Design and implement of the recurrent radial basis function neural network control for brushless DC motor

In this paper, intelligent PID neural network (IPIDNN) controller based on a recurrent radial basis function neural network (RRBFNN) for brushless dc motor (BLDCM) speed control is proposed. First, the dynamic model of BLDCM system is derived. Then, the PID controller with online tuning using an RRBFNN is proposed to control the BLDCM for improving speed tracking response. The parameter learning of RRBFNN is based on the supervised gradient descent method, using a delta adaptation law. Moreover, all the control algorithms are implemented in a TMS320F28069 DSP-based control computer. Finally, it is validated that the proposed controller accomplishes the advanced control performance, with low overshoot and reduced improved transient and compared to the conventional PID method in the presence of parameter uncertainties.