OPTIMIZED MODELING OF WOOD DRYING PROCESS USING KERNAL PRINCIPAL COMPONENT ANALYSIS AND PSO-SVM

摘要

It is the key to establish the model which can describe wood drying regular accurately and integrally to realize online predictive control and improve control level in wood drying process. To aim at the test sample data that had much interference and redundancy in drying process, this paper adopted Kernel Principal Component Analysis (KPCA) to pretreat wood drying data, and then established the wood drying model based on PSO-SVM. The results of simulation experiments showed that the model established on the basis of the pretreated and dimension reduced training sample data had strong practicability, and could get better predictive accuracy, less computations and higher computing speed.