| 基于改进BP神经网络的控制图模式识别系统 |
| |
| 引用本文： | 张祥敢,刘长安,方文涛.基于改进BP神经网络的控制图模式识别系统[J].组合机床与自动化加工技术,2011(9). |
| |
| 作者姓名： | 张祥敢 刘长安 方文涛 |
| |
| 作者单位： | 1. 山东大学机械学院,济南,250061
2. (颐中)青岛烟草机械有限公司,山东青岛,266021 |
| |
| 摘 要： | 提出一种基于激励函数参数可调和动态阈值的改进BP神经网络控制图模式识别算法,并优化Monte Carlo工序数据模拟方法,使样本数据更具与实际生产数据相同的质量特性.根据改进后的网络参数迭代公式,将预处理后的样本数据作为输入对该神经网络识别器进行训练,训练结果用于生产过程的控制图模式识别.改进BP神经网络识别器的拓扑结构简单,在保证识别精度的前提下,提高识别速度,改善神经网络的泛化能力.最后,通过计算机模拟和生产现场应用验证该算法的可行性.
|
| 关 键 词： | 改进BP神经网络 控制图模式识别 Monte Carlo方法 |
The System of Control Chart Pattern Recognition Based on Improved BP Neural Network |
| |
| ZHANG Xiang-gan,LIU Chang-an,FANG Wen-tao.The System of Control Chart Pattern Recognition Based on Improved BP Neural Network[J].Modular Machine Tool & Automatic Manufacturing Technique,2011(9). |
| |
| Authors: | ZHANG Xiang-gan LIU Chang-an FANG Wen-tao |
| |
| Affiliation: | ZHANG Xiang-gan1,LIU Chang-an1,FANG Wen-tao2(1.School of Mechanical Engineering,Shandong University,Jinan 250061,China,2.Etsong(Qindao) Tobacoo Machinery Co.,Led.,Qindao Shandong 266021,China) |
| |
| Abstract: | An improved back propagation neural network algorithm for control chart pattern recognition is proposed,which is based on adjustable activation function parameters and dynamic threshold.In order to make the quality characteristics of sample data the same as actual production data,an optimized process data Monte Carlo simulation method is also proposed.From the iterative formula of improved network parameters,the sample data is pretreated as input to the neural network recognizer for training,and the trainin... |
| |
| Keywords: | improved BP neural network control chart pattern recognition Monte Carlo method |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
