A blackboard software architecture for integrated intelligent control systems

This paper describes a software architecture which supports the design of hierarchical controllers that provide facilities for adaptation, supervision and task planning. It details how this form of functional hierarchy differs from the structural hierarchy also inherent within a complex control system. Then, both forms of hierarchy are combined in a single design notation and development methodology. The system utilises intelligent control techniques (neuro-fuzzy and genetic optimisation) for controlling a cryogenic plant used for superconductor testing by cooling the test samples to temperatures below 100 degrees K. The system supports the design of a hierarchical controller that provides facilities for adaptation supervision and task planning. Simulation results are presented.