A Knowledge-Based System for the Design of Rubber Compounds in Motor Racing

This work presents P-Race, a knowledge-based system designed to support the formulation of rubber compounds of tyre tread, in order to take part (and win) in motor racing. Because of the different competence involved in the decision making process (the compound designer and the race engineer), multiple knowledge representations have been adopted, and integrated into a unique Case-Based Reasoning (CBR) computational framework. The case-based approach captures the episodic knowledge characterising most of reasoning activity of the race engineer. Moreover, a dedicated representation formalism called Abstract Compounds Machine (ACM) has been created in order to allow the core knowledge about rubber compounds to be explicitly represented, computed and integrated in the CBR architecture. The most meaningful and innovative contribution of P-Race consists of a general case-based architecture where the adaptation step is performed by the ACM chemical formulation model. This system has been developed for the Motorsports Department of Pirelli Tyres, where it is currently in use