| 一种用于BP神经网络训练的改进遗传算法 |
| |
| 引用本文： | 周祥,陈丙珍,何小荣. 一种用于BP神经网络训练的改进遗传算法[J]. 化工学报, 2001, 52(10): 925-927 |
| |
| 作者姓名： | 周祥 陈丙珍 何小荣 |
| |
| 作者单位： | 清华大学化学工程系 |
| |
| 摘 要： | 引 言近年来 ,人工神经网络已广泛应用于化工领域中的参数预测及故障诊断等方面[1,2 ] ,其中最常用的是ＢＰ网络 ,它能够模拟很多映射关系[3 ,4 ] .但在ＢＰ网络的训练过程中 ,如何跳出局部极小点是一个难点 ,对此前人已有一些研究成果 ,其中包括改进的梯度下降搜索法 (ｇｒａｄｉｅｎｔｄｅｓｃｅｎｄｒｅｓｅａｒｃｈ ,ＧＤＲ) [5] 、模拟退火法 (ｓｉｍｕｌａｔｅｄａｎｎｅａｌｉｎｇ ,ＳＡ) [6]和ＥＧＡ算法 (ｅｘｔｅｎｄｅｄｇｅｎｅｔｉｃａｌｇｏｒｉｔｈｍ)等[7,8] .本文对局部极小点产生的主要原因进行了分析 ,并对遗传算法中的…
|
| 关 键 词： | BP神经网络 局部极小点 遗传算法 评价函数 变异模型 化工生产 应用 |
| 文章编号： | 0438-1157(2001)10-0925-03 |
| 修稿时间： | 2000-10-20 |
IMPROVED GENETIC ALGORITHM FORTRAINING OF BP NEURAL NETWORK |
| |
| ZHOU Xiang,CHEN Bingzhen,HE Xiaorong. IMPROVED GENETIC ALGORITHM FORTRAINING OF BP NEURAL NETWORK[J]. Journal of Chemical Industry and Engineering(China), 2001, 52(10): 925-927 |
| |
| Authors: | ZHOU Xiang CHEN Bingzhen HE Xiaorong |
| |
| Abstract: | The training process of Back Propagation Neural Network (BPNN) is easily converged at a local minimum, which slows the training process sharply.In this paper, an analysis is given to the chief formative reason of local minimum, and an improved Genetic Algorithm (GA) is introduced to overcome local minimum.Most BPNNs use Sigmoid function as the transfer function of network nodes, this paper indicates that the flat characteristic of Sigmoid function results in the formation of local minimum.In the improved GA, pertinent modifications are made to the evaluation function and the mutation model.The evaluation of solution is associated with both values of error function and gradient model corresponding to the certain solution, so that solutions away from local minimum are highly evaluated.The sensitivity of error function to network parameter is imported to form a self-adapting mutation model, which is powerful to diminish error function.Both modifications help to drive solutions out of local minimum.A case study of a real industrial process shows the advantage of the improved GA to overcome local minimum and to accelerate the training process. |
| |
| Keywords: | BP neural network local minimum GA evaluation function mutation model |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《化工学报》浏览原始摘要信息 |
|
点击此处可从《化工学报》下载免费的PDF全文 |
|
