An efficient neural controller for a DC servo motor by using ANN and PLR identifiers

This work introduces an artificial neural network based efficient speed control for a DC motor. For this task; first, the motor mathematical model is obtained in the digital form. Secondly, in order to be able to develop necessary inputs to drive the plant, open loop control signals, the direct and inverse models of the system are identified by conventional and ANN identifiers working together. After that, a neural controller is introduced, which is trained by a composite error signal. The success of the designed control system is tested by a simulation study considering real conditions to be able to occur in actual operation.