Abstract: The principal problems to realize fully automatic control of drying are mathematical modeling and carrying out drying schedule. The paper applied neural network to the research of wood drying control, established time-delay neural network schedule model useful to wood moisture content prediction, gave the identification structure of time-delay neural network and used practical drying data of three species to train and test the networks. The simulation results showed that the prediction model were feasible, effective, and had good ability of dynamic track and forecasting characteristics, which did not only realize mathematical modeling for drying schedule, but were significant to optimize schedule implementation and control of wood drying as well.

Key words: wood moisture content, model, identification, time-delay neural network, prediction