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 ANN approach has been applied to automotive vacuum brake for predicting the optimized evacuation time and the power for a vacuum pump of 110 cc capacity with vacuum tank capacity of 3 cc at pressure of 500 mbar. The ANN predictions for the evacuation time and power of the tested vacuum brake yielded a good statistical performance with mean square error of 8.21152 e-3 and regression value between 0.9904 e-01. Comparisons of the ANN predictions and the experimental results demonstrate that to automotive vacuum brake can accurately be modeled using ANNs. Consequently, with the use of ANNs, the evacuation time and power of the brake can easily be determined by performing only a limited number of tests instead of a detailed experimental study, thus saving both time and cost. As a result the proposed NN model has strong potential as a feasible tool for the prediction of evacuation time of a vacuum pump used in automobile brakes.