault diagnosis,a knowledge acquisition method of aeroengine wear fault diagnosis based on oil data mining was proposed.This method uses self-organizing neural network to fuse the original multi-dimensional feature data and get the fusion value,uses Parzen window method to establish the limit value of fusion value and divide the sample into normal state,warning state and abnormal state,and uses the software of Weka to extract knowledge rules from oil analysis data.This method can identify different wear state information from oil spectrum data,and extract knowledge rules to build knowledge base of aeroengine wear diagnosis system,which realizes the automation and intellectualization of aeroengine fault diagnosis based on oil spectral wear datalubricant spectrum.The proposed knowledge acquisition method for wear fault diagnosis was validated by using the actual oil spectrum data of an aircraft engine.The results show that the fusion value obtained by data fusion can accurately reflect the deterioration state of aero-engine,it has a high recognition rate by using the boundary value of the fusion value to divide the sample state and extract the knowledge rules.
Aimed at the problem of low automation and intellectualization of aeroengine wear fault diagnosis,a knowledge acquisition method of aeroengine wear fault diagnosis based on oil data mining was proposed.This method uses self-organizing neural network to fuse the original multi-dimensional feature data and get the fusion value,uses Parzen window method to establish the limit value of fusion value and divide the sample into normal state,warning state and abnormal state,and uses the software of Weka to extract knowledge rules from oil analysis data.This method can identify different wear state information from oil spectrum data,and extract knowledge rules to build knowledge base of aeroengine wear diagnosis system,which realizes the automation and intellectualization of aeroengine fault diagnosis based on oil spectral wear datalubricant spectrum.The proposed knowledge acquisition method for wear fault diagnosis was validated by using the actual oil spectrum data of an aircraft engine.The results show that the fusion value obtained by data fusion can accurately reflect the deterioration state of aero-engine,it has a high recognition rate by using the boundary value of the fusion value to divide the sample state and extract the knowledge rules.
引文
[1]陈立波,宋兰琪,陈果.航空发动机滑油综合监控中的磨损故障融合诊断研究[J].航空动力学报,2009,24(1):169-175.CHEN L B,SONG L Q,CHEN G.Study on fusion diagnosis techniques of wear faults in synthesized monitoring of aeroengine[J].Journal of Aerospace Power,2009,24(1):169-175.
[2]马安祥,李艳军,曹愈远,等.基于免疫理论的航空发动机磨损故障智能诊断[J].航空学报,2015,36(6):1896-1904.MA A X,LI Y J,CAO Y Y,et al.Intelligent diagnosis for aircraft engine wear fault based on immune theory[J].Acta Aeronautica Et Astronautica Sinica,2015,36(6):1896-1904.
[3]李爱,陈果,张强,等.基于多Agent协同诊断的飞机液压系统综合监控技术[J].航空学报,2010,31(12):2407-2416.LI A,CHEN G,ZHANG Q,et al.Integrated monitoring technology for aircraft hydraulic system based on multi-agent collaborative diagnosis[J].Acta Aeronautica Et Astronautica Sinica,2010,31(12):2407-2416.
[4]陈果,左洪福.基于知识规则的发动机磨损故障诊断专家系统[J].航空动力学报,2004,19(1):23-29.CHEN G,ZUO H F.Expert systems of engine wear fault diagnosis based on knowledge rule[J].Journal of Aerospace Power,2004,19(1):23-29.
[5]宋兰琪,汤道宇,陈立波,等.航空发动机滑油光谱专家系统知识库建立[J].航空学报,2000,21(5):453-456.SONG L Q,TANG D Y,CHEN L B,et al.Knowledge base building in the expert system of aircraft engine spectrometric oil analysis[J].Acta Aeronautica Et Astronautica Sinica,2000,21(5):453-456.
[6]李爱,陈果.基于SVM的航空发动机油样光谱诊断界限值制定[J].航空动力学报,2011,26(4):771-778LI A,CHEN G.Establishment of the threshold of oil spectrum analysis in the aifcraft engine based on SVM[J].Journal of Aerospace Power,2011,26(4):771-778.
[7]胡金海,余治国,翟旭升,等.基于改进D-S证据理论的航空发动机转子故障决策融合诊断研究[J].航空学报,2014,35(2):436-443.HU J H,YU Z G,ZHAI X S,et al.Research of decision fusion diagnosis of aero-engine rotor fault based on improved D-S theory[J].Acta Aeronautica Et Astronautica Sinica,2014,35(2):436-443.
[8]AI L,WANG J,WANG X.Multi-features fusion diagnosis of tremor based on artificial neural network and D-S evidence theory[J].Signal Processing,2008,88(12):2927-2935.
