CNG exhausts emission modeling: Neural network approach

Abstract

<span style="mso-bidi-language:HI">Traditional statistical regression and Artificial Neural Network (ANN) modeling techniques were applied to assess the emission characteristics of CNG vehicles (cars and three wheelers) to understand the influence of explanatory parameters, like vehicle age, vehicle type and air-fuel ratio on emissions of CO, HC, CO_{<span style="mso-bidi-font-family: Arial;mso-bidi-language:HI">2</span>}<span style="mso-bidi-font-family: Arial;mso-bidi-language:HI"> <span style="mso-bidi-language:HI">and O_{<span style="mso-bidi-font-family:Arial;mso-bidi-language:HI">2</span>}<span style="mso-bidi-font-family:Arial;mso-bidi-language:HI">. <span style="mso-bidi-language:HI">For ANN modeling. multilayer feed-forward neural network with single hidden layer was considered and back propagation algorithm was applied for training. ANN model, ANN models are shown better predictive models than the traditional statistical modeling techniques for predicting the CNG exhaust emissions (CO, <span style="mso-bidi-font-family:Arial; mso-bidi-language:HI">HC, <span style="mso-bidi-language:HI">CO_{<span style="mso-bidi-font-family:Arial;mso-bidi-language:HI">2</span>}<span style="mso-bidi-font-family:Arial;mso-bidi-language:HI">, <span style="mso-bidi-language:HI">and O_{<span style="mso-bidi-font-family: Arial;mso-bidi-language:HI">2</span>}<span style="mso-bidi-font-family: Arial;mso-bidi-language:HI">).

</span></span></span></span></span></span></span></span></span></span>