Standalone CMAC control system with online learning ability
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
The particle swarm - explosion, stability, and convergence in amultidimensional complex space
IEEE Transactions on Evolutionary Computation
| Hi-index | 0.00 |
The parameters selection of proportional coefficient and integral coefficient (PI) for speed controller is important for direct torque control system. However, it is difficult to adjust these parameters. In this paper, firstly, we use particle swarm optimization to search the appropriate PI values of the speed controller. Secondly, based on the optimized PI parameters, the fuzzy-PI speed control strategy is presented to solve the poor self-adaptability problem. Thus, the proportional coefficient kp and integral coefficient ki can be adjusted dynamically to adapt to the speed variations. And finally, to obtain the high-speed parallel processing ability, the well-trained RBF neural network replaces the fuzzy-PI speed controller. The comparison with conventional PI speed controller shows that the proposed intelligent integrated speed controller brings good benefits of fast speed response and good stability and reduces the torque ripple. The validity of the proposed intelligent integrated speed controller is verified by the simulation results.