Modeling of temperature-humidity for wood drying based on time-delay neural network

Abstract

The temperature-humidity models of wood drying were developed based on Time-delay neural network and the identification structures of Time-delay neural network were given. The controlling model and the schedule model, which revealed the relation between controlling signal and temperature-humidity and the relation between wood moisture content and temperature-humidity of wood drying, were separately presented. The models were simulated by using the measured data of the experimental drying kiln. The numerical simulation results showed that the modeling method was feasible, and the models were effective.

Keywords

Wood drying / Temperature-humidity model / System identification / Time-Delay neural network

References

[1] Cloutier A., Fortin Y. A model of moisture movement in wood based on water potential and the determination of the effective water conductivity [J]. Wood Science Technology, 1993, 27(2): 95-114.

[2] Dedic A. Dj., Mujumdar A.S., Voronjec D.K. A three dimensional model for heat and mass transfer in convective wood drying [J]. Drying Technology, 2003, 21(1): 1-15.

[3] He Y., Li X. Neural network control technology and application [M], 2000 Beijing: Science Press 45-54.

[4] Hua L., Bibeau E., Gartshore P.F. et al. Modeling of airflow in wood kilns [C], 1998 Portland, Oregon: Portland Wood Show 121-127.

[5] Hukka A. Deformation properties of Finnish spruce and pine wood in tangential and radial directions in association to high temperature drying. Part III. Experimental results under drying conditions (mechano-sorptive creep) [J]. Holz als Roh-und Werkstoff, 2000, 58: 63-71.

[6] Kaiser M. Time-delay neural network for control [C], 1994 Capri, Italy: IFAC Symposium on Robot Control 851-856.

[7] Kumpati S.N., Kannan P. Identification and control of dynamical systems using neural network [J]. IEEE Transactions on Neural Network, 1990, 1(1): 4-27.

[8] Pang, S. 1996. Development and validation of a kiln-wide model for drying of softwood lumber[C]. Proceedings of 5th International IUFRO Wood Drying Conference, Quebec City, Canada, p103–110

[9] Perre P., Turner I.W. The use of numerical simulation as a cognitive tool for studying the microwave drying of softwood in an over-sized waveguide [J]. Wood Science Technology, 1999, 33(6): 445-464.

[10] Salin J.G. Analysis and optimization of the conditioning phase in timber drying [J]. Drying Technology, 2001, 19(8): 1711-1724.

[11] Shi Dan, Zhang Hongjian, et al. 2002. Time-delay neural network for the prediction of carbonation tower’s temperature [C]. 19th IEEE Instrumentation and Measurement Technology Conference, Anchorage, Alaska, USA, 21–23, May, p379–383

[12] Sun Z., Bannister P., Carrington C.G. Dynamic modeling of the wood stack in a wood drying kiln [J]. Chemical Engineering Research & Design, 2000, 78(A1): 107-117.

[13] Tarasiewicz S., Leger F. Modeling simulation and control of the wood drying process. Part 1. A set of PDE’s as an internal model [J]. Drying Technology, 1998, 16(6): 1075-1084.

[14] Wang, G.X., Liu Wei, Gu Lizhu, et al. 2001. Development of an intelligent control system for wood drying processes [C]. 2001 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM2001), Teatro Sociale, Como, Italy, July 8–12, p371–376

[15] Xu L. Neural Network for control [M], 1999 Harbin: Harbin Industry University Press 45-48.

[16] Yan, G., De Silva, C.W., Wang, G.X. 1999. Modeling and adaptive control of a kiln dryer for wood [C]. IASTED International Conference on Control and Applications, Banff, Canada, July 25–29, p144–149