Performance and Exhaust Emissions of a SI Two-stroke Engine with Biolubricants Using Artificial Neural Network

Abstract

Abstract Biolubricants are a new generation of renewable and eco-friendly vegetable-based lubricants which have attracted a lot of attention in recent years. In this research study a back-propagation neural network model has been developed for predicting the effect of different types of biolubricants on the performance and exhaust emissions of a 200 cc two stroke engine. The inputs of the model are lubricant type, lambda and engine speed. Model outputs are: engine brake power, torque, BSFC (brake specific fuel consumption) and exhaust emissions which include CO, CO2, UHC, O2 and NOx emissions. Engine's brake power, torque and brake specific fuel consumption, as well as exhaust emissions have been predicted with the Artificial Neural Network (ANN) model. The relationship between input parameters and engine performance and emissions are determined using the network. The application of ANNs are highly recommended to predict the IC engine parameters under investigation.