Application of associative memory neural networks to the control of a switched reluctance motor

The application of an associative memory neural network to the problem of torque ripple minimisation in a switched reluctance motor is presented. Conventional techniques for torque linearisation and decoupling are reviewed, after which the application of neural techniques to the problem is described. An instrumented test rig based around a 4 kW IGBT converter and a four phase switched reluctance motor has been constructed. Results obtained experimentally and by simulation demonstrate the effectiveness of the approach. The neural network has been implemented using both digital signal processor and field programmable gate array technologies.<>