Multi-objective iterative learning control with application to vacuum heat treatment process

Many industrial processes involve systems with spatiotemporal dynamics. As demands for accuracy and performance grow, conventional control algorithms are no longer sufficient. There is a need for improved identification and control methods that account for both temporal and spatial dynamics and are realizable in practical scenarios. This work presents an approach that competes with existing on-line feedback, using predictive iterative learning control. The control scheme is characterized along with details of its design and implementation. Simulations supplying are modeled after vacuum wafer heating in a furnace. The approach qualitatively tackled the nearly opposing goals of accurate parametric identification of the plant and trajectory tracking, demonstrating success when applied to practical problem.