Big data analysis on manufacturing variables affecting properties of medium density fiberboard

Abstract

The properties of medium density fiberboard (MDF) panels manufactured by reconstituting wood fibers and binders under high temperature and pressure depend on various manufacturing variables, including wood-related parameters, adhesive-related ones, and process-related ones. This study focused on the analysis of big data (about 400 million data) of the manufacturing variables (1389 variables) of MDF panels to understand the influence of these variables on the properties of MDF, using Ridge, Lasso, and Elastic-net regression. Both Lasso and Elastic-net regression were better than Ridge one in predicting the properties of MDF. The analysis results also showed that flash tube dryer, mat forming, and hot-pressing variables were closely related to panel density while fiber bin, refiner, forming, press, and hot-press heating variables affected the modulus of rupture (MOR) of the MDF panel. The analysis of interactions between manufacturing variables and MDF properties showed that the panel density affected internal bond (IB) strength, core density, and moisture content while IB strength and moisture content were associated with the MOR of the MDF panel. However, it is not clear which variables are dominantly affecting the formaldehyde emission of MDF.