An optimization algorithm of neural network for wood physical property modeling

Mingbao Li; Jiawei Zhang; Runlong Guo; Hongyu Su

doi:10.1117/12.806743

13 October 2008 An optimization algorithm of neural network for wood physical property modeling

Mingbao Li, Jiawei Zhang, Runlong Guo, Hongyu Su

Proceedings Volume 7127, Seventh International Symposium on Instrumentation and Control Technology: Sensors and Instruments, Computer Simulation, and Artificial Intelligence; 71272F (2008) https://doi.org/10.1117/12.806743
Event: Seventh International Symposium on Instrumentation and Control Technology, 2008, Beijing, China

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.

Citation Download Citation

Mingbao Li, Jiawei Zhang, Runlong Guo, and Hongyu Su "An optimization algorithm of neural network for wood physical property modeling", Proc. SPIE 7127, Seventh International Symposium on Instrumentation and Control Technology: Sensors and Instruments, Computer Simulation, and Artificial Intelligence, 71272F (13 October 2008); https://doi.org/10.1117/12.806743

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available