Developing a neural network and real genetic algorithm combined tool for an engine test bed

摘要: AbstractIn the automotive industry, engine test engineers are required to deal with a huge quantity of experimental data obtained from beds each day. Those must be analysed evaluate performance and guide further operations. In order improve efficiency reduce expenditure time in testing, it is very important for bed controllers develop mathematical model existing data. This paper presents an investigation neural network-genetic algorithm (GA) combined tool modelling. modelling tool, real-coded GA has been employed train three different groups networks (a multilayer perceptron group, radial basis function bar group) then finally find most suitable network The results given this show that proposed successfully used Rover testing.