An adaptive learning current controller for field-oriented controlled induction motor by neural network

The authors propose and investigate a novel adaptive learning current controller using an artificial neural network adapted to an inverter-fed vector control AC drive system. The proposed adaptive learning current-controlled PWM (pulse width modulation) adaptively minimizes a current ripple in a constant switching frequency. This technique is applied to an electrical drive system with an induction motor and is studied by simulation. It was verified that the proposed controller has a good transient characteristic due to the neural network's learning ability under the condition of load torque variation. Compared with classical methods, the proposed approach shows better performance.<<ETX>>