Military aircraft components state parameter prediction using deep belief learning
LI Junliang1.2 TENG Kenan1 XIA Fei2.3
Author information+
1. Scientific Research Departments , Naval Aeronautical University, Yantai 264001, China;
2. The 92635th Unit of Navy , Qingdao 266041, China;
3.State Grid Liaoyang Electric Power Supply Company, Liaoyang 111000, China
Military aircraft state monitoring data have the characteristics of multidimensionality, nonlinearity and strong coupling, and monitoring data samples are of large capacity with high updating rate. So, existing state prediction models are difficult to meet the engineering requirements of high precision and realtime performance. How to predict military aircraft status informations accurately and fast is a difficult problem which needs to be settled. The paper uses the deep belief learning theory and simulated annealing algorithm to present a state prediction model for military aircraft key components. The research process consists of three stages: choosing monitoring parameters of the aircraft key components under different mission profile in order to design network samples; developing a deep learning network and prediction model; validating the model with testing date. Lastly, an aircraft engine was employed to demonstrate the efficacy of the proposed approach. The predicted results were compared with those by the SVM and ELMAN. It is found that the average error between the predicted and the measured values based on the proposed approach is less than 0.04, much smaller than that of the SVM and ELMAN method, and its running time is shorter than the above two methods, which proves the feasibility and effectiveness of the proposed approach.
LI Junliang1.2 TENG Kenan1 XIA Fei2.3.
Military aircraft components state parameter prediction using deep belief learning[J]. Journal of Vibration and Shock, 2018, 37(6): 61-67
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 彭宇,刘大同.数据驱动故障预测和健康管理综述[J].仪器仪表学报,2014,35(3):481-495
PENG Y. LIU D T. Data-driven prognostics and health management :A re view of recent advances[J],Chinese journal Scientific instrument,2014,35(3):481-495(in Chinese)
[2] 李向前.复杂装备故障预测与健康管理关键技术研究[D].北京,北京理工大学,2014,06:6-12
LI X Q .Research on Key Technology of Fault Prognos-tic and Health Management for Complex Equipment[D]. Beijing, Beijing Institute of Technology,2014,06:6-12(in Chinese)
[3] 王少萍.大型飞机机载系统预测与健康管理技术[J].航空学报,2015,35(6):1459-1472
WANG S P. Prognostics and health management key technology of aircraft airborne system[J]. ACTA AERONAUTICA ET ASTRONAUTICA SINICA, 2015,35(6):1459-1472
[4] 赵宇.可靠性数据分析[M].北京,国防工业出版社,2011:33-55
ZHAO Y.Data Analysis of Reliability[M].Beijing, Na-tional Defense Industry Press, 2011:33-55(in Chinese)
[5] 周忠宝,马超群,周经伦.基于动态贝叶斯的动态故障树分析[J].系统工程理论与实践,2008,32(2):36-42
ZHOU Z B,MA C Q. Dynamic fault tree analysis based on dynamic Bayesian networks[J].Systems Engineering Theory &Practice, 2008,32(2):36-42(in Chinese)
[6] Mirikitani D T,NiKolaev N.Recursive Bayesian Re-current Neural Networks for Time-Series Model-ing[J].IEEE Transactions on Neural Networks,2010,21(2):262-274.
[7] ZHAO W G,Jianzhou Wang,Haiyan Lu. Combining forecasts of electricity consumption in China with time-varying weights updated by a high-order Markov chain model[J].Journal of management science,2014,45:80-91.
[8] Sapankevych N,Sankar R.Time series prediction using Support Vector Machines: A Survey[J]. Computational Intelligence Magazine,2009,4(02):24-38.
[9] 徐圆,刘莹,朱群雄.基于多元时滞序列驱动的复杂过程故障预测方法应用研究[J], 化工学报,2013,64(12) : 4290-4295.
XU Y.LIU Y,ZHU Q X.A complex process fault prog-nosis approach based on multivariate delayed se-quences[J]. CIESC Journal,2013 ,64 (12):42904295 (in Chinese)
[10] Mirikitani D T,NiKolaev N.Recursive Bayesian Re-current Neural Networks for Time-Series Modeling[J]. IEEE Transactions on Neural Networks,2010,21(2):262-274.
[11] GONCALVES L F,BOSA J L,BALEN T R,et al. Fault detection, siagnosis and prediction in electrical valves using self-organizing maps[J], Journal of Elec-tronic Testing,2011,27(4): 551-564
[12] 张琪,吴亚锋,李锋.基于遗传神经网络的旋转机械故障预测方法研究[J].计算机测量与控制,2016,24(2):11-13
ZHANG Q,WU YF,LI F. Research on mechanical fault prediction based on improved neural network[J]. Com-puter measurement & control,2016,24(2):11-13(in Chi-nese)
[13] 李瑞莹,康锐. 基于神经网络的故障率预测方法[J].航空学报,2008,29(2):357-362
LI R Y, KANG R. Failure Rate Forecasting Method Based on Neural Networks[J].ACTA AERONAUTICA ET ASTRONAUTICA SINICA, 2008,29(2):357-362(in Chinese)
[14] 张磊,李行善,于劲松.一种基于二元估计与粒子滤波的故障预测算法[J].北京航空航天大学学报,2008,34(7):798-802
ZHANG L,LI X S,YU J S.Fault prognostic algorithm based on dual estimation and particle filter[J].Journal of Beijing University of Aeronautics and Astronautics, 2008,34(7):798-802(in Chinese)
[15] 蔡志强,孙树栋, 司书宾等.基于FMECA的复杂装备故障预测贝叶斯网络建模[J].系统工程理论与实践, 2013,33(1):187-192
CAI Z Q,SUN S D, SI S B, et al. Modeling of failure prediction Bayesian Network Based on FMECA[J]. Systems Engineering Theory &Practice, 2013,33(1):187-192
[16] HINTON G E,SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science,2006,313(5786):504-507.
