A two-parameter model for the determination of optimum liquefied petroleum gasses (LPG) storage volume

In this work, a mathematical-based methodology is employed to develop a reliable model for the prediction of safe volume for liquefied petroleum gases (LPG) storage vessels. To this end, a novel soft computing approach namely least square support vector machine (LSSVM) modeling optimized with coupled simulated annealing (CSA) optimization technique is utilized. To evaluate the performance and accuracy of the LSSVM model, graphical (cross plot and error distribution curve) and statistical (error parameters) analyses have been utilized. Additionally, comparative studies are conducted between the LSSVM model and a multilayer perceptron artificial neural network (MLP-ANN) model. Obtained results prove that the proposed CSA-LSSVM model is more robust, reliable and efficient than the developed MLP-ANN model for the prediction of liquid volume correction factor. Consequently, the developed LSSVM model results indicate an average absolute relative deviation equals to 0.02782% from the corresponding liquid volume correction factor literature values, and a squared correlation coefficient of 0.9999.