Search Results

This paper presents the details of the study to optimize and arrive at a design base for a vacuum pump in an automotive engine using resilient back propagation algorithm for Artificial Neural Networking (ANN). The reason for using neural networks is to capture the accuracy of experimental data while saving computational time, so that system simulations can be performed within a reasonable time frame. Vacuum Pump is an engine driven part. Design and optimization of a vacuum pump in an automotive engine is crucial for development. The NN predicted values had a good correlation with the actual values of tested proto sample. The design optimization by means of this study has served the purpose of generating the data base for future development of different capacity vacuum pumps.

The fuel injection timing is one of the most important operating parameters that affect the atomization, mixture formation and combustion which determines the performance and emissions of a gasoline engine. Optimizing the injection timing will improve the performance of the engine to a large extend. Towards this end artificial neural-network (ANN) technique using Levenberg-Marquardt (LM) training algorithm is used to train and optimize the fuel injection timing of a single cylinder, four-stroke gasoline engine. Experimental studies have been carried out to obtain training as well as test data. For various engine speeds between 700 and 5000 rpm and for different manifold absolute pressures, fuel injection timing was measured by conducting experiments. The experimental data set generated is used to train the neural network to arrive at the optimized performance of the engine.