Real world evaluation and control of vehicle engine exhaust air pollution using adaptive neural fuzzy inference system

Abstract

Internal combustion engines are considered primarily responsible for air pollution. Accordingly, a concentrated effort has been made to reduce these pollutants which are emitted from the exhaust system of these engines while preserving energy and fuel consumption. There are also other sources besides internal combustion engines, such as power stations and those released from industry and home consumption. Industrial and household fuel consumers are also adding pollution. The industrial development requires the establishment of effective control systems to deal with its equipment to increase its operational life and increase its productivity with lower maintenance costs. Therefore, the aim of the study in this research is exposed to be used of adaptive neural fuzzy inference system to control the components of the emission of exhaust pollutants for gasoline vehicle. Exhaust pollutants consist of unburned carbon monoxide, hydrocarbons, carbon dioxide, water vapor nitrogen oxides, and energy produced from the combustion process which emit into atmosphere through the exhaust tailpipe. Also, there are hydrocarbons produced from gasoline vaporization and from the crankcase of the vehicle. The results indicate that the adaptive neural fuzzy inference system proves to be a useful tool for simulating and controlling vehicle engine exhaust emissions.