A DPSO-Based NN-PID Controller for MIMO Systems

The neural networks are generally trained using the standard back propagation (BP) algorithm and its variants. In the BP algorithm, the initial weights are generated randomly which affects the convergence of algorithm, and hence, the algorithm is prone to the problem of local optima. In the proposed work, dynamic particle swarm optimization (DPSO) has been used to initialize the weights of the NN-PID controller for multiple input multiple output (MIMO) systems. The results obtained using the proposed DPSO-based NN-PID controller were compared with the other existing NN-PID control techniques. Simulation results show that the performance of the BP algorithm was significantly improved with the use of DPSO algorithm for initializing the weights.