Abstract
Waste lubricant oil (WLO) is a hazardous residual that requires proper management, being WLO regeneration the preferred approach. However, regeneration is only viable if the WLO does not coagulate in the equipment. Otherwise, the process needs to be shut down for cleaning and maintenance. To mitigate this risk, a laboratory test is currently used to assess the WLO coagulation potential before it enters the process. This laboratory test is, however, time-consuming, presents several safety risks, and is subjective. To expedite decision-making, process analytics technology (PAT) and machine learning were used to develop a model to classify WLOs according to their coagulation potential. Three approaches were followed, spanning linear and non-linear models. The first approach (benchmark) uses partial least squares for discriminant analysis (PLS-DA) and interval PLS combined with standard chemometric preprocessing techniques (27 model variants). The second approach uses wavelet transforms to decompose the spectra and PLS-DA for feature selection (10 model variants). Finally, the third approach uses convolutional neural networks (CNN) to estimate the optimal filter for feature extraction (1 model variant). These models were trained on real industrial data. The results show that the three modelling approaches can attain high accuracy, with an average of 91%. The spectral filtering using wavelet transforms proved to be a viable option to reduce the number of models to explore compared to the benchmark approach. The CNN was also able to streamline the preprocessing selection by implicitly estimating the optimal filter. The models also provided physical insight into the WLO coagulation phenomenon.