Artificial intelligence approach in designing of car brakes

Computer-aided technology of car brakes tribological designing is presented. It is founded on DataBases (DB), Expert Systems (ES) created by heuristic logical programming methods using an artificial intelligence approach. There are also Hybrid Expert Systems (HES) which have "pure" Expert System parts and calculation modules (developed by traditional methods of software creating). The DB include detailed information regarding materials, prototypes of the car brakes, experimental results together with description of the test conditions. The basis of the ES is a Knowledge Base (KB). The knowledge is presented as a system of rules (if...then). The ES are teachable. They can build logical chains allowing checking hypothesis by comparison of proposed fact with the rules. The logical conclusions can be explained in details automatically. First, filling of the KB and DB is done, then the added information is confronted with the KB rules and compared with numerical information from DB. Second, optimum design is developed. Here the ES helps the designer to set correctly the optimization problem and solve it. The ES uses the Theory of Decisions for defining of the friction unit structure and the parameter optimization method earlier offered by the authors.