| 基于Sigmoid函数参数调整的双隐层BP神经网络的板形预测 |
| |
| 引用本文： | 张雪伟,王焱.基于Sigmoid函数参数调整的双隐层BP神经网络的板形预测[J].化工自动化及仪表,2010,37(4):42-44,48. |
| |
| 作者姓名： | 张雪伟 王焱 |
| |
| 作者单位： | 济南大学,控制科学与工程学院,济南,250022 |
| |
| 基金项目： | 国家自然科学基金，山东省自然科学基金 |
| |
| 摘 要： | 提出一种改进的BP神经网络处理板形缺陷数据的方法,建立双隐层BP神经网络模型,并对Sigmoid激活函数的形状进行调节。将其应用到冷轧的板形缺陷识别中,与利用Levenberg-Marquardt规则训练的BP神经网络预测结果作对比,表明该方法不仅有效地减少双隐层BP网络的学习时间,同时改善了网络的泛化能力,有利于板形缺陷在线识别。
|
| 关 键 词： | 板形识别 双隐层BP神经网络 Sigmoid函数 L-M优化算法 |
Double-layer BP Neural Network Flatness Forecast Based on Parameter Adjustment of Sigmoid Transfer Function |
| |
| ZHANG Xue-wei,WANG Yan.Double-layer BP Neural Network Flatness Forecast Based on Parameter Adjustment of Sigmoid Transfer Function[J].Control and Instruments In Chemical Industry,2010,37(4):42-44,48. |
| |
| Authors: | ZHANG Xue-wei WANG Yan |
| |
| Affiliation: | (School of Control Science and Engineering,University of Jinan,Jinan 250022,China) |
| |
| Abstract: | In order to build a double hidden-layer BP neural network model to adjust the shape of Sigmoid activation function,a method improving the BP neural network to preprocess the plate defective data was proposed.Comparing the data of this method with the formula Levenberg-Marquardt preprocessing method,the results show the time of learning BP neural network can be effectively reduced and the network＇s generalization ability be improved by this method,and it benefits the on-line identification of the plate defects. |
| |
| Keywords: | flatness recognition double-layer BP neural network Sigmoid function Levenberg-Marquardt optimization algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
