A differential evolution based neural network approach to nonlinear system identification |
| |
| Authors: | Bidyadhar Subudhi Debashisha Jena |
| |
| Affiliation: | 1. Department of Electrical Engineering, National Institute of Technology, Rourkela-769008, India;2. Department of Electrical & Electronics Engineering, National Institute of Technology Karnataka, Surathkal-575025, India;1. College of Civil Engineering, Tongji University, 1239 Siping Rd, Shanghai 200092, China;2. Department of Civil and Environmental Engineering, Vanderbilt University, Box 1831-B, Nashville, TN 37235, USA;1. Department of Computer Science, University of Tabriz, Tabriz, Iran;2. Peter Faber Business School, Australian Catholic University, Australia;1. Tecnológico de Monterrey, Mexico;2. Bioprocess Department, UPIBI-Instituto Politécnico Nacional, Mexico |
| |
| Abstract: | This paper addresses the effectiveness of soft computing approaches such as evolutionary computation (EC) and neural network (NN) to system identification of nonlinear systems. In this work, two evolutionary computing approaches namely differential evolution (DE) and opposition based differential evolution (ODE) combined with Levenberg Marquardt algorithm have been considered for training the feed-forward neural network applied for nonlinear system identification. Results obtained envisage that the proposed combined opposition based differential evolution neural network (ODE-NN) approach to identification of nonlinear system exhibits better model identification accuracy compared to differential evolution neural network (DE-NN) approach. The above method is finally tested on a one degree of freedom (1DOF) highly nonlinear twin rotor multi-input–multi-output system (TRMS) to verify the identification performance. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
