| 改进遗传BP网络在涡流检测中的应用 |
| |
| 引用本文： | 刘东辉,孙晓云. 改进遗传BP网络在涡流检测中的应用[J]. 无损检测, 2005, 27(9): 469-471 |
| |
| 作者姓名： | 刘东辉 孙晓云 |
| |
| 作者单位： | 河北科技大学,石家庄,050054 |
| |
| 基金项目： | 河北省自然科学基金资助项目(602378)，河北省教育厅博士基金资助项目(B2001206) |
| |
| 摘 要： | 针对传统的BP算法存在收敛性能差,易陷入局部最小的缺点,在涡流无损检测的缺陷快速识别中,提出采用遗传算法(GA)作为神经网络的学习算法。为避免网络的过早收敛,对传统的遗传BP网络进行了改进,应用自适应算法选择遗传算子值。结果表明,与BP神经网络相比,改进GA神经网络的收敛性能和推广能力都有了显著提高。
|
| 关 键 词： | 涡流检测 遗传算法 收敛 自适应算法 |
| 文章编号： | 1000-6656（2005）09-0469-03 |
| 收稿时间： | 2004-11-19 |
| 修稿时间： | 2004-11-19 |
Neural Network with Improved Genetic Algorithm for Eddy Current Testing |
| |
| LIU Dong-hui,SUN Xiao-yun. Neural Network with Improved Genetic Algorithm for Eddy Current Testing[J]. Nondestructive Testing, 2005, 27(9): 469-471 |
| |
| Authors: | LIU Dong-hui SUN Xiao-yun |
| |
| Abstract: | For eddy current testing, genetic algorithm (GA) was adopted, which could overcome the disadvantages of back propagation (BP) artificial neural network (ANN), such as slow convergence and possibility of being trapped on locally minimum value. Moreover, genetic operators were selected by adaptive algorithm to avoid unwanted early convergence. Compared with BP-ANN, the precision and generalization of GA-ANN were improved remarkably. |
| |
| Keywords: | Eddy current testing Genetic algorithm Convergence Adaptive algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
