基于ARIMA模型的民用航空发动机低压转子振动故障分析
|
摘要
民用航空发动机运行数据是航空公司制定发动机维护方案的重要参考依据。针对某航空公司CFM56-7B发动机的振动值变化趋势提出了一种基于回归分析和ARIMA(autoregressive integrated moving average)模型的故障分析方法。采用回归分析法对各航段发动机振动值和转速之间的关系进行回归拟合,针对指数拟合方程的指数项系数建立ARIMA分析模型,得到方程拟合系数预测值与真实值之间的对应关系并分析结果,从而预判发动机是否有振动故障征兆。结果表明,ARIMA模型能够较好地描述发动机振动-转速拟合系数变化趋势,能够有效地预测发动机振动故障,可为航空公司制定发动机维护方案提供重要依据。
The operation data of Civil Aero-engine is an important reference for airlines to make engine maintenance plans. A fault analysis method based on regressive analysis and ARIMA( autoregressive integrated moving average) model was proposed for the development trend of vibration value of an airline CFM56-7 B engine. The regression analysis method was used to fit the vibration value and rotational speed of the engine in each flight. The ARIMA analysis model was established for the exponential coefficient of the exponential fitting equation,then the corresponding relationship between the predicted value and the real value of the equation fitting coefficient was obtained and analyzed,and then whether the engine has vibration fault symptoms was predicted. The results show that ARIMA model can describe the trend of engine vibration-speed fitting coefficient well and predict engine vibration fault effectively,and the model provides an important basis for airlines to make engine maintenance plans.
The operation data of Civil Aero-engine is an important reference for airlines to make engine maintenance plans. A fault analysis method based on regressive analysis and ARIMA( autoregressive integrated moving average) model was proposed for the development trend of vibration value of an airline CFM56-7 B engine. The regression analysis method was used to fit the vibration value and rotational speed of the engine in each flight. The ARIMA analysis model was established for the exponential coefficient of the exponential fitting equation,then the corresponding relationship between the predicted value and the real value of the equation fitting coefficient was obtained and analyzed,and then whether the engine has vibration fault symptoms was predicted. The results show that ARIMA model can describe the trend of engine vibration-speed fitting coefficient well and predict engine vibration fault effectively,and the model provides an important basis for airlines to make engine maintenance plans.
引文
1金向阳,林琳,钟诗胜,等.航空发动机振动趋势预测的过程神经网络法[J].振动、测试与诊断,2011,31(3):331-334Jin Xiangyang,Lin Lin,Zhong Shisheng,et al. Chattering reduction sliding mode control for electro-hydraulic position servo system[J].Journal of Vibration,Measurement and Diagnosis,2011,31(3):331-334
2 王俨剀,马进锐,廖明夫,等.发动机振动趋势预测模型研究[J].振动、测试与诊断,2014(3):516-523Wang Yankai,Ma Jinrui,Liao Mingfu,et al. Research on trend prediction model of engine vibration[J]. Journal of Vibration,Measurement and Diagnosis,2014(3):516-523
3 董欢.某型航空发动机中介轴承故障诊断技术研究[D].沈阳:沈阳航空航天大学,2017Dong Huan. Research on fault diagnosis technology of inteeshaft bearings in an aeroengine[D]. Shenyang:Shenyang Aerospace University,2017
4 Wang S,Chen X,Tong C,et al. Matching synchrosqueezing wavelet transform and application to aeroengine vibration monitoring[J].IEEE Transactions on Instrumentation and Measurement,2017,66(2):360-372
5 刘炳文,王铁,李国兴,等.工况特征参数对客车燃油经济性的影响[J].科学技术与工程,2018,18(17):181-186Liu Bingwen,Wang Tie,Li Guoxing,et al. Influence of operating condition characteristic parameters on fuel economy of the bus[J].Science Technology and Engineering,2018,18(17):181-186
6 田宏卫,林权,李洪军,等.一种基于相关性分析的故障风机损失发电量估计方法的研究[J].科学技术与工程,2016,16(11):185-188Tian Hongwei,Lin Quan,Li Hongjun,et al. Research on an estimation method of power generation loss of the fault wind turbine based on correlation analysis[J]. Science Technology and Engineering,2016,16(11):185-188
