Title: Application of neural network for air-fuel ratio identification in spark ignition engine

Authors: Samir Saraswati, Satish Chand

Addresses: Department of Mechanical Engineering, MNNIT, Allahabad 211004, India. ' Department of Mechanical Engineering, MNNIT, Allahabad 211004, India

Abstract: In the present work, Recurrent Neural Network (RNN) is used for Air-Fuel Ratio (AFR) identification in Spark Ignition (SI) engine. AFR identification is difficult due to nonlinear and dynamic behaviour of SI engines. Delays present in the engine dynamics limits the performance of engine controller. Identifying AFR few steps in advance can help engine controller to take care of these. RNN is trained using data from engine simulations in MATLAB/SIMULINK© environment. Uncorrelated signals were generated for training and generalisation and it has been shown that RNN can predict engine simulations with reasonably good accuracy. RNN discussed can also work as a virtual AFR sensor and it can very well replace costly AFR sensor used in SI engines.

Keywords: air-fuel ratio control; air-fuel ratio sensors; AFR sensors; engine modelling; recurrent neural networks; RNNs; spark ignition engines; simulation; virtual sensors.

DOI: 10.1504/IJCAT.2008.020956

International Journal of Computer Applications in Technology, 2008 Vol.32 No.3, pp.206 - 215

Published online: 26 Oct 2008 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article