| 基于差分进化的BP神经网络在纱线质量预测中的应用 |
| |
| 引用本文： | 曹成辉,黄海涛,王强.基于差分进化的BP神经网络在纱线质量预测中的应用[J].河南工程学院学报（自然科学版）,2012,24(3):1-5. |
| |
| 作者姓名： | 曹成辉 黄海涛 王强 |
| |
| 作者单位： | 1. 河南工程学院纺织工程系,河南郑州,450007
2. 方圆标志认证集团山东有限公司,山东济南,250000 |
| |
| 摘 要： | 为了提高BP神经网络在纱线质量预测上的精度,采用差分进化算法训练BP神经网络,利用差分进化算法的全局寻优能力优化BP神经网络的权值和阈值,建立了反映纱线质量的重要指标——单纱强度和条干CV%的神经网络预测模型.对真实数据的测试表明该算法效果良好,提高了BP神经网络算法的预测精度,能够为企业的纱线质量预测提供有效支持.
|
| 关 键 词： | 差分进化算法 BP神经网络 纱线质量 预测 |
Application of BP neural network based on differential evolution algorithm for the prediction of yarn quality |
| |
| CAO Cheng-hui,HUANG Hai-tao,WANG Qiang.Application of BP neural network based on differential evolution algorithm for the prediction of yarn quality[J].Journal of Hennan Institute of Engineering(Natural Science Edition),2012,24(3):1-5. |
| |
| Authors: | CAO Cheng-hui HUANG Hai-tao WANG Qiang |
| |
| Affiliation: | 1.Department of Textile Engineering,Henan Institute of Engineering,Zhengzhou 450007,China; 2.China Quality Mark Certification Group Shandong Company Limited,Jinan 250000,China) |
| |
| Abstract: | In order to improve the prediction accuracy of the BP neural network in yarn quality,the Differential Evolution(DE) algorithm was adopted to train the BP neural network,using the ability of global optimization of DE algorithm to optimize the weight values and threshold values of BP neural network,and the prediction models were established for important indexes of yarn quality: the single yarn strength and the unevenness value CV.The experimental data showed that the algorithm proposed in this paper enhanced the prediction accuracy of the BP neural network algorithm,and could provide effective support for enterprises in the prediction of yarn quality. |
| |
| Keywords: | differential evolution algorithm BP neural network yarn quality prediction |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