[9]文振华,左洪福.基于粗糙集-集成神经网络的航空发动机磨损故障诊断方法[J].中国机械工程,2007,18(21):2580-2584.WEN Z H,ZUO H F.A diagnosis method for aero engine wear fault based on rough sets theory and integrated neural network[J].China Mechanical Engineering,2007,18(21):2580-2584.
[10]赵世荣,黄向华.应用神经网络信息融合诊断航空发动机故障[J].航空动力学报,2008,23(1):163-168.ZHAO S R,HUANG X H.Fault diagnosis for aeroengine gas path components based on neural network multisensor data fusion[J].Journal of Aerospace Power,2008,23(1):163-168.
[11]LIU Y Y,JU Y F,DUAN C D,et al.Structure damage diagnosis using neural network and feature fusion[J].Engineering Applications of Artificial Intelligence,2011,24(1):87-92.
[12]DONG L,XIAO D,LIANG Y,et al.Rough set and fuzzy wavelet neural network integrated with least square weighted fusion algorithm based fault diagnosis research for power transformers[J].Electric Power Systems Research,2008,78(1):129-136.
[13]姜万录,刘思远.多特征信息融合的贝叶斯网络故障诊断方法研究[J].中国机械工程,2010,21(8):940-945.JIANG W L,LIU S Y.Fault diagnosis approach study of bayesian networks based on multi-characteristic information fusion[J].China Mechanical Engineering,2010,21(8):940-945.
[14]SHI X,MANDUCHI R.On the Bayes fusion of visual features[J].Image&Vision Computing,2007,25(11):1748-1758.
[15]余鹰,苗夺谦,赵才荣,等.基于粗糙集的多标记决策系统知识获取方法[J].计算机科学与探索,2015,9(1):94-104.YU Y,MIAO D Q,ZHAO C R.Knowledge acquisition methods for multi-label decision system based on rough sets[J].Journal of Frontiers of Computer Science and Technology,2015,9(1):94-104.
[16]牛星岩,沈颂华,董世良.基于粗糙集理论的飞机供电系统诊断规则提取[J].航空学报,2007,28(6):1428-1432.NIU X Y,SHEN S H,DONG S L.Fault diagnosis in aircraft power system based on rough sets[J].Acta Aeronautica Et Astronautica Sinica,2007,28(6):1428-1432.
[17]ZHANG J,WONG J S,LI T,et al.A comparison of parallel large-scale knowledge acquisition using rough set theory on different MapReduce runtime systems[J].International Journal of Approximate Reasoning,2014,55(3):896-907.
[18]陈果,宋兰琪,陈立波.基于神经网络规则提取的航空发动机磨损故障诊断知识获取[J].航空动力学报,2008,23(12):2170-2176.CHEN G,SONG L Q,CHEN L B.Knowledge acquisition for aero-engine wear fault diagnosis based on rule extraction from neural networks[J].Journal of Aerospace Power,2008,23(12):2170-2176.
[19]张明明,刘晓波,丁伟明.网格细化小波聚类在航空发动机转子系统故障诊断中的应用[J].机床与液压,2016,44(11):163-167.ZHANG M M,LIU X B,DING W M.Application of wavelet clustering algorithm based on the grid refinement in fault diagnosis of aero-engine rotor system[J].Machine Tool&Hydraulics,2016,44(11):163-167.
[20]葛科宇,陈果.基于Weka平台知识获取的航空发动机磨损故障诊断专家系统[J].机械科学与技术,2011,30(11):1955-1959.GE K Y,CHEN G.Knowledge acquisition of aero-engine wear fault diagnosis expert system based on weka platform[J].Mechanical Science and Technology for Aerospace Engineering,2011,30(11):1955-1959.
[2]马安祥,李艳军,曹愈远,等.基于免疫理论的航空发动机磨损故障智能诊断[J].航空学报,2015,36(6):1896-1904.MA A X,LI Y J,CAO Y Y,et al.Intelligent diagnosis for aircraft engine wear fault based on immune theory[J].Acta Aeronautica Et Astronautica Sinica,2015,36(6):1896-1904.
[3]李爱,陈果,张强,等.基于多Agent协同诊断的飞机液压系统综合监控技术[J].航空学报,2010,31(12):2407-2416.LI A,CHEN G,ZHANG Q,et al.Integrated monitoring technology for aircraft hydraulic system based on multi-agent collaborative diagnosis[J].Acta Aeronautica Et Astronautica Sinica,2010,31(12):2407-2416.
[4]陈果,左洪福.基于知识规则的发动机磨损故障诊断专家系统[J].航空动力学报,2004,19(1):23-29.CHEN G,ZUO H F.Expert systems of engine wear fault diagnosis based on knowledge rule[J].Journal of Aerospace Power,2004,19(1):23-29.
