Loughborough University
Browse
author_final_version.pdf (315.44 kB)

Structure optimisation of input layer for feed-forward NARX neural network

Download (315.44 kB)
journal contribution
posted on 2016-03-24, 11:25 authored by Zongyan Li, Matt BestMatt Best
This paper presents an optimization method for reducing the number of input channels and the complexity of the feed-forward NARX neural network (NN) without compromising the accuracy of the NN model. By utilizing the correlation analysis method, the most significant regressors are selected to form the input layer of the NN structure. Applications of vehicle handling and ride model identification are presented in this paper to demonstrate the optimization technique. The optimal input layer structure and the optimal number of neurons for the NN models are investigated and the results show that the optimised NN model requires significantly less coefficients and training time while maintains high simulation accuracy compared with that of the unoptimised model.

Funding

This work was supported by Jaguar Land Rover and the UK-EPSRC grant EP/K014102/1 as part of the jointly funded Programme for Simulation Innovation.

History

School

  • Aeronautical, Automotive, Chemical and Materials Engineering

Department

  • Aeronautical and Automotive Engineering

Published in

International Journal of Modelling, Identification and Control

Citation

LI, Z. and BEST, M.C., 2016. Structure optimisation of input layer for feed-forward NARX neural network. International Journal of Modelling, Identification and Control, 25 (3), pp. 217-226.

Publisher

© Inderscience

Version

  • AM (Accepted Manuscript)

Publisher statement

This work is made available according to the conditions of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) licence. Full details of this licence are available at: https://creativecommons.org/licenses/by-nc-nd/4.0/

Publication date

2016

Notes

This paper was accepted for publication in the journal International Journal of Modelling and the definitive published version is available at http://dx.doi.org/10.1504/IJMIC.2016.075814

ISSN

1746-6172

eISSN

1746-6180

Language

  • en