基于BP神经网络的矿井热动力灾害监测研究
Research on Mine Thermodynamic Disaster Monitoring Based on BP Neural Network
-
摘要: 针对煤矿井下热动力灾害监测方式单一、易产生误判漏判等问题,提出一种基于BP神经网络的矿井热动力灾害监测方法。该方法根据矿井热动力致灾因素之间的相互耦合关系,利用多源数据融合的数据-特征-决策三级架构,首先在数据级利用卡尔曼滤波算法对特征参量数据进行归一化优化处理;然后在特征级采用BP神经网络对特征参量数据进行多源融合识别,获得煤层自燃和明火燃烧的特征识别结果;最后在决策级将特征识别结果与瓦斯浓度、煤尘浓度和特征信号持续时间相融合,得出最终监测判决结果。研究表明:该方法综合多参数融合判断,提高判决辨识矿井热动力灾害的准确率,能有效解决对矿井热动力灾害监测的误判漏判问题。Abstract: Aiming at the problems of the monitoring method of thermodynamic disaster in coal mines is single, which are prone to misjudgment and leakage, a method for monitoring thermodynamic disaster of mines based on BP neural network is proposed. According to the mutual coupling relation of the mine thermodynamic causal factors, the method uses three-level architecture for data-characteristics-decision of multi-source data fusion, first, the feature parameter data is normalized using the Kalman filter algorithm at the data level, and then, BP neural network is used for multi-source fusion recognition of feature parameter data at feature level to obtain the feature recognition result of coal seam spontaneous combustion and open flame combustion. Finally, the characteristic recognition results are fused with gas concentration, coal dust concentration and characteristic signal duration at the decision level to get the final monitoring verdict results. The research shows that this method integrates multi-parameter fusion judgments, improves the accuracy of judgment and identification of mine thermodynamic disaster, can effectively solve the problem of misjudgment and leakage of mine thermodynamic disaster monitoring.
-
Keywords:
- thermodynamic disaster /
- data fusion /
- Kalman filter /
- BP neural network /
- gas concentration
-
-
[1] 丁百川.我国煤矿主要灾害事故特点及防治对策[J].煤炭科学技术,2017,45(5):109-114. [2] 梁运涛,侯贤军,罗海珠,等.我国煤矿火灾防治现状及发展对策[J].煤炭科学技术,2016,44(6):1-6. [3] 孙继平,孙雁宇.矿井火灾监测与趋势预测方法研究[J].工矿自动化,2019,45(3):1-4. [4] 王德明.煤矿热动力灾害及特性[J].煤炭学报,2018, 43(1):137-142. [5] 闫晗晗,邢波涛,任璐,等.遥感数据融合技术文献综述[J].电子测量技术,2018,41(9):26-36. [6] LauBPL, Marakkalage SH, Zhou Y, et al. A Survey of Data Fusion in Smart City Applications[J]. Information Fusion, 2019, 52: 357-374. [7] 侯秀丽,阮进军.无线传感网络多源信息融合技术研究[J].电子世界,2019(5):199-200. [8] 罗俊海,杨阳.基于数据融合的目标检测方法综述[J].控制与决策,2020,35(1):1-15. [9] 傅剑锋,雍静.基于数据融合技术的火灾探测算法[J].低压电器,2007(12):22-24. [10] 刘天奇.不同煤质煤尘云与煤尘层最低着火温度实验研究[J].燃烧科学与技术,2019,25(5):445-450. [11] 沈云鸽,王德明,朱云飞.不同自燃倾向性煤的指标气体产生规律实验研究[J].中国安全生产科学技术,2018,14(4):69-74. [12] 刘浩雄,刘贞堂,钱继发,等.煤尘二次爆炸特性研究[J].工矿自动化,2018,44(6):80-86. [13] 梁燕华,张传斌.基于神经网络数据融合实现火灾预警[J].科技传播,2017,9(4):11-12. [14] 张令心,戴静涵,沈俊凯,等.基于LM-BP神经网络的钢筋混凝土框架结构震害快速预测模型[J].自然灾害学报,2019,28(2):1-9. [15] Nagalakshmi S, Kamaraj N. On-line Evaluation of Loa-dability Limit for Pool Model with Tcsc Using Back Propagation Neural Network[J]. International Journal of Electrical Power and Energy Systems, 2013, 47: 52. [16] 连方圆,白静.一种改进的基于神经网络的WSN数据融合算法[J].计算机测量与控制,2014,22(2): 476-479. [17] 潘正华.模糊推理算法的数学原理[J].计算机研究与发展,2008,45(S1):165-168. [18] Ojha V, Abraham A, Sná?觢el V. Heuristic Design of Fuzzy Inference Systems: a Review of Three Decades ofResearch[J]. EngineeringApplications of Artificial Intelligence, 2019, 85: 845-864. [19] 王兰婷,裴道武.一般全蕴涵模糊推理方法[J].模糊系统与数学,2019,33(3):46-55. [20] 张琦,朱合华,黄贤斌,等.基于Mamdani模糊推理的山岭隧道围岩RMR14分级[J].岩土工程学报,2017, 39(11):2116-2124. [21] 王坚,史朝辉,郭新鹏,等.Mamdani模糊推理算法的直觉化扩展[J].计算机科学,2016,43(S1):44-45. [22] 李长龙,刘伟,周邵萍.基于Mamdani模糊推理的槽罐车运输安全评价[J].华东理工大学学报(自然科学版),2017,43(4):591-596.
计量
- 文章访问数: 29
- HTML全文浏览量: 0
- PDF下载量: 1
下载:
