In the automotive industry, engine test engineers are required to deal with a huge quantity of experimental data obtained from engine test beds each day. Those data must be analysed to evaluate engine performance and to guide further engine test operations. In order to improve efficiency and reduce expenditure of time in engine testing, it is very important for engine test bed controllers to develop a mathematical model from existing engine test data. This paper presents an investigation of a neural network-genetic algorithm (GA) combined tool for engine modelling. In the modelling tool, a real-coded GA has been employed to train three different groups of neural networks (a multilayer perceptron group, a radial basis function group, and a bar function networks group) and then finally to find the most suitable neural network model for engine modelling. The experimental results given in this paper show that the proposed tool has been successfully used for Rover engine testing.result, based on a two-cylinder, four-stroke direct JAUTO229
The engine test bed is introduced briefly and the importance of modelling for the engine test is discussed. The application of combining radial basis function (RBF) networks and a real-coded genetic algorithm (RCGA) to create the model is described for the engine test. Finally, the experimental results are analysed and it is shown that the proposed approach combining RCGA and RBF models is well suited for the engine test data modelling task.
Since multi-objective optimizations are becoming more important in engine calibration, the paper investigates multi-objective genetic algorithms in the application of engine optimization. Although several multi-objective genetic algorithms have been developed and some have been applied successfully in the automotive industry, it is difficult to determine which multi-objective genetic algorithm outperforms others in finding the set of optimal solutions or Pareto-optimal front in a practical multi-objective optimization problem. Based on some widely used multi-objective genetic algorithms, the paper proposes a combined scheme to deal with the difficulties in finding the optimal solution set during the engine calibration process. In the proposed approach the real-coded representation is employed in the genetic algorithm and the elitist strategy is applied for each multi-objective genetic algorithm used. To assess the proposed approach, two computational examples are given to minimize the brake specific fuel consumption and to maximize the output power torque simultaneously. The results show that the proposed approach is well suited to multi-objective optimization in engine calibration.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.