Least Squares Support Vector Machine Classifiers
Neural Processing Letters
Computers and Industrial Engineering
An overview of statistical learning theory
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
Soft sensor is an effective tool to estimate industrial process variables which are hard to be measured online for the technical or economical reasons. The modeling methods of the sensor are related to the approximating precision and speed. A soft sensor model with rough set and Least Squares Support Vector Machines (LSSVM) is presented in the paper. The rough set is employed to compress the data for preprocessing, which can get rid of the multicollinearity and reduce the dimension of input variables for the model. To solve the nonlinear and multiple input characteristics of industrial process, the LSSVM is delivered for model regression. The model is applied for moisture content soft sensing of vacuum oil purifier. The result shows that the proposed method features high speed and precise approximation ability, which has better performance of generalization for tracking the trend of the moisture content variety during oil purification.