A neuro-fuzzy supervisory control system for industrial batch processes

The automation of complex industrial batch processes is a difficult problem due to the extremely nonlinear and variable system behavior or the conflic ting goals within the different process phases. The introduction of a singl e multiple-input multiple-output controller is not useful because of the ra ther high design effort and the low transparency of its complex structure. A more suitable hierarchical fuzzy-logic (FL) based supervisory control con cept is proposed in this paper. It permits the decomposition of the complex control problem into a series of smaller and simpler ones. In the upper le vel of the hierarchy the FL-based supervisory controller classifies the act ual process phase in terms of the available process sensor signals and acti vates dynamically the appropriate situation specific low-level controllers. This paper presents the generic concept of the FL supervisory controller t hat comprises both a FL process diagnosis and a control mode selection as w ell as experiences with the industrial application.