Title :
Design of single neuron PID multi-variable controller based on evolving PSO
Author :
Wang, Guanghui ; Chen, Jie ; Pan, Feng
Author_Institution :
Dept. of Auto-control, Beijing Inst. of Technol., Beijing
Abstract :
Coupling multi-variable controller contains some problems of complex nonlinear control. Single neuron PID controller has a good capability of self-adapting, self-learning, nonlinear and robustness. This paper uses some single neuron PID controllers to design coupling multi-variable controller, accompanying a large amount of optimization problem of nonlinear multi-dimension complex function. To solve that problem, evolving PSO has been proposed in this paper. To ravel out particle swarm optimizationpsilas (PSO) problem of local minima, crossover and mutation operations have been added to it. Simulation experiments of two typical objects have been made, and demonstrate the effectiveness and superiority of the proposed algorithm. This designed controller has a good performance. Evolving PSO can solve the complex problem in this controller design effectively.
Keywords :
control system synthesis; multidimensional systems; multivariable control systems; neurocontrollers; nonlinear control systems; particle swarm optimisation; three-term control; PSO; complex nonlinear control; controller design; nonlinear multidimension complex function; particle swarm optimization; single neuron PID multivariable controller; Automatic control; Couplings; Design automation; Design optimization; Genetic mutations; Intelligent control; Neurons; Particle swarm optimization; Robust control; Three-term control; Coupling Multi-variable Control; PSO; Single Neuron PID;
Conference_Titel :
Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4244-2113-8
Electronic_ISBN :
978-1-4244-2114-5
DOI :
10.1109/WCICA.2008.4594292