SVM-based moisture content modelling for Sugi drying process

In this paper, moisture content modelling method based on support vector machine for Sugi drying process is proposed. Moisture content is the quantity of water contained in the Sugi. In general, water in Sugi can be presented as free water and bound water. Sugi drying process refers to reduce the process of Sugi moisture content which is mainly determined by drying temperature and equilibrium moisture content. It is complex nonlinear relationship among them such that theoretical modelling could not be obtained to describe accurately them. As for a nonlinear modelling technique based on statistical learning theory, support vector machine aims at the achievement of high estimating accuracy. As a result, a new moisture content model for Sugi drying process is proposed by using support vector machine technique, including free moisture content model and bound moisture content model. Also, infinite impulse response filter technology is considered to filter the estimating output. Simulation results are given to show the effectiveness of the proposed method compared with moisture content modelling method based on least square technique.