State prediction for the actuators of civil aircraft based on a fusion framework of relevance vector machine and autoregressive integrated moving average
Restricted accessResearch articleFirst published online May, 2018
State prediction for the actuators of civil aircraft based on a fusion framework of relevance vector machine and autoregressive integrated moving average
Relevance vector machine is a newly proposed and effective state prediction algorithm proved by practical applications; however, the accuracy of the single relevance vector machine model for the long-term prediction is unable to achieve satisfactory results with time goes by. Then, an autoregressive integrated moving average model is introduced to correct the prediction error caused by the single relevance vector machine, and a fusion framework based on the combination of relevance vector machine and autoregressive integrated moving average model is adopted to improve the accuracy of long-term prediction. In addition, a targeted approach for retraining the old model is put forward so that the state prediction model can be updated in time and suits the actual situation better. The effectiveness of the proposed fusion framework is illustrated via an aircraft actuator, and the experiments based on a model of civil aircraft actuator data set show that the proposed method yields a satisfied performance in state prediction of aircraft actuators.
HanYOhSChoiB. Fault detection and identification of aircraft control surface using adaptive observer and input bias estimator. IET Control Theory A2012; 6(10): 1367–1387.
2.
MaJNiSXieWet al. An improved strong tracking multiple-model adaptive estimation: a fast diagnosis algorithm for aircraft actuator fault. T I Meas Control2016; 38(7): 1–9.
3.
TianZLiSWangYet al. A network traffic hybrid prediction model optimized by improved harmony search algorithm. Neural Network World2015; 25(6): 669–686.
4.
A380. Technical training manual, A380 RR Trent 900 maintenance courses, February 2010.
5.
LiYTongSLiT. Observer-based adaptive fuzzy tracking control of MIMO stochastic nonlinear systems with unknown control directions and unknown dead zones. IEEE T Fuzzy Syst2015; 23(4): 1228–1241.
6.
GuoRGuoKDongJet al. Time-varying and anti-disturbance fault diagnosis for a class of nonlinear systems. Proc IMechE, Part I: J Systems and Control Engineering2015; 229(7): 573–586.
7.
LamJZhangBChenYet al. Reachable set estimation for discrete-time linear systems with time delays. Int J Robust Nonlin2015; 25(2): 269–281.
8.
NiuGYangB. Dempster-Shafer regression for multi-step-ahead time-series prediction towards data-driven machinery prognosis. Mech Syst Signal Pr2009; 23(3): 740–751.
9.
AwadMKhannaR. Support vector regression. Neu Inf Pro Lett Rev2007; 11(10): 203.
10.
TianZLiSWangYet al. A multi-model fusion soft sensor modelling method and its application in rotary kiln calcination zone temperature prediction. T I Meas Control2016; 38(1): 110–124.
11.
LiangLWangQChenY. Application of support vector machine in online monitoring of wastewater treatment based on combined kernel functions. In: Proceedings of the international conference on electrical and control engineering, Yichang, China, 16–18 September 2011, pp.3840–3843. New York: IEEE.
12.
TianZGaoXShiT. Combination kernel function least squares support vector machine for chaotic time series prediction. Acta Phys Sin2014; 63(16): 160508–160288.
13.
QinXZhaoQZhaoHet al. Prognostics of remaining useful life for lithium-ion batteries based on a feature vector selection and relevance vector machine approach. In: Proceedings of the international conference on prognostics and health management, Dallas, TX, 19–21 June 2017, pp.1–6. New York: IEEE.
14.
JiangJJingXLiMet al. Research on the performance of relevance vector machine for regression and classification. In: Proceedings of the advanced information technology, electronic and automation control conference, Chongqing, China, 19–20 December 2015, pp.758–762. New York: IEEE.
15.
TippingME. Sparse Bayesian learning and the relevance vector machine. J Mach Learn Res2001; 1(3): 211–244.
16.
HuXJiangJCaoDet al. Battery health prognosis for electric vehicles using sample entropy and sparse Bayesian predictive modeling. IEEE T Ind Electron2016; 63(4): 2645–2656.
17.
LiuFSongHQiQet al. Time series regression based on relevance vector learning mechanism. In: Proceedings of the international conference on wireless communications, networking and mobile computing, Dalian, China, 12–14 October, pp.1–4. New York: IEEE.
18.
NiuLZhaoJLiuM. Application of relevance vector regression model based on sparse Bayesian learning to long-term electricity demand forecasting. In: Proceedings of the international conference on mechatronics and automation, Changchun, China, 9–12 August 2009, pp.2363–2367. New York: IEEE.
19.
ZhaoJXuLLiuL. Equipment fault forecasting based on ARMA model. In: Proceedings of the international conference on mechatronics and automation, Harbin, China, 5–8 August 2007, pp.3514–3518. New York: IEEE.
20.
SuSZhangWZhaoS. Fault prediction for nonlinear system using sliding ARMA combined with online LS-SVR. Mathematical Problems in Engineering2014; 2014: 692848.
21.
LeeYTongL. Forecasting time series using a methodology based on autoregressive integrated moving average and genetic programming. Knowl-Based Syst2011; 24(1): 66–72.
22.
ChenH. A new method of load forecasting based on generalized autoregressive conditional heteroscedasticity model. Autom Electr Power Syst2007; 31(15): 51–54105.
23.
FujimuraHKimHTanJKet al. Posture estimation from kinect image using RVM regression analysis. In: Proceedings of the international conference on control, automation and systems, Busan, South Korea, 13–16 October 2015, pp.1540–1542. New York: IEEE.
24.
TippingME. The relevance vector machine. Adv Neur In2000; 12(3): 652–658.
25.
ChangMKangMPechtM. Prognostics-based LED qualification using similarity-based statistical measure with RVM regression model. IEEE T Ind Electron2017; 64(7): 5667–5677.
26.
YuHWuZChenDet al. Probabilistic prediction of bus headway using relevance vector machine regression. IEEE T Intell Transp2017; 18(7): 1772–1781.
27.
TianZLiSWangYet al. A prediction method based on wavelet transform and multiple models fusion for chaotic time series. Chaos Soliton Fract2017; 98: 158–172.
28.
BoroojeniKGAminiMHBahramiSet al. A novel multi-time-scale modeling for electric power demand forecasting: from short-term to medium-term horizon. Electr Pow Syst Res2017; 142: 58–73.
29.
PappasSSEkonomouLKaramousantasDCet al. Electricity demand loads modeling using autoregressive moving average (ARMA) models. Energy2008; 33(9): 1353–1360.
