Design of an expert system for the optimization of steel compositions and process route

Abstract This paper describes a new integrated approach to build an expert system to generate and evaluate alternative steelmaking aim compositions that not only meet the customer requirements but also suit the established rolling schedules. The methodology developed is based on the hybrid approach combining knowledge-bases as well as mathematical modelling and is applicable for C–Mn steel grades. The expert system consists of two modules. The first module utilizes various empirical models for the relationship between mechanical properties and the elements in steelmaking aim compositions, along with knowledge-bases containing expert and heuristic knowledge of expert metallurgists to generate a list of alternative steelmaking aim compositions. The second module uses the output of the first module and computes the microstructural evolution during processing depending on steel composition and the known values of processing conditions such as strain, strain rate, temperature, interpass time and plate cooling rate. Calculated values of the metallurgical parameters are then utilized to estimate realistically the achievable mechanical properties in the final hot rolled product using knowledge-bases. The output of this expert system is expected to assist the product development metallurgists in the selection of appropriate steelmaking aim composition for any combination of property specifications required by the customer.