| 粒子群优化神经网络在木材干燥动态建模中的应用 |
| |
| 引用本文： | 刘德胜,张佳薇.粒子群优化神经网络在木材干燥动态建模中的应用[J].佳木斯大学学报,2007,25(1):46-48. |
| |
| 作者姓名： | 刘德胜 张佳薇 |
| |
| 作者单位： | 东北林业大学机电学院,黑龙江,哈尔滨,150040;佳木斯大学信息电子技术学院,黑龙江,佳木斯,154007;东北林业大学机电学院,黑龙江,哈尔滨,150040 |
| |
| 摘 要： | 木材干燥是一个复杂的非线性系统,由于木材结构复杂且具有多样性和变异性,很难建立一个理想的符合木材干燥过程的数学模型.提出了利用粒子群算法的全局寻优能力优化动态递归网络连接权值系数的方法,对木材干燥动态建模.仿真结果表明:粒子群优化BP算法建立木材干燥动态模型提高了期望误差精度和收敛速度,避免了BP算法陷入局部极小值,具有较好的预测精度.
|
| 关 键 词： | 粒子群算法 神经网络 木材干燥 |
| 文章编号： | 1008-1402（2007）01-0046-03 |
| 收稿时间： | 2006-10-09 |
| 修稿时间： | 2006年10月9日 |
Application on Dynamics Modeling of Wood Drying Based on Neural Network Evolved by Particle Swarm Optimization |
| |
| LIU De-sheng,ZHANG Jia-wei.Application on Dynamics Modeling of Wood Drying Based on Neural Network Evolved by Particle Swarm Optimization[J].Journal of Jiamusi University(Natural Science Edition),2007,25(1):46-48. |
| |
| Authors: | LIU De-sheng ZHANG Jia-wei |
| |
| Institution: | 1. College of Mechanics and Eiectridty, Northeast Forestry University, Harbin 150040, China; 2. Department of Infoation and Electronic Teclnology,Jiamusi 154007, China |
| |
| Abstract: | For the variety,complexity and variability of wood,its drying process is a complicated nonlinear system,so it is difficult to get an ideal model for wood drying.The initial weights of dynamical recurrent neural network were evolved by the characteristics of global optimization of particle swarm optimization algorithm.Lumber Moisture Content models are obtained in this paper.Training results showed that mean-square errors and accelerate of convergence were improved with PSO-BP lumber moisture Content models and BP arithmetic immersion minim value was avoided,showed relatively high prediction precision. |
| |
| Keywords: | particle swarm optimization algorithm neural network wood drying |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
