Optimized torque control of switched reluctance motor at all operational regimes using neural network

Switched reluctance motor (SRM) optimal control parameters, which maximize torque per ampere, are calculated using a dynamic SRM model. In order to in clude the effect of the-magnetic nonlinearity, static torque and flux-linka ge data are used in the dynamic model. The static data are generated experi mentally, To recreate these control parameters, online, artificial neural n etworks are used. Two separate networks are trained. One is trained with th e low-speed control parameters for torque control at low speed, while the o ther is trained with the high-speed control parameters for torque control a t high speed. The speed at which the SRM makes a transition from chopping c ontrol to single-pulse operation (i.e., low-speed to high-speed operation), commonly referred to as base speed, is torque (current) dependent, A small table is maintained in the controller to identify the: base:speed for diff erent torque demands. When the motor exceeds the base speed for a certain t orque demand, the controller switches from the low-speed neural network to the high-speed neural network and vice versa, It is also shown that the SRM is capable of producing an extended constant-horsepower operation with thi s optimal control. The power factor (the energy ratio) is shown td improve in this extended speed constant-horsepower range. Simulation and experiment al results are presented to demonstrate the effectiveness of the proposed c ontrol scheme.