Neural network based robust variable structure control of wood drying kiln

Abstract

Proper control of the wood-drying kiln is crucial to ensure the satisfactory quality of dried wood and in minimizing drying time and energy. This paper investigates the development and evaluation of a robust control system for a wood drying kiln process incorporating variable structure control (VSC) such that the moisture content of lumber will reach and be stabilized at the desired set point. A description of the dynamics of the wood drying process by means of the time-delay neural network is also presented, in which the back-propagation algorithm was implemented for testing, training and validation. Then this identified model is used for simulation purpose and controller design. For comparison purpose, a conventional proportional-integral-derivative (PID) controller is also employed and system performance is evaluated through simulations. The results are evaluated to tune the controller parameters to achieve good performance in the wood-drying kiln and the VSC strategy promises improved performance. The control system developed in this study may be applied in industrial wood-drying kilns, with a clear potential for improved quality and increased speed of drying.