Share Email Print
cover

Proceedings Paper

An optimization algorithm of neural network for wood physical property modeling
Author(s): Mingbao Li; Jiawei Zhang; Runlong Guo; Hongyu Su
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

As a heterogeneous nature material, there are unknown nonlinear relationships existing in the wood physical property modeling. To solve the complex nonlinear relationship of modeling parameters, an optimization algorithm of neural network based on Gauss-Chebyshev for wood physical property modeling is presented in this paper. The density of wood ring and moisture content are considered as the model inputs, while wood vertical elastic modulus as the output. By comparison the performance between Gauss neural network and Gauss-Chebyshev neural network, the latter is convergence fast with high generalization ability and approximation accuracy of the model.

Paper Details

Date Published: 13 October 2008
PDF: 6 pages
Proc. SPIE 7127, Seventh International Symposium on Instrumentation and Control Technology: Sensors and Instruments, Computer Simulation, and Artificial Intelligence, 71272F (13 October 2008); doi: 10.1117/12.806743
Show Author Affiliations
Mingbao Li, Northeast Forestry Univ. (China)
Jiawei Zhang, Northeast Forestry Univ. (China)
Runlong Guo, Northeast Forestry Univ. (China)
Hongyu Su, Northeast Forestry Univ. (China)


Published in SPIE Proceedings Vol. 7127:
Seventh International Symposium on Instrumentation and Control Technology: Sensors and Instruments, Computer Simulation, and Artificial Intelligence

© SPIE. Terms of Use
Back to Top