7 程超.基于时间序列法和回归分析法的改进月售电量预测方法研究[D].重庆:重庆大学,2016Cheng Chao. Improvement of monthly electricity sales forecasting method based on time-series method and regression method[D].Chongqing:Chongqing University,2016
8 Contreras J,Espinola R,Nogales F J,et al. ARIMA models to predict next-day electricity prices[J]. IEEE Power Engineering Review,2002,22(9):57-57
9 董大勇,刘珂言.基于ARIMA模型的工业品出厂价格指数预测与分析[J].统计与决策,2016(1):179-181Dong Dayong,Liu Keyan. Prediction and analysis of ex-factory price index of industrial products based on ARIMA models[J]. Statistics and Decision,2016(1):179-181
10 Khashei M,Bijari M. A novel hybridization of artificial neural networks and ARIMA models for time series forecasting[J]. Applied Soft Computing Journal,2011,11(2):2664-2675
11 Box G E P,Jenkins G M,Reinsel G C,et al. Time series analysis:forecasting and control,5th edition[J]. Journal of the Operational Research Society,2015,22(2):199-201
12 欧阳敏华. STAR模型下退势单位根检验统计量的比较[J].统计与决策,2017(23):19-22Ouyang Minhua. Comparative study on performance of de-trending unit root test in STAR models[J]. Statistics and Decision,2017(23):19-22
13 于寄语.时间序列的结构变化和单位根检验[D].武汉:华中科技大学,2017Yu Jiyu. The structural changes of time series models and unit root test[D]. Wuhan:Huazhong University of Science and Technology,2017
2 王俨剀,马进锐,廖明夫,等.发动机振动趋势预测模型研究[J].振动、测试与诊断,2014(3):516-523Wang Yankai,Ma Jinrui,Liao Mingfu,et al. Research on trend prediction model of engine vibration[J]. Journal of Vibration,Measurement and Diagnosis,2014(3):516-523
3 董欢.某型航空发动机中介轴承故障诊断技术研究[D].沈阳:沈阳航空航天大学,2017Dong Huan. Research on fault diagnosis technology of inteeshaft bearings in an aeroengine[D]. Shenyang:Shenyang Aerospace University,2017
4 Wang S,Chen X,Tong C,et al. Matching synchrosqueezing wavelet transform and application to aeroengine vibration monitoring[J].IEEE Transactions on Instrumentation and Measurement,2017,66(2):360-372
5 刘炳文,王铁,李国兴,等.工况特征参数对客车燃油经济性的影响[J].科学技术与工程,2018,18(17):181-186Liu Bingwen,Wang Tie,Li Guoxing,et al. Influence of operating condition characteristic parameters on fuel economy of the bus[J].Science Technology and Engineering,2018,18(17):181-186
6 田宏卫,林权,李洪军,等.一种基于相关性分析的故障风机损失发电量估计方法的研究[J].科学技术与工程,2016,16(11):185-188Tian Hongwei,Lin Quan,Li Hongjun,et al. Research on an estimation method of power generation loss of the fault wind turbine based on correlation analysis[J]. Science Technology and Engineering,2016,16(11):185-188
7 程超.基于时间序列法和回归分析法的改进月售电量预测方法研究[D].重庆:重庆大学,2016Cheng Chao. Improvement of monthly electricity sales forecasting method based on time-series method and regression method[D].Chongqing:Chongqing University,2016
8 Contreras J,Espinola R,Nogales F J,et al. ARIMA models to predict next-day electricity prices[J]. IEEE Power Engineering Review,2002,22(9):57-57
9 董大勇,刘珂言.基于ARIMA模型的工业品出厂价格指数预测与分析[J].统计与决策,2016(1):179-181Dong Dayong,Liu Keyan. Prediction and analysis of ex-factory price index of industrial products based on ARIMA models[J]. Statistics and Decision,2016(1):179-181
10 Khashei M,Bijari M. A novel hybridization of artificial neural networks and ARIMA models for time series forecasting[J]. Applied Soft Computing Journal,2011,11(2):2664-2675
11 Box G E P,Jenkins G M,Reinsel G C,et al. Time series analysis:forecasting and control,5th edition[J]. Journal of the Operational Research Society,2015,22(2):199-201
12 欧阳敏华. STAR模型下退势单位根检验统计量的比较[J].统计与决策,2017(23):19-22Ouyang Minhua. Comparative study on performance of de-trending unit root test in STAR models[J]. Statistics and Decision,2017(23):19-22
13 于寄语.时间序列的结构变化和单位根检验[D].武汉:华中科技大学,2017Yu Jiyu. The structural changes of time series models and unit root test[D]. Wuhan:Huazhong University of Science and Technology,2017