PSO and GA designed Pareto of Fuzzy Controller in AC Motor Drive

In electric vehicles EV, can be implemented a controller has highest extend of battery’s lifetime meet a superior dynamic speed behavior? This research offer multi-objective approaching planned by a Particle Swarm Optimization (PSO) complementary with Genetic Algorithm (GA). This hybrid evolutionary learning is utilized as an automated method to generate the optimal parameters of fuzzy logic controller (FLC) type Mamdani. The Pareto front characterizes the speed controller of an Induction Motor (IM). where the first function is the error between the actual speed and desired speed, and the other function is the energy dissipated from the electrical supply during (10 sec), in present work the multi-objective optimization of PSO and GA have been implemented separately using two M-file/MATLAB, and compacted the results to sketch the global Pareto, while the evaluation of “fitness functions” of the two computational algorithms have been determined using SIMULINKMATLAB, the simulation has a completely mathematical model of induction motor IM, voltage source inverter VSI and FLC. The FLC have been implemented using RSLogix 5000. The empirical results demonstrate that the proposed method realized a limited disbursed energy as possible as better dynamic behavior of the IM speed along the Pareto front.