Neural Network based Fault Diagnosis Methodfor Satellite Attitude Control System

Abstract

The closed-loop in control system usually brings difficulties for fault identification, because it may destroy the identification ability of the parameters andenhance the false alarm rate as well as the missed alarm rate,leading to the abnormality of multiple variables under the same faulty mode. Firstly, the effect of close loop is analyzed for the single-input single-output (SISO)system,while for the multiple-input multiple-output(MIMO)system the fault propagation is derived theoretically,and the influences on system variables are analyzed. Secondly,the neural network is used to construct the fault identification method. Finally,the mathematical simulation validates the negative effect of closed-loop on fault diagnosis,and the simulation of satellite attitude control systemverifies thattheproposed methodis more effective, comparing with the traditional ones.

Keywords

satellite control system / fault identification / closed-loop fault / deep learning network / moving window

References

[1] 闻竞竞, 黄道. 故障诊断方法综述[C]//全国第18届计算机技术与应用(CACIS)学术会议. 宁波:CACIS, 2007.
[2] MEHRA R K,PESCHON J. An innovations approach to fault detection and diagnosis in dynamic systems[J]. Automatica, 1971, 7(5):637-640.
[3] 周东华. 动态系统的故障诊断技术[C]//2007-2008控制科学与工程学科发展报告. 北京:中国科学技术出版, 2008.
[4] 王海清, 宋执环, 王慧. PCA过程监测方法的故障检测行为分析[J]. 化工学报, 2002, 53(3):297-301. WANG H Q, SONG Z H, WANG H. Fault detection behavior analysis of PCA-based process monitoring approach[J]. Journal of Chemical Industry and Engineering, 2002, 53(3):297-301.
[5] 邢琰, 吴宏鑫, 王晓磊, 等. 航天器故障诊断与容错控制技术综述[J]. 宇航学报, 2003, 24(3):221-226. XING Y, WU H X, WANG X L, et al. Review of spacecraft fault diagnosis and fault-tolerant control technology[J]. Journal of Astronautics, 2003, 24(3):221-226.
[6] FRANK P M, DING X. Survey of robust residual generation and evaluation methods in observer-based fault detection systems[J]. Journal of Process Control, 1997, 7(6):403-424.
[7] 周东华, 胡艳艳. 闭环系统故障诊断技术综述[J]. 自动化学报, 2013, 39(11):1933-1943. ZHOU D H, HU Y Y. Review on fault diagnosis techniques for closed-loop systems[J]. Acta Automatica Sinica, 2013, 39(11):1933-1943.
[8] MACGREGOR J F, FOGAL D T. Closed-loop identification:the role of the noise model and prefilters[J]. Journal of Process Control, 1995, 5(3):163-171.
[9] GHANTASALA S, EL-FARRA N H. Model-based fault isolation and reconfigurable control of transport-reaction processes with actuator faults[C]//American Control Conference. New York, USA:IEEE, 2007.
[10] HAMAD A, YU D, GOMM J B. Fault detection and isolation for engine under closed-loop control[C]//Proceedings of 2012 UKACC International Conference on Control. Cardiff, UK:IEEE, 2012.
[11] LE T T, WATTON J, PHAM D T. Fault classification of fluid power systems using a dynamics feature extraction technique and neural networks[J]. Proceedings of the Institution of Mechanical Engineers, Part I:Journal of Systems and Control Engineering, 1998, 212(2):87-97.
[12] WANG J, QIN S J. Closed-loop subspace identification using the parity space[J]. Automatica, 2006, 42(2):315-320.
[13] WANG K, CHEN J, SONG Z. Data-driven sensor fault diagnosis systems for linear feedback control loops[J]. Journal of Process Control, 2017(54):152-171.
[14] 卫洁洁, 杨喜旺, 黄晋英, 等. 基于神经网络的滚动轴承故障诊断[J]. 组合机床与自动化加工技术, 2017(11):93-96. WEI J J, YANG X W, HUANG J Y, et al. Rolling bearing fault diagnosis based on the deep neural networks[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2017(11):93-96.
[15] 王新颖, 宋兴帅, 杨泰旺. 学习神经网络在管道故障诊断中的应用研究[J]. 安全与环境工程, 2018, 25(1):137-142. WANG X Y, SONG X S, YANG T W. Application of depth learning neural network in pipeline fault diagnosis[J]. Safety and Environmental Engineering, 2018, 25(1):137-142.
[16] 董晴, 宋威. 基于粒子群优化的神经网络分类算法[J]. 传感器与微系统, 2017, 36(9):143-150. DONG Q, SONG W. Deep neural network classification algorithm based on particle swarm optimization[J]. Transducer and Microsystem Technologies, 2017, 36(9):143-150.
[17] 刘丹枫, 刘建霞. 面向学习过拟合问题的神经网络模型[J]. 湘潭大学自然科学学报, 2018, 40(2):96-99. LIU D F, LIU J X. A neural network model for the overfitting problem in deep learning[J]. Natural Science Journal of Xiangtan University, 2018, 40(2):96-99.
[18] HE Z, SHARDT Y A W, WANG D, et al. An incipient fault detection approach via detrending and denoising[J]. Control Engineering Practice, 2018(74):1-12.
[19] 谢彦红, 孙呈敖, 李元. 基于滑动窗口SVDD的间歇过程故障监测[J]. 信息与控制, 2015, 44(5):531-537. XIE Y H, SUN C A, LI Y. Intermittent process fault monitoring based on sliding window SVDD[J]. Information and Control, 2015, 44(5):531-537.
[20] 何章鸣. 非预期故障的数据驱动诊断方法研究[D]. 长沙:国防科技大学, 2015. HE Z M. Research on data-driven diagnosis methods for unanticipated fault[D]. Changsha:National University of Defense Technology, 2015.