Least Squares Support Vector Machines(LSSVM) regression principle and measure methods of moisture content during wood drying were introduced. Wood moisture content is a key parameter for regulating and controlling wood drying proces. In this paper soft sensor model based on LSSVM was established for the weakness of wood moisture content measurement in drying process, and parameters selection adopted improved exhaust algorithm. The simulation results of Fraxinus mandshurica and Xylosma racemosum showed that the LSSVM soft sensor model had well robustness and generalization ability, and could predict wood moisture content measurement in drying process accurately, which offered an effective approach for measuring the parameters in the complicated and nonlinear process of wood drying.

Soft sensor modeling of moisture content in drying process based on LSSVM

There are some problems with the strip steel heated in the annealing furnace such as the multiple correlations between temperature in the annealing furnace, steel strip tension, tension roll speed and other variables, noise in field data, which lead to the difficulty to predict the time of welding seam achieved air-knife. The least square support vector machine (LSSVM) inductance model optimized by the particle swarm optimization with compression factor (PSO-CF) algorithm is presented for the difficulty of the time prediction in this paper. The improved algorithm can improve PSO convergence accuracy, and effectively avoid falling into local optimum. It can be both the global fitting ability and local fitting ability of least squares support vector machine. The parameters of LSSVM model are optimized by improved PSO-CF algorithm to escape from the blindness of man-made choice. Using the algorithm in prediction of the arrival time and the position of welding seam, the numerical simulation results illustrate good generalization performance and prediction ability of the proposed method.

Application of soft sensor in welding seam tracking prediction based on LSSVM and PSO with compression factor

An intelligent MC measuring system for lumber was designed by the authors and presented in this article.The hardware circuit and software flow chart of this system are described in detail.A dynamic compensation method is applied to eliminate zero drift and temperature drift errors.A test showed that the mean errors of the measured results from this new system was less than 4% above fiber saturation point,and less than 2% below fiber saturation point,and even lower tian 1% around the final MC(14%～9%).These results demonstrated the precision and reliability of the system to be effectively improved.

Zhao Zhen-fei

Papers

Design of an Intelligent and Automatic Lumber Moisture Content Measuring System