[17] Arel L,Rose DC,Karnowski TP. Deep machine learning a new frontier in artificial intelligence research[J]. Computational Intelligence Magazine 2010,5(4): 8-13
[18] 郭丽丽,丁世飞.深度学习研究进展[J].计算机科学, 2015,42(5):28-33
GUO L L, DING S F. Research progress on deep learn-ing[J].Computerscience,2015,42(5):28-33, (in Chinese)
[19] Prasanna T, Pingfeng W. Failure diagnosis using deep belief learning based health state classification[J]. Re-liability Engineering and System Safety,115 (2013,124-135)
[20] 雷亚国,贾 峰,周 昕 等.基于深度学习理论的机械装备大数据健康检测方法[J].机械工程学报,2016,51(21):49-56
LEI Y G,JIA F,ZHOU X, et al. A Deep Learning-based Method for Machinery Health Monitoring with Big Da-ta[J]. JOURNAL OF MECHANICAL ENGINEERING, 2016,51(21):49-56(in Chinese)
[21] 冯通,基于深度学习的航空飞行器故障自助检测研究[J].计算机仿真,2015,32(11):119-122
FENG T,A Fault Detection Algorithm of aviation Aircraft based on Deep Learning[J],Computer si-mulation 2015,32(11):119-122 (in Chinese)
[22] HINTON G E.A practical guide to training restricted Boltzmann machines[J] .Momentum, 2010,9:1.
[23] Lee H,Grosse R, Ng AY. Convolutional deep belief networks for scalable unsupervised learning of hierar-chical representations[C]. //International conference on machine learning. Montreal, Canada,2009:609-616
[24] 王利民,马乃仓.军用飞机最低技术放飞条件逻辑决断分析方法研究[J].计算机与现代化,2012 (10):200-206
WANG L M,MA N C. Study on Logic Decision Method of Making Military Aircraft Minimum Technique Flight Condition[J]. Computer and modern, 2012 (10):200-206(in Chinese)
[25] 孙闯,何正嘉,张周锁,等. 基于状态信息的航空发动机运行可靠性评估[J].机械工程学报, 2013, 49(6):30-37.
SUN C, HE Z J, ZHANG Z S,et al.Operating relia-bility assessment for aero-engine based on condition monitoring information[J]. Journal of Mechanical En-gineering, 2013, 49(6):30-37. (in Chinese)
[26] 王华伟,高军,吴海桥.基于竞争失效的航空发动机剩余寿命预测[J].机械工程学报,2014,50(6):197-205
WANG H W, GAO J, WU H Q. Residual Remaining Life Prediction Based on Competing Failures for Aircraft Engines[J].JOURNAL OF MECHANICAL ENGINEERING, 2014,50(6):197-205 (in Chinese)
[27] 唐崇凯,曲建岭,高峰.飞参判据及应用[J].计算机工程,2011,37(10):280-283
Tang C K,QU J L,GAO F.Flight Data Criterion and Its Application[J].Computer Engineering,2011,37(10):280-283 (in Chinese)
[28] 李军亮,胡国才.基于ELMAN网络的某型直升机飞行状态识别[J].火力与指挥控制,2015,40(12):57-60
LI J L,HU G C. Helicopter Flight Condition Recog-nitionBased on Elman Neural Network[J].Fire Control & Command Control, 2015,40(12):57-60(in Chinese)
[29] 李国勇,杨丽娟.神经.模糊.预测控制及其MATLAB 实现[M].北京:电子工业出版社,2013: 85-127
LIJ,YANG L J. Nerve. fuzzy control and The MATLAB predictive [M].Beijing,.Publishing House of Electronics Beijing ,Industry,2013:85-127(in Chinese)
[30] 徐玉秀,杨文平,吕轩,等.基于支持向量机的汽车发动机故障诊断研究[J].振动与冲击,2013,32(8):143-146
XU Yu-xiu, YANG Wen-ping, LU Xuan, etal. Fault di-agnosis for a car engine based on support vector ma-chine[J].Journal of vibration and shock, 2013,32(8):143-146
[31] 袁胜发,储福磊.支持向量机及其在故障诊断中的应用[J].振动与冲击,2007,26(11):29-35
YUAN Sheng-fa, CHU Fu-lei. Support vector machine and its application in machine fault diagnosis[J]. Journal of vibration and shock, 2007,26(11):29-35
[32] 陈昌,汤宝平,吕中亮.基于威布尔分布极最小向量机的滚动轴承退化趋势预测[J].振动与冲击,2014,33(2):52-56
CHEN Chang, TANG Bao-ping, LV Zhong-liang. De-gradation trend prediction of rolling bearings based on weibull distribution and least squares support vector machine[J]. Journal of vibration and shock, 2014,33(2):52-56