Prediction-based neural fuzzy controller design using modified electromagnetism-like algorithm

Based on the electromagnetism-like algorithm (EM), we propose a novel hybrid learning algorithms which is the improved EM algorithm with back-propagation technique (IEMBP) for recurrent fuzzy neural system design. IEMBP are composed of initialization, local search, total force calculation, movement, and evaluation. They are hybridization of EM and BP. EM algorithm is a population-based meta-heuristic algorithm originated from the electromagnetism theory. For recurrent fuzzy neural system design, IEMBP simulate the “attraction” and “repulsion” of charged particles by considering each neural system parameters as an electrical charge. The modification from EM algorithm is the neighborhood randomly local search is replaced by BP and the is adopted for IEMBP. IEMBP combines EM with BP to obtain high speed convergence and less computation complexity. However, it needs the system gradient information for optimization. IEMBP are used to develop the update laws of RFNN for inverted pendulum system control. Finally, several illustration examples are presented to show the performance and effectiveness of IEMBP.