Modeling a nonlinear process using the exponential autoregressive time series model

Huan Xu; Feng Ding; Erfu Yang

doi:10.1007/s11071-018-4677-0

Modeling a nonlinear process using the exponential autoregressive time series model

Huan Xu, Feng Ding^*, Erfu Yang

^*Corresponding author for this work

Design, Manufacturing And Engineering Management

Research output: Contribution to journal › Article › peer-review

42 Citations (Scopus)

31 Downloads (Pure)

Abstract

The parameter estimation methods for the nonlinear exponential autoregressive (ExpAR) model are investigated in this work. Combining the hierarchical identification principle with the negative gradient search, we derive a hierarchical stochastic gradient algorithm. Inspired by the multi-innovation identification theory, we develop a hierarchical-based multi-innovation identification algorithm for the ExpAR model. Introducing two forgetting factors, a variant of the hierarchical-based multi-innovation identification algorithm is proposed. Moreover, to compare and demonstrate the serviceability of these algorithms, a nonlinear ExpAR process is taken as an example in the simulation.

Original language	English
Pages (from-to)	2079-2092
Number of pages	14
Journal	Nonlinear Dynamics
Volume	95
Issue number	3
Early online date	6 Dec 2018
DOIs	https://doi.org/10.1007/s11071-018-4677-0
Publication status	Published - 28 Feb 2019

Funding

Acknowledgements This work was supported by the 111 Project (B12018), the National Natural Science Foundation of China (No. 61273194) and the National First-Class Discipline Program of Light Industry Technology and Engineering (LITE2018-26).

Keywords

hierarchical identification
multi-innovation identification
negative gradient search
nonlinear ExpAR model
parameter estimation

Access to Document

10.1007/s11071-018-4677-0

Xu-etal-ND-2019-Modeling-a-nonlinear-process-using-the-exponential-autoregressiveAccepted author manuscript, 318 KB

Cite this

@article{0d8b0a65a5f94f99851024b01dfd5164,

title = "Modeling a nonlinear process using the exponential autoregressive time series model",

abstract = "The parameter estimation methods for the nonlinear exponential autoregressive (ExpAR) model are investigated in this work. Combining the hierarchical identification principle with the negative gradient search, we derive a hierarchical stochastic gradient algorithm. Inspired by the multi-innovation identification theory, we develop a hierarchical-based multi-innovation identification algorithm for the ExpAR model. Introducing two forgetting factors, a variant of the hierarchical-based multi-innovation identification algorithm is proposed. Moreover, to compare and demonstrate the serviceability of these algorithms, a nonlinear ExpAR process is taken as an example in the simulation.",

keywords = "hierarchical identification, multi-innovation identification, negative gradient search, nonlinear ExpAR model, parameter estimation",

author = "Huan Xu and Feng Ding and Erfu Yang",

year = "2019",

month = feb,

day = "28",

doi = "10.1007/s11071-018-4677-0",

language = "English",

volume = "95",

pages = "2079--2092",

journal = "Nonlinear Dynamics",

issn = "0924-090X",

publisher = "Springer Netherlands",

number = "3",

}

TY - JOUR

T1 - Modeling a nonlinear process using the exponential autoregressive time series model

AU - Xu, Huan

AU - Ding, Feng

AU - Yang, Erfu

PY - 2019/2/28

Y1 - 2019/2/28

N2 - The parameter estimation methods for the nonlinear exponential autoregressive (ExpAR) model are investigated in this work. Combining the hierarchical identification principle with the negative gradient search, we derive a hierarchical stochastic gradient algorithm. Inspired by the multi-innovation identification theory, we develop a hierarchical-based multi-innovation identification algorithm for the ExpAR model. Introducing two forgetting factors, a variant of the hierarchical-based multi-innovation identification algorithm is proposed. Moreover, to compare and demonstrate the serviceability of these algorithms, a nonlinear ExpAR process is taken as an example in the simulation.

AB - The parameter estimation methods for the nonlinear exponential autoregressive (ExpAR) model are investigated in this work. Combining the hierarchical identification principle with the negative gradient search, we derive a hierarchical stochastic gradient algorithm. Inspired by the multi-innovation identification theory, we develop a hierarchical-based multi-innovation identification algorithm for the ExpAR model. Introducing two forgetting factors, a variant of the hierarchical-based multi-innovation identification algorithm is proposed. Moreover, to compare and demonstrate the serviceability of these algorithms, a nonlinear ExpAR process is taken as an example in the simulation.

KW - hierarchical identification

KW - multi-innovation identification

KW - negative gradient search

KW - nonlinear ExpAR model

KW - parameter estimation

UR - http://www.scopus.com/inward/record.url?scp=85058155605&partnerID=8YFLogxK

U2 - 10.1007/s11071-018-4677-0

DO - 10.1007/s11071-018-4677-0

M3 - Article

AN - SCOPUS:85058155605

SN - 0924-090X

VL - 95

SP - 2079

EP - 2092

JO - Nonlinear Dynamics

JF - Nonlinear Dynamics

IS - 3

ER -

Modeling a nonlinear process using the exponential autoregressive time series model

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this