| SOFM与BP神经网络在矿井水源判别中的应用 |
| |
| 引用本文： | 孙浩. SOFM与BP神经网络在矿井水源判别中的应用[J]. 华北科技学院学报, 2014, 0(6): 12-16 |
| |
| 作者姓名： | 孙浩 |
| |
| 作者单位： | 华北科技学院安全工程学院,北京东燕郊101601 |
| |
| 摘 要： | 介绍了SOFM神经网络与BP神经网络,以李咀孜煤矿为例,分别利用SOFM网络与BP网络,针对地下水化学特征分别建立突水判别模型,实例结果表明:SOFM网络模型比BP网络模型具有更高的判别精度,更快的运算速度,更好的反应地下水系统特性,为矿井水害防治提供了一种辅助决策手段。
|
| 关 键 词： | 突水水源 SOFM神经网络 BP神经网络 判别模型 |
Comparison of Application on Elman and BP Neural Networks in Discriminating Water Bursting Source of Coalmine |
| |
| SUN Hao. Comparison of Application on Elman and BP Neural Networks in Discriminating Water Bursting Source of Coalmine[J]. Journal of North China Institute of Science and Technology, 2014, 0(6): 12-16 |
| |
| Authors: | SUN Hao |
| |
| Affiliation: | SUN Hao ( North China Institute of Science and Technology, Yanjiao, 101601, China) |
| |
| Abstract: | The discrimination of the mine water - bursting source is deemed to be a basic knowledge for thewater control in the mines. A speedy and precise discrimination is of key importance to the safe production ofthe whole mine. This paper introduces SOFM neural networks and Back -propagation neural networks. TakeLijuzi Mine as an example, establishes the distinguishing model for water bursting by SOFM neural networksand BP neural networks with groundwater chemical characteristics, respectively. Experimental results show thatthe SOFM neural model is more precise and faster than BP neural model in discrimination. The SOFM neuralmodel could better respond characteristics of groundwater systems. It provides an assistant means for decisiori -makingto prevent waterinrush from coal floor. |
| |
| Keywords: | water bursting source elman neural networks back - propagation neural networks discrimi nating model |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
