Research On Brushless DC Motor Control Of BP Neural Network

The brushless DC motors which adopt electronic phase change instead of mechanical one, overcome a variety of the traditional DC motors, which are caused by the brush friction. Furthermore, with many advantages such as good speed regulation, litter volume and high efficiency, brushless DC motors find their wide application in every line of work in national industry and daily life.In the control strategy of the brushless DC motors, the artificial neural network (ANN) has great potential in application. After introducing the development, status quo, basic theory of neural network and its application to automatic control, this thesis mainly BP neural network and its application to PID control.Applying the BP neural network in PID control can efficiently overcome the limitations of badness of parameter adjusting and poor performance when the plant has nonlinearity, time-varying and difficulty in setting up the accurate model. This paper designs an adaptive PID controller and uses the improved conjugate gradient to improve the PID controller parameters on-line. Finally, carried on simulation to BLDC, simulation result indicate, use neural network go on after improving the system robustness and dynamic performance.