Prediction of Thermal Modified Wood Color Change after Artificial Weathering Based on IPSO-SVM Model

Abstract

Abstract The support vector machine (SVM) model was applied to the prediction of the color change of heat-modified wood after artificial weathering. In order to improve the prediction performance, the improved particle swarm optimization (IPSO) algorithm was used to optimize the parameters of the SVM model, and the IPSO-SVM model was established based on the nonlinear descending weight strategy to improve the particle swarm optimization. To verify the performance of the established model, MAE, RMSE and R2 of the test set and training set were compared with the PSO-SVM model and SVM model. According to the analysis of the results, the RMSE of the training set data of IPSO-SVM model is reduced by 49% and 72%, the MAE is reduced by 52% and 78%, and the RMSE of the test set data is reduced by 6% and 24%, and the MAE is reduced by 2% and 25%, respectively. The results show that the support vector machine optimized by the improved particle swarm optimization algorithm is more accurate in predicting the color change of the heat-modified wood after artificial weathering.