Determinant analysis of oil agglomeration of coal fines using multiple regression and neural network models

Oil agglomeration has gained importance owing to its simplicity and efficiency in beneficiating coal fines. In this study, high ash coal samples taken from six mines in India were put through an oil agglomeration process to investigate the usage of castor oil or blend of castor and turpentine for recovery of coal fines from coal-water slurry. The performance of the process has been evaluated based on ash rejection [AR (%)] and yield (%). Various Statistical analyses were carried out to investigate the role of various process parameters, such as PD, OD, AT, and oil-type on AR (%) and yield (%). Step-wise regression was performed for development of prediction model for AR (%) and yield (%). Determinant analysis was performed using general linear model (GLM). Our findings indicate that pulp density was the strongest determinant for AR (%), followed by oil dosage and agitation time. Similarly, oil dosage was the primary determinant for yield (%), followed by pulp density and agitation time. Sensitivity analysis was also carried out using artificial neural network (ANN) and the results in respect AR (%) revealed that agitation time was the most important predictor followed by pulp density and oil dosage.