An adaptive PID neural network for complex nonlinear system control

NEUROCOMPUTING

卷:135

Article

Kang, Jun^1,2  Meng, Wenjun¹  Abraham, Ajith^3,4,5  Liu, Hongbo^3,5 

[1] Taiyuan Univ Sci & Technol, Sch Mech Engn, Taiyuan 030024, Peoples R China

[2] North Univ China, Software Sch, Taiyuan 030051, Peoples R China

[3] Sci Network Innovat & Res Excellence, MIR Labs, Machine Intelligence Res Labs, Auburn, WA 98071 USA

[4] VSB Tech Univ Ostrava, Ctr Excellence IT4Innovat, Ostrava 70833, Czech Republic

[5] Dalian Maritime Univ, Sch Informat Sci & Technol, Dalian 116026, Peoples R China

关键词: Complex nonlinear system;    Adaptive;    PID neural network;    PSO;    Gradient descent;   

DOI  :  10.1016/j.neucom.2013.03.065

来源: Elsevier

【 摘 要 】

Usually it is difficult to solve the control problem of a complex nonlinear system. In this paper, we present an effective control method based on adaptive PID neural network and particle swarm optimization (PSO) algorithm. PSO algorithm is introduced to initialize the neural network for improving the convergent speed and preventing weights trapping into local optima. To adapt the initially uncertain and varying parameters in the control system, we introduce an improved gradient descent method to adjust the network parameters. The stability of our controller is analyzed according to the Lyapunov method. The simulation of complex nonlinear multiple-input and multiple-output (MIMO) system is presented with strong coupling. Empirical results illustrate that the proposed controller can obtain good precision with shorter time compared with the other considered methods. (c) 2014 Elsevier B.V. All rights reserved.

【 授权许可】

Free