High speed on-line neural network control of an induction motor immune to analog circuit nonidealities

A neural network using the Random Weight Change algorithm is shown able to be trained to perform on-line control of the current of an induction motor stator, despite analog circuit nonidealities. The induction motor is a complex nonlinear electromechanical system, with rapidly time-varying system parameters. Due to the small time constant of this power electronic system, the neural network must be able to finish each training cycle in less than 50 microseconds, which is only possible when controlled by specifically designed hardware circuits. An analog circuit is preferred for its ability to implement a reasonable size of network on one integrated chip. The analog circuit nonidealities are overcome by the Random Weight Change (RWC) algorithm. RWC is based on the method of random searching, and achieves similar performance to the back-propagation (BP) algorithm. The back-propagation algorithm is very difficult to implement in analog hardware due to its sensitivity to offset and nonlinearity errors. The RWC algorithm is simulated with analog circuit nonidealities, and is shown to be immune to these problems, thus the RWC algorithm is found ideally suited for the high speed analog circuit neural network implementation