Modified Levenberg-Marquardt Algorithm for BP Neural Network Training in Dynamic Model Identification of Mechanical Systems

LI, Ming, WU, Huapeng, WANG, Yongbo, HANDROOS, Heikki and CARBONE, Giuseppe (2016). Modified Levenberg-Marquardt Algorithm for BP Neural Network Training in Dynamic Model Identification of Mechanical Systems. Journal of Dynamic Systems, Measurement, and Control. (In Press)

Full text not available from this repository.
Official URL: http://dx.doi.org/10.1115/1.4035010
Link to published version:: 10.1115/1.4035010

Abstract

For modelling a dynamic system in practice, it often faces the difficulty in improving the accuracy of the constructed analytical model, since some components of the dynamic model are often ignored deliberately due to the difficulty of identification. It is also unwise to apply the neural network to approximate the entire dynamic system as a black box, when the comprehensive knowledge of most components of the dynamics of a large system are available. This paper proposes a method that utilizes the BP neural network to identify the unknown components of the dynamic system based on the experimental front‐end inputs‐outputs data of the entire system. It can avoid the difficulty in getting the direct training data for the unknown components, and brings great benefits in the practical application, since to get the front‐end inputs‐outputs data of the entire dynamic system is easier and cost‐effective. In order to train such neural network for the unknown components of dynamics, a modified Levenberg‐Marquardt algorithm, which can utilize the front‐end inputs‐outputs data of the entire dynamic system, has been developed in the paper. Three examples from different application points of view are presented in the paper, and the results show that, the proposed modified Levenberg‐Marquardt algorithm is efficient to train the neural network for the unknown components of the system based on the data of entire system. The constructed dynamics model, in which the unknown components is substituted by the neural network, can satisfy the requisite accuracy successfully in the computation

Item Type: Article
Research Institute, Centre or Group: Materials and Engineering Research Institute > Centre for Automation and Robotics Research > Sheaf Solutions
Identification Number: 10.1115/1.4035010
Depositing User: Helen Garner
Date Deposited: 23 Dec 2016 13:53
Last Modified: 13 Jun 2017 13:56
URI: http://shura.shu.ac.uk/id/eprint/14381

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics