Title :
Simple adaptive control for SISO nonlinear systems using neural network based on genetic algorithm
Author :
An, Shi-Qi ; Lu, Tian ; Ma, Yu-Ju
Author_Institution :
Coll. of Autom. & Electron. Eng., Qingdao Univ. of Sci. & Technol., Qingdao, China
Abstract :
This paper presents a method of continuous-time simple adaptive control (SAC) using neural network based on genetic algorithm (GA) for a single-input single-output (SISO) nonlinear systems, bounded-input bounded-output, and bounded nonlinearities. According to the power of neural network and the characteristics of simple adaptive control, constructed a simple adaptive control using neural networks, and in neural network learning process, introduce genetic algorithm, using genetic algorithm to optimize the neural network weights. Simple adaptive control, neural network and genetic algorithm were combined to form Genetic Algorithms-Neural Network Simple Adaptive Control (GA-NNSAC). Finally, the simulation results show that the proposed method has fine accuracy, dynamic character and robustness through computer simulations.
Keywords :
adaptive control; control nonlinearities; genetic algorithms; learning (artificial intelligence); neurocontrollers; nonlinear control systems; SISO nonlinear systems; bounded nonlinearities; bounded-input bounded-output nonlinearities; continuous-time control; genetic algorithm; neural network learning process; simple adaptive control; single-input single-output system; Adaptation model; Adaptive control; Algorithm design and analysis; Artificial neural networks; Machine learning; Optimization; Genetic Algorithm; Neural network; Nonlinear system; SISO; Simple adaptive control;
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2010 International Conference on
Conference_Location :
Qingdao
Print_ISBN :
978-1-4244-6526-2
DOI :
10.1109/ICMLC.2010.5580615