Downloads: 129 | Views: 204

Case Studies | Mechanical Engineering | India | Volume 6 Issue 2, February 2017

Experimental and Neural Network Based Investigation of External Scavenged Two Stroke S.I. Engine

Rahul D. Raut ^[2] | Kisan V. Wankhede | Suvarna V. Mehere | Kunal R. Kavitkar

Abstract: Two stroke spark ignition engines have high exhaust emissions and low brake thermal efficiency due to the short circuiting losses and incomplete combustion, which occur during idling and at part load operating conditions. To eliminate the short circuiting losses, new scavenging system has been developed. Here attempt is made to regulate the natural aspirated air for better fuel economy with increasing a speed and reduced emissions. In this project an attempt has been made to improve scavenging characteristic of two stroke engine. In the world, scientific studies increases day by day and computer programs facilitate the humans life. Scientists examine the humans brains neural structure and they try to be model in the computer and they give the name of artificial neural network (ANN). The purpose of this study is to estimate fuel economy of an automobile engine by using ANN algorithm. Engine characteristics were simulated by using Neuro Solution software. This study deals with artificial neural network (ANN) modelling of a two stroke scavenging to predict the characteristics of the engine. To acquire data for training and testing the proposed ANN, two stroke engines operated at different loads. Using some of the experimental data for training, an ANN model based on feed forward neural network for the engine was developed. Then, the performance of the ANN predictions were measured by comparing the predictions with the experimental results which were not used in the training process. It observed that the ANN model can predict the engine characteristics quite well with correlation coefficients, with very small errors. This study shows that, as an alternative to classical modelling techniques, the ANN approach can be used to accurately predict the performance of internal combustion engines.

Keywords: Scavenging, Artificial neural network ANN, BSFC, Short circuiting losses, Neuro solution, and Brake Power

Edition: Volume 6 Issue 2, February 2017,

Pages: 1117 - 1124