On-line speed control of the shunt-connected DC motor via a neurocontroller

This paper presents the speed neural control of a shuntconnected DC motor. The rotor speed of the DC motor can follow an arbitrarily selected reference. The purpose is to achieve accurate reference control of the speed, especially when motor and load parameters are unknown. For this task, an on-line B-spline neural network is proposed due to its simple structure, adaptability, and robustness, taking into account the unknown nonlinear dynamics of the DC motor and load. Laboratory tests demonstrate the applicability of the proposition compared with the conventional PI control scheme. The performance of the resulting system has been tested on a 120 V, 2.8 A, 188.49 rad/sec DC motor.