Optimization and control of a small-angle negative ion source using an on-line adaptive controller based on the connectionist normalized local spline neural network

Abstract We have developed CTL, an on-line adaptive controller, to optimize and control a repetitively pulsed, small-angle negative ion source. CTL processes multiple diagnostics to determine the ion source operating conditions. A figure of merit is constructed that weights beam current magnitude, noise, and pulse-to-pulse repeatability. The operating space of the ion source is mapped coarsely using automated scan procedures. Then CTL, using information derived by fitting the sparse operating-space data with the Connectionist Normalized Local Spline artificial neural network, interactively adjusts four ion-source control knobs (through regulating control loops) to optimize the figure of merit. Fine tuning is performed by executing a modified gradient search algorithm directly on the machine. Resulting beam quality is consistently quite good. CTL has tuned the ion source for nearly optimum operation on six cold startups in one to four hours from the time of initial arc. After a brief interruption of operation, return to optimized beam performance typically takes only about fifteen minutes.