Optimization of Diesel Engine Operating Parameters Using Neural Networks 2003-01-3228
Neural networks are useful tools for optimization studies since they are very fast, so that while capturing the accuracy of multi-dimensional CFD calculations or experimental data, they can be run numerous times as required by many optimization techniques. This paper describes how a set of neural networks trained on a multi-dimensional CFD code to predict pressure, temperature, heat flux, torque and emissions, have been used by a genetic algorithm in combination with a hill-climbing type algorithm to optimize operating parameters of a diesel engine over the entire speed-torque map of the engine. The optimized parameters are mass of fuel injected per cycle, shape of the injection profile for dual split injection, start of injection, EGR level and boost pressure. These have been optimized for minimum emissions. Another set of neural networks have been trained to predict the optimized parameters, based on the speed-torque point of the engine. These networks can be thought of as ‘engine maps’ and have been used to simulate the emissions of the engine over the FTP heavy duty diesel cycle. Improvements resulting from the optimization have been recorded. The entire process of getting optimized parameters for an engine, starting from raw engine data or CFD results is capable of being automated and has been shown to take a reasonably small amount of computational time.