DEVELOPMENT OF EMISSION ORIENTATED PRODUCTION CONTROL STRATEGIES USING FUZZY EXPERT-SYSTEMS, NEURAL NETWORKS AND NEURO-FUZZY APPROACHES

In industrial production processes, materials and different forms of e nergy are provided, converted, stored and transported. Environmental i mpacts can be identified at any stage of the energy and material how p rocess. Due to the fact that production units and processes are interc onnected with energy and material flows, it is of special interest to develop production control mechanisms, which control the energy and ma terial streams so that available resources are utilised most efficient ly and reduce emissions and by-products caused by the production proce ss. Methodical production control strategies can be based on optimal a lgorithms, production rules or methods of machine learning. Due to the complexity of real production systems, it is advisable to use heurist ic approaches. In order to analyse the behaviour of different control strategies, the developed systems are verified by an exemplary product ion system from the textile industry, consisting of a dye house, a hyd ro-power, a boiler house, and a flue gas neutralisation facility. A ve rification of the developed systems shows that Fuzzy Expert Systems, N eural Networks, and Neuro-Fuzzy approaches can be applied for the cont rolling of energy and material flows, taking into account economic and emission orientated goals. The selection of a certain approach mainly depends on the structure of the available production knowledge.