Combined Prediction on Avionics State Optimized by MAGA

doi:10.3969/j.issn.1000-1093.2016.04.022

Abstract

Abstract: A combined prediction method based on hidden Markov model (HMM) and least square support vector machine (LS-SVM) is presented for prediction of avionics states. Multi-agent genetic algorithm (MAGA) is used to estimate HMM parameters to overcome the problem of that Baum-Welch algorithm is easy to fall into local optimal solution. The conditional probability of states is introduced into the HMM modeling to reduce the effect of uncertainty factor. MAGA is used to estimate the parameters of LS-SVM model, and the pruning algorithm is used for achieving the sparse approximation of LS-SVM in parameter estimation, thus achieving the objective of improving the generalization performance of LS-SVM. On this basis, a combined prediction model of avionics state is established. The analysis results show the combined prediction model has high prediction accuracy, calculating speed and stability.

Key words: instrument and equipment of aerocraft, parameter estimation, hidden Markov model, least square support vector machine, multi-agent genetic algorithm, state prediction

CLC Number:

V241

ZHAO Jian-zhong， OUYANG Zhong-hui， ZHANG Lei，ZHAO Jian-yin. Combined Prediction on Avionics State Optimized by MAGA[J]. Acta Armamentarii, 2016, 37(4): 727-734.

References

［1］彭宇,刘大同,彭喜元. 故障预测与健康管理技术综述［J］.电子测量与仪器学报, 2010, 24(1): 1-9.
PENG Yu, LIU Da-tong, PENG Xi-yuan. A review: prognostics and health management ［J］. Journal of Electronic Measurement and Instrument, 2010, 24(1): 1-9. (in Chinese)
［2］ Sheppard J W, Kaufman M A,Wilmering T J. IEEE standards for prognostics and health management［C］∥Proceedings of IEEE AUTOTESTCON. Salt Lake City,Utah,US:IEEE,2008:97-103.
［3］卓东风,原媛. 小波包变换和隐马尔科夫模型(HMM)在液压系统故障预测中的应用［J］.山西大学学报：自然科学版, 2013，36(3):357-362.
ZHUO Dong-feng,YUAN Yuan. Application of hydraulic system fault prediction based in wavelet packet transform and hidden Markov model(HMM) ［J］. Journal of Shanxi University: Natual Science Edition, 2013,36(3):357-362. (in Chinese)
［4］王久崇,樊晓光,盛晟,等. 改进的蜂群LS-SVM故障预测［J］. 空军工程大学学报：自然科学版, 2013,14(1):16-19.
WANG Jiu-chong,FAN Xiao-guang, SHENG Sheng, et al. Improved artificial bee colony LS-SVM fault prediction［J］. Journal of Air Force Engineering University: Natual Science Edition, 2013,14(1):16-19. (in Chinese)
［5］ Jiang H,　Li X W, Liu C J. Large margin hidden Markov models for speech recognition［J］.IEEE Transactions on Audio, Speech and Language Processing, 2006,9(5):1584-1594.
［6］谢松汕,许宝杰,吴国新,等.基于HMM/SVM的风电设备故障趋势预测方法研究［J］.计算机测量与控制, 2014, 22(1):39-41.
XIE Song-shan, XU Bao-jie,WU Guo-xin, et al. Wind power electricity generation facility fault trend prediction method study based on HMM/SVM ［J］. Computer Measurement ＆ Control, 2014, 22(1):39-41. (in Chinese)
［7］柳新民,邱静,刘冠军. 基于HMM-SVM的故障诊断模型及应用［J］.仪器仪表学报, 2006, 27(1): 45-53.
LIU Xin-min, QIU Jing, LIU Guan-jun. Hybrid HMM and SVM approach for fault diagnosis ［J］. Chinese Journal of Scientific Instrument, 2006, 27(1): 45-53.(in Chinese)
［8］ He X, Li D. A new look at discriminative training for hidden Markov models［J］. Pattern Recognition Letters, 2007, 28(5): 1285-1294.
［9］张星辉,康建设,高存明,等. 基于MoG-HMM的齿轮箱状态识别与剩余使用寿命预测研究［J］.振动与冲击, 2013,32(15):20- 31.
ZHANG Xing-hui,KANG Jian-she, GAO Cun-ming, et al. Gearbox state identification and remaining useful life prediction based on MoG-HMM［J］. Journal of Vibration and Shock, 2013,32(15): 20- 31. (in Chinese)
［10］钟伟才,刘静,焦李成. 多智能体遗传算法用于线性系统逼近［J］.自动化学报, 2004,30(6):933-938.
ZHONG Wei-cai, LIU Jing, JIAO Li-cheng. Optimal approximation of linear systems by multi-agent genetic algorithm ［J］. Acta Automatica Sinica, 2004,30(6):933-938.(in Chinese)
［11］谢燕丽,许青林,姜文超. 一种基于交叉和变异算子改进的遗传算法研究［J］. 计算机技术与发展, 2014, 24(4): 80-83.
XIE Yan-li,XU Qing-lin,JIANG Wen-chao. An improved genetic algorithm based on crossover and mutation operators［J］. Computer Technology and Development, 2014, 24(4): 80-83. (in Chinese)
［12］邓乃扬,田英杰. 支持向量机-理论、算法与拓展［M］.北京: 科学出版社, 2009.
DENG Nai-yang, TIAN Ying-jie. Support vector machine-theory, algorithm and development ［M］. Beijing: Science Press, 2009.(in Chinese)
［13］ Cortes C, Vapnik V N. Support vector networks ［J］.Machine Learning,1995,20(3):273-297.
［14］李丽敏,王仲生,姜洪开. 基于多状态MOG-HMM和Viterbi的航空发动机突发故障预测［J］. 振动、测试与诊断, 2014, 34(2): 310-399.
LI Li-min, WANG Zhong-sheng, JIANG Hong-kai. Aero-engine abrupt failure prognosis based on multi-states MOG-HMM and Viterbi algorithm［J］. Journal of Vibration and Shock ＆ Diagnosis, 2014,34(2): 310-399. (in Chinese)
［15］ Jiao L C, Bo L F, Wang L. Fast sparse approximation for least squares support vector machine ［J］. IEEE Transactions on Neural Networks, 2007, 18(3): 685-697.
［16］ Rabiner L R, Huang B H. An introduction to hidden Markov models［J］. IEEE Signal Processing Magazine, 1986, 3(1): 4-16.

