Victoria University Research Repository (Victoria University) · 2011 · 35 citations · 0 references
Open access
EngineeringComputer ScienceMechatronics EngineeringArtificial IntelligenceOptimizationProcess ControlAdaptive ControlControl SystemsControl TheoryEvolutionary ComputationNeural Control SystemsOptimal ControlFuzzy ControlFuzzy Control SystemsIntelligent ControlNeural Network ControlParticle Swarm ControlParticle Swarm OptimizationPid Control DesignRadial Basis Function Networks
The ball and plate system is a typical multi-variable plant, which is the extension of the traditional ball and beam problems. Particle swarm optimization algorithm fuzzy neural network control (PSO-FNNC) scheme is introduced for the ball and plate system. The fuzzy neural network (FNNC) is optimized by the offline particle swarm optimization (PSO) of global searching ability, and the online radius basis function (RBF) algorithm ability of local searching. Then, the optimized fuzzy RBF neural network (FRBF) tuned PID controller. The simulation results demonstrate the potential of the proposed technique, especially tracking speed, tracking accuracy and robustness, is improved obviously, which embodies the nice characters of the PSO-FNNC scheme.