A COMPARISON OF FUZZY EXPERT-SYSTEMS, NEURAL NETWORKS AND NEURO-FUZZYAPPROACHES - CONTROLLING ENERGY AND MATERIAL FLOWS

In industrial production processes, materials and different forms of e nergy are provided, transformed respectively converted, stored and tra nsported. With this process joint products in different states of aggr egation are emitted. Environmental impacts can be identified at any st age of the energy and material flow process. Due to the fact that prod uction units and processes are interconnected with energy and material flows, it is of special interest to develop production control mechan isms which control the energy and material streams in a way that utili zes available resources most efficiently and reduces emissions and by- products caused by the production process. These production control st rategies have to consider variations in the input and output flows of succeeding and preceding production units. The development of producti on control strategies depends especially on the structure of integrate d production systems. If it is possible to influence the energy and ma terial flows by the selection of special production processes and an a dequate allocation of jobs and aggregates, the construction of product ion control strategies can be reduced to a combined scheduling and tec hnology selection problem. Methodical production control strategies ca n be based on optimal algorithms (e.g. dynamic programming) heuristics (e.g, rule-based approaches) and methods of machine learning (e.g. ne ural networks). Due to the complexity of real production systems, it i s advisable to use rule-based approaches or neural networks depending on the structure of the available production knowledge.