[1]	WANG Qian, HOU Hong, YIN Shao-ping, CHEN Zhi-fei. Research on Double Reference Source Estimation Method for 3-dimension Space of Near-field Underwater Moving Target withLinear Track [J]. Acta Armamentarii, 2016, 37(4): 677-683.
[2]	XU Zhou, ZHANG Hao, CHENG Shui-ying. Parameter Estimation of Unknown Envelope Multicomponent LFM Signal [J]. Acta Armamentarii, 2016, 37(3): 462-470.
[3]	CHENG Jie， WANG Xiao-ming, YU Ji-yan, JIA Fang-xiu. Parameter Estimation of Axial Dual-spin System in a Trajectory Correction Projectile with Decoupled Canards [J]. Acta Armamentarii, 2016, 37(10): 1812-1819.
[4]	DENG Bing, LUAN Jun-bao. Study of Reconnaissance Reception Algorithm of Wide-band Channelization in the Fractional Fourier Domain [J]. Acta Armamentarii, 2015, 36(6): 1040-1045.
[5]	DENG Bing， LUAN Jun-bao， TANG Guang-sheng. Error Analysis of Instantaneous Frequency Estimation Based on Short-time Fractional Fourier Transform [J]. Acta Armamentarii, 2015, 36(11): 2104-2110.
[6]	ZHU Tian-jun，KONG Xian-wei，LI Bin. Research on Driving Status Recognition of Heavy Duty Vehicle Based on Double-layer HMM Model [J]. Acta Armamentarii, 2015, 36(10): 1832-1840.
[7]	CHEN Lei， CHEN Dian-ren， LIU Ying. A New Chirp Signal Parameter Estimation Algorithm [J]. Acta Armamentarii, 2014, 35(2): 207-213.
[8]	LUO Yan-yan, WANG Zhen, LI Xiao-ning, LIU Lei. Accelerated Thermal Cycling Test and Failure Analysis of Electrical Connectors [J]. Acta Armamentarii, 2014, 35(11): 1908-1913.
[9]	ZHU Kai-ran, SU Tao, HE Xue-hui. Research Advances in Explosives Detection Technique Based on Nuclear Quadrupole Resonance [J]. Acta Armamentarii, 2013, 34(12): 1575-1588.
[10]	XIAO Xuan, WANG Qing-zhe, CHENG Yuan，FU Meng-yin, LIU Tong. High Accuracy Navigation Algorithm for Tightly Coupled INS/Odometer [J]. Acta Armamentarii, 2012, 33(4): 395-400.
[11]	WU Jing， WU Xiao-yan₁， TENG Jiang-chuan₁， CHEN Yong-xing₁. Simulation Model Validation Based on Continuous Hidden Markov Model [J]. Acta Armamentarii, 2012, 33(3): 367-372.
[12]	HE Guang-lin，HE Qing-zhe. Characteristic Research on Runaway Escapement Driven by Two Slide-blocks [J]. Acta Armamentarii, 2009, 30(2): 134-139.
[13]	LIU Feng，SUN Da-peng, HUANG Yu, TAO Ran, WANG Yue. Fast Parameter- Estimation of LFM Signal Based on Improved Combined WVD and Randomized Hough Transform [J]. Acta Armamentarii, 2009, 30(12): 1642-1646.
[14]	FU Yong-ling, HAN Guohui, WANG Zhan-lin,CHEN Juan. Research on Optimization Method for Accelerated Life Test of CQ2-series Cylinder [J]. Acta Armamentarii, 2009, 30(11): 1493-1498.
[15]	FAN Chao, LI Ying-cai, YI Hong-wei. Influence of Velocity-Height Ratio of Satellite on the TDICCD Camera [J]. Acta Armamentarii, 2007, 28(7): 817-821.