Prediction of CO and HC emissions in Otto motors through neural networks

Abstract

This paper explains the application of RNA (Artificial Neural Networks) for the prediction of pollutant emissions generated by mechanical failures in ignition engines, from which the percentage of CO (% Carbon Monoxide) and the particulate can be quantified. per million HC (ppm Unburned Hydrocarbons), through the study of the Otto cycle admission phase, which is recorded through the physical implementation of a MAP sensor (Manifold Absolute Pressure). A rigorous sampling protocol and consequent statistical analysis is applied. The selection and reduction of attributes of the MAP sensor signal is made based on the greater contribution of information and significant difference with the application of 3 statistical methods (ANOVA, correlation matrix and Random Forest), from which a base of data that allows the training of two neural networks feed-forward backpropagation, with which we obtain a classification error of 5.4061e-09 and 9.7587e-05  for the neural network of CO and HC respectively.