煤矿外因火灾早期探测方法研究

发布时间：2018-11-26 11:22

【摘要】：针对煤矿井下环境特点,提出了基于数字图像处理和支持向量机的煤矿外因火灾早期探测方法。该方法根据火灾初期的变化特征,用图像处理方法提取温度变化率、面积增长率、火焰闪烁频率和整体稳定性等特征值,并将其作为输入信号,利用支持向量机进行数据融合后实现火灾探测。实验结果表明,该方法能够对煤矿井下高危火源和干扰信号进行分类识别,具有探测率高、误判率低、实时性好、鲁棒性强的特点。
[Abstract]:According to the characteristics of underground coal mine environment, this paper presents an early detection method of coal mine external fire based on digital image processing and support vector machine. According to the characteristics of the initial fire, the image processing method is used to extract the characteristic values of temperature change rate, area growth rate, flame flicker frequency and overall stability, and take them as input signals. Support vector machine (SVM) is used to realize fire detection after data fusion. The experimental results show that this method can be used to classify and identify high risk fire sources and interference signals in coal mines, and has the characteristics of high detection rate, low error rate, good real-time performance and strong robustness.
【作者单位】： 西安科技大学电气与控制工程学院;
【基金】：国家自然科学基金项目(51277149) 陕西省教育厅专项项目(14JK1467) 西安科技大学博士启动基金项目(2014QDJ010)
【分类号】：TD752.3
，

本文编号：2358418