Papers Published

1. Kamran, Farrukh and Harley, Ronald G. and Burton, Bruce and Habetler, Thomas G. and Brooke, Martin A., Fast on-line neural-network training algorithm for a rectifier regulator, IEEE Transactions on Power Electronics, vol. 13 no. 2 (1998), pp. 366 - 371 [63.662857] .
   (last updated on 2007/04/11)

   Abstract:
   This paper addresses the problem of deadbeat control in fully controlled high-power-factor rectifiers. Improved deadbeat control can be achieved through the use of neural-network-based predictors for the input-current reference to the rectifier. In this application, on-line training is absolutely required. In order to achieve sufficiently fast on-line training, a new random-search algorithm is presented and evaluated. Simulation results show that this type of network training yields equivalent performance to standard backpropagation training. Unlike back-propagation, however, the random weight change (RWC) method can be implemented in mixed digital/analog hardware for this application. The paper proposes a very large-scale integration (VLSI) implementation which achieves a training epoch as low as 8 µs.

   Keywords:
   Electric rectifiers;Neural networks;Learning algorithms;Online systems;Computer simulation;VLSI circuits;Power electronics;