Electronic Nose Testing for Confined Space Application Utilizes Principal Component Analysis and Support Vector Machine

Abstract

A confined space has a limited space for entry and exit but it is large enough for workers to enter and perform work inside. It is not designed for continuous occupancy because it can contribute atmospheric hazards accidents that threaten the worker safety and industry progress. In this work, we reported the testing an instrument to assist workers for atmosphere testing during pre-entry. An electronic nose (e-nose) using specific sensor arrays is the integration between hardware and software that able to sense different concentrations of gases in an air sample using pattern recognition techniques. The instrument utilizes multivariate statistical analysis which is Principal Component Analysis (PCA) for discriminate the different concentrations of gases and the Support Vector Machine (SVM) to classify the acquired data from the air sample. The instrument was successfully tested using diesel, gasoline, petrol and thinner. The results show that the instrument able to discriminate an air sample using PCA with total variation for 99.94%, while the classifier success rate for SVM indicates at 98.21% for train performance and 95.83% for test performance. This will contribute significantly to acquiring a new and alternative method of using the instrument for monitoring the atmospheric hazards in confined space to ensure the safety of workers during work progress in a confined space.