Classification of Polluted Silicone Rubber Insulators by Using LIBS Assisted Machine Learning Techniques

Silicone rubber (SR) samples are coated with various types of artificially prepared pollutants, in order to identify and distinguish them by employing laser induced breakdown spectroscopy (LIBS). LIBS analysis is successful identifying the elemental composition pollutants. The presence copper sulphate as well carbon-based compounds such fly ash, coal calcium-based cement calcium phosphate (fertilizer) have been identified increment normalized intensity ratio copper, carbon peaks respectively. spectral data has used conjunction several machine learning (ML) algorithms linear discriminant analysis, decision tree, K-nearest neighbors gradient boosting techniques classify seven different contaminated SR samples. When compared other ML approaches utilized present study, classification using Light technique reflected better accuracy 97.43% a reasonable computation time 5.1 s.