This paper proposed a multi-innovation Nesterov accelerated gradient (MNAG) parameter identification method for the autoregressive exogenous (ARX) model. First, a momentum acceleration term is added stochastic gradient descent (SGD) algorithm to increase the convergence rate of the SGD. Second, the parameter updating process is expanded from a single batch of current information iteration to the multiple batches of both previous and current information iteration, which extended the algorithm from single-innovation Nesterov accelerated gradient (NAG) to multi-innovation NAG parameter identification method. That enhances the algorithm’s anti-noise and anti-abnormal data abilities, and its data utilization rate. Then, the convergence of the MNAG parameter identification method is proven. The effectiveness of the MNAG parameter identification method is verified by numerical simulation and the rotational speed system of a ring-pendulum double-sided polisher.
BouzraraKGarnaTRagotJ, et al. (2012) Decomposition of an ARX model on Laguerre orthonormal bases. ISA Transactions51: 848–860.
2.
ChenJDingF (2011) Modified stochastic gradient identification algorithms with fast convergence rates. Journal of Vibration and Control17: 1281–1286.
3.
ChenJDingFLiuY, et al. (2018) Multi-step-length gradient iterative algorithm for equation-error type models. Systems & Control Letters115: 15–21.
4.
ChenJLiuYDingF, et al. (2020a) Gradient-based particle filter algorithm for an ARX model with nonlinear communication output. IEEE Transactions on systems Man Cybernetics-systems50: 2198–2207.
5.
ChenJZhuQLiuY (2020b) Modified Kalman filtering based multi-step-length gradient iterative algorithm for ARX models with random missing outputs. Automatica118: 109034.
6.
DingF (2010) Several multi-innovation identification methods. Digital Signal Processing20: 1027–1039.
7.
DingF (2023) Least squares parameter estimation and multi-innovation least squares methods for linear fitting problems from noisy data. Journal of Computational and Applied Mathematics426: 115107.
8.
DingFChenT (2007) Performance analysis of multi-innovation gradient type identification methods. Automatica43(1): 1–14.
9.
DingFLiuPLiuG (2010) Multi-innovation least-squares identification for system modeling. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)40(3): 767–778.
10.
DingFLiuGLiuX (2011) Parameter estimation with scarce measurements. Automatica47: 1646–1655.
11.
DingFLvLPanJ, et al. (2020) Two-stage gradient based iterative estimation methods for controlled autoregressive systems, using the measurement data. International Journal of control automation and systems18: 886–896.
12.
DingFXuLZhangX, et al. (2023) Filtered auxiliary model recursive generalized extended parameter estimation methods for Box–Jenkins systems by means of the filtering identification idea. International Journal of Robust and Nonlinear Control33(10): 5510–5535.
13.
GoodwinGSinK (1984) Adaptive Filtering, Prediction and Control. New Jersey: Englewood Cliffs.
14.
GultekinAKilicaslanS (2022) Estimation of dynamic model of a missile fin with freeplay by using system identification methods. Journal of the Faculty of Engineering and Architecture of GAZI University37: 1899–1913.
15.
IkedaAFujitaKTakewakiI (2014) Story-wise system identification of actual shear building using ambient vibration data and ARX model. Eearthquakes and Structures7: 1093–1118.
16.
JinJDuanZOkaK (2016) Model identification and analysis for parallel permanent magnetic suspension system based on ARX model. International Journal of Applied Electromagnetics and Mechanics52: 145–152.
17.
JingS (2022) Identification of an ARX model with impulse noise using a variable step size information gradient algorithm based on the kurtosis and minimum Renyi error entropy. International Journal of Robust and nonlinear control32: 1672–1686.
18.
KhanMBaigDAshrafB, et al. (2022) Dynamic modeling of a nonlinear two-wheeled robot using data-driven approach. Processes10: 524.
19.
LiuYYuLDingF (2010) Multi-innovation extended stochastic gradient algorithm and its performance analysis. Circuits, Systems, and Signal Processing29(4): 649–667.
20.
MaoYDingF (2016) Data filtering-based multi-innovation stochastic gradient algorithm for nonlinear output error autoregressive systems. Circuits, Systems, and Signal Processing35: 651–667.
21.
MaoYDingFYangE (2017) Adaptive filtering-based multi-innovation gradient algorithm for input nonlinear systems with autoregressive noise. International Journal of Adaptive Control and Signal Processing31: 1388–1400.
22.
OuyangHShihSWuC (2017) Optimal combinations of non-sequential regressors for ARX-based typhoon inundation forecast models considering multiple objectives. Water9(7): 519.
23.
PopovRGeorgievАDzhonovaA (2016) Parameter estimation of borehole thermal properties using artificial intelligence methods. Bulgarian Chemical Communications48: 88–95.
24.
QinYPengHZhouF, et al. (2015) Nonlinear modeling and control approach to magnetic levitation ball system using functional weight RBF network-based state dependent ARX model. Journal of the Franklin Institute352: 4309–4338.
25.
SoloV (1979) The convergence of AML. IEEE Transactions on Automatic Control24(6): 958–962.
26.
WanLDingF (2019) Decomposition- and gradient-based iterative identification algorithms for multivariable systems using the multi-innovation theory. Circuits, Systems, and Signal Processing38: 2971–2991.
27.
WangSDingR (2013) Three-stage recursive least squares parameter estimation for controlled autoregressive auto regressive systems. Applied Mathematical Modeling37: 7489–7497.
28.
WofiszHKullTMMullerD, et al. (2020) Self-learning model predictive control for dynamic activation of structural thermal mass in residential buildings. Energy and Buildings207: 109–542.
29.
WuJPengHChenQ, et al. (2014) Modeling and control approach to a distinctive quadrotor helicopter. ISA Transactions53: 173–185.
30.
XuL (2023) Parameter estimation for nonlinear functions related to system responses. International Journal of Control Automation and Systems21(3): 1780–1792.
31.
XuLDingF (2017) Parameter estimation algorithms for dynamical response signals based on the multi-innovation theory and the hierarchical principle. IET Signal Processing11: 228–237.
XuLDingFGuY, et al. (2017) A multi-innovation state and parameter estimation algorithm for a state space system with d-step state-delay. Signal Processing140: 97–103.
34.
XuLDingFWanL, et al. (2020a) Separable multi-innovation stochastic gradient estimation algorithm for the nonlinear dynamic responses of systems. International Journal of Adaptive Control and Signal Processing34(7): 937–954.
35.
XuWPengHTianX, et al. (2020b) DBN based SD-ARX model for nonlinear time series prediction and analysis. Applied Intelligence50: 4586–4601.
36.
XuLDingFYangE (2021) Auxiliary model multi-innovation stochastic gradient parameter estimation methods for nonlinear sandwich systems. International Journal of Robust and Nonlinear Control31(1): 148–165.
37.
ZardianMAyobA (2015) Intelligent modelling and active vibration control of flexible manipulator system. Journal of Vibroengineering17: 1879–1891.