[5]宋兰琪,汤道宇,陈立波,等.航空发动机滑油光谱专家系统知识库建立[J].航空学报,2000,21(5):453-456.SONG L Q,TANG D Y,CHEN L B,et al.Knowledge base building in the expert system of aircraft engine spectrometric oil analysis[J].Acta Aeronautica Et Astronautica Sinica,2000,21(5):453-456.
[6]李爱,陈果.基于SVM的航空发动机油样光谱诊断界限值制定[J].航空动力学报,2011,26(4):771-778LI A,CHEN G.Establishment of the threshold of oil spectrum analysis in the aifcraft engine based on SVM[J].Journal of Aerospace Power,2011,26(4):771-778.
[7]胡金海,余治国,翟旭升,等.基于改进D-S证据理论的航空发动机转子故障决策融合诊断研究[J].航空学报,2014,35(2):436-443.HU J H,YU Z G,ZHAI X S,et al.Research of decision fusion diagnosis of aero-engine rotor fault based on improved D-S theory[J].Acta Aeronautica Et Astronautica Sinica,2014,35(2):436-443.
[8]AI L,WANG J,WANG X.Multi-features fusion diagnosis of tremor based on artificial neural network and D-S evidence theory[J].Signal Processing,2008,88(12):2927-2935.
[9]文振华,左洪福.基于粗糙集-集成神经网络的航空发动机磨损故障诊断方法[J].中国机械工程,2007,18(21):2580-2584.WEN Z H,ZUO H F.A diagnosis method for aero engine wear fault based on rough sets theory and integrated neural network[J].China Mechanical Engineering,2007,18(21):2580-2584.
[10]赵世荣,黄向华.应用神经网络信息融合诊断航空发动机故障[J].航空动力学报,2008,23(1):163-168.ZHAO S R,HUANG X H.Fault diagnosis for aeroengine gas path components based on neural network multisensor data fusion[J].Journal of Aerospace Power,2008,23(1):163-168.
[11]LIU Y Y,JU Y F,DUAN C D,et al.Structure damage diagnosis using neural network and feature fusion[J].Engineering Applications of Artificial Intelligence,2011,24(1):87-92.
[12]DONG L,XIAO D,LIANG Y,et al.Rough set and fuzzy wavelet neural network integrated with least square weighted fusion algorithm based fault diagnosis research for power transformers[J].Electric Power Systems Research,2008,78(1):129-136.
[13]姜万录,刘思远.多特征信息融合的贝叶斯网络故障诊断方法研究[J].中国机械工程,2010,21(8):940-945.JIANG W L,LIU S Y.Fault diagnosis approach study of bayesian networks based on multi-characteristic information fusion[J].China Mechanical Engineering,2010,21(8):940-945.
[14]SHI X,MANDUCHI R.On the Bayes fusion of visual features[J].Image&Vision Computing,2007,25(11):1748-1758.
[15]余鹰,苗夺谦,赵才荣,等.基于粗糙集的多标记决策系统知识获取方法[J].计算机科学与探索,2015,9(1):94-104.YU Y,MIAO D Q,ZHAO C R.Knowledge acquisition methods for multi-label decision system based on rough sets[J].Journal of Frontiers of Computer Science and Technology,2015,9(1):94-104.
[16]牛星岩,沈颂华,董世良.基于粗糙集理论的飞机供电系统诊断规则提取[J].航空学报,2007,28(6):1428-1432.NIU X Y,SHEN S H,DONG S L.Fault diagnosis in aircraft power system based on rough sets[J].Acta Aeronautica Et Astronautica Sinica,2007,28(6):1428-1432.
[17]ZHANG J,WONG J S,LI T,et al.A comparison of parallel large-scale knowledge acquisition using rough set theory on different MapReduce runtime systems[J].International Journal of Approximate Reasoning,2014,55(3):896-907.
[18]陈果,宋兰琪,陈立波.基于神经网络规则提取的航空发动机磨损故障诊断知识获取[J].航空动力学报,2008,23(12):2170-2176.CHEN G,SONG L Q,CHEN L B.Knowledge acquisition for aero-engine wear fault diagnosis based on rule extraction from neural networks[J].Journal of Aerospace Power,2008,23(12):2170-2176.
[19]张明明,刘晓波,丁伟明.网格细化小波聚类在航空发动机转子系统故障诊断中的应用[J].机床与液压,2016,44(11):163-167.ZHANG M M,LIU X B,DING W M.Application of wavelet clustering algorithm based on the grid refinement in fault diagnosis of aero-engine rotor system[J].Machine Tool&Hydraulics,2016,44(11):163-167.
[20]葛科宇,陈果.基于Weka平台知识获取的航空发动机磨损故障诊断专家系统[J].机械科学与技术,2011,30(11):1955-1959.GE K Y,CHEN G.Knowledge acquisition of aero-engine wear fault diagnosis expert system based on weka platform[J].Mechanical Science and Technology for Aerospace Engineering,2011,30(11):1955-1959.