|
|||||
|
|
| 基于神经网络的多参数矿井火灾识别方法 | |
| 引用本文： | 任慧,孙继平,田子建,王会芹.基于神经网络的多参数矿井火灾识别方法[J].辽宁工程技术大学学报(自然科学版),2007,26(4):555-558. |
| 作者姓名： | 任慧 孙继平 田子建 王会芹 |
| 作者单位： | 1. 中国传媒大学,自动化系,北京,100024;中国矿业大学(北京)煤炭资源与安全开采国,家重点实验室,北京,100083 2. 中国矿业大学(北京)煤炭资源与安全开采国,家重点实验室,北京,100083 3. 中国传媒大学,自动化系,北京,100024 |
| 基金项目： | 高等学校博士学科点专项科研基金资助项目(20050290010) |
| 摘 要： | 针对矿井火灾早期预测预报研究了新的方法,将矿井火灾图像与温度、烟雾、CO、CO2、O2等多个参数相结合,进行综合分析,对矿井火灾进行判断。依据神经网络建立的数学模型,采用神经网络的学习算法,对矿井火灾进行识别。通过仿真分析结果表明,矿井火灾正确识别率很高,特别是采用RBF神经网络,正确识别率达到98%以上,从而为神经网络实际用于矿井火灾识别成为可能,该方对矿井火灾早期预测预报具有重要的理论意义和实用价值。 |
| 关 键 词： | 矿井火灾 多参数 神经网络 火灾识别 |
| 文章编号： | 1008-0562（2007）04-0555-04 |
| 修稿时间： | 2006-04-12 |
Mine fire identification method with multi-parameters based on neural network |
|
| REN Hui,SUN Ji-ping,TIAN Zi-jian,WANG Hui-qin.Mine fire identification method with multi-parameters based on neural network[J].Journal of Liaoning Technical University (Natural Science Edition),2007,26(4):555-558. | |
| Authors: | REN Hui SUN Ji-ping TIAN Zi-jian WANG Hui-qin |
| Affiliation: | 1.Automation Department, Communication University of China, Beijing 100024,China; 2.China University of Mining and Technology(Beijing |
| Abstract: | In view of the early prediction of mine fires,a new method has been studied.Combined mine fire image with temperature,smoke,CO,CO2,O2 and many other parameters are comprehensively analyzed and the method can be used to predict mine fires.Based on neural network,the mathematical model is set up.With study algorithm of neural network,the model can identify mine fires.By simulation analysis of mine fire,the correct recognition rate of mine fire is very high.Especially when RBF neural network model is employed,the correct recognition rate is more than 98 %.So,it is possible that the neural network is used to identify mine fires.The study and application of this method has a great theoretical and practical value for early prediction of mine fires. |
| Keywords: | mine fire multi-parameter neural network fire identification |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |
