Detection of Fuel Adulteration Using Wave Optical with Machine Learning Algorithms

摘要

Fuel is a very important factor and has considerable influence on the airquality in the environment, which is the heart of the world. The increase of vehiclesin lived-in areas results in greater emission of carbon particles in the environment.Adulterated fuel causes more contaminated particles to mix withbreathing air and becomes the main source of dangerous pollution. Adulterationis the mixing of foreign substances in fuel, which damages vehicles and causesmore health problems in living beings such as humans, birds, aquatic life, andeven water resources by emitting high levels of hydrocarbons, nitrogen oxides,and carbon monoxide. Most frequent blending liquids are lubricants and kerosenein the petrol, and its adulteration is a considerable problem that adds to environmentalpollution. This study focuses on detecting the adulteration in petrol usingsensors and machine learning algorithms. A modified evanescent wave opticalfiber sensor with discrete wavelet transform is proposed for classification of adulterateddata from the samples. Furthermore, support vector machine classifier isused for accurate categorization. The sensor is first tested with fuel and numericaldata is classified based on machine learning algorithms. Finally, the result is evaluatedwith less error and high accuracy of 99.9, which is higher than all existingtechniques.