The Prediction of Oil Quality based on Least Squares Support Vector Machines

Least squares support vector machines (LS-SVM) is a new improvement of classic support vector machines (SVM). The inequality constraints of original space are replaced by equality constraints. So the quadratic programming of SVM is inverted to solve linear equations, the complexity of computation is reduced, the solution speed and convergence precision are improved. Based on the local data from hydrogenation equipment, a predictive model based on least squares support vector machines (LS-SVM) is established for three important quality targets of diesel oil in this paper. Finally, it is proved that the proposed predictive models based on LS-SVM can predict the quality target more efficiently and rapidly than stands SVM and neural network. It provided a method for online prediction and diagnosing fault of quality targets.