Revised KAD tool to optimize F1 cars through a combined-elitarian genetic-fuzzy algorithm

Abstract

The KAD (Knowledge Aided Design) tool is developed to predict the performance of an F1 car in different driving conditions and with different configurations. The regulations to put in trimming a car, also in the exasperated technology of the competitions, still demand a remarkable dose of luck and an elevated number of tests. It is then important to know a set of regulations close to the optimal trim before testing the car on the track. The difficult phase of this process is to evaluate the lap time. As a matter of fact driving style, track conditions and car behavior should be simulated. The optimisation of the fuzzy controller that simulates the pilot for an F1 racing car is difficult due to handling problems and velocity of response. For this purpose a specific Genetic Algorithm (GA) was conceived and tuned to work with a lumped mass model of an F1 racing car for the optimization of the fuzzy controller that simulates the pilot. A new mutation and a new crossover operator were defined to complement the standard crossover and mutation operators of the basic Holland's GA. This was necessary in order to increase the overall performance of the fuzzy pilot. This approach was tested on an F1 car due to the huge amount of data available (Donnarumma