矿井带式输送机胶带火灾是严重威胁煤矿安全生产的重大灾害之一。运输机胶带不同于一般的矿井可燃物，具有分布连续、影响范围广等特点。一方面，胶带火灾的蔓延速度极快，而且燃烧时会产生大量的毒害气体，易滋生二次灾害；另一方面，胶带输送机大多安装于进风巷道中，一旦发生胶带火灾，胶带火灾产生的大量毒害气体在短时间内会随风流扩散到其他巷道或采煤工作面，危害速度极快、波及范围极广，会造成人员的重大伤亡以及财产和资源的重大损失。为了避免胶带火灾事故造成更大的损失，不能只将重点放在火灾事故发生前的预防上，应对矿井胶带火灾事故进行超前预测，将其扼杀于摇篮之中。

针对矿井输送机胶带火灾动态监测预警的技术难题，本文通过矿井胶带火灾热解与燃烧特性实验研究，确定了矿井胶带火灾监测预警指标，在无线自组网、传感器动态监测、火灾报警与联动控制、危险程度预测等方面进行创新研究与开发。首先，本文研究矿井胶带火灾预警指标，对于矿井胶带火灾风险预警指标内在关联性差、火灾不同发展阶段的标志性气体和特征温度不明确、火灾风险预警指标缺失等难题，研究了矿井胶带火灾热解燃烧的特性，总结出胶带火灾监测预警指标；其次，进行矿井胶带火灾无线智能监测技术研究，研发具有高透传、低功耗、抗干扰、防水、防尘、防爆的无线温度、气体传输终端，网关、井下分站、地面传输接口设备，实现对胶带运输巷道的精准监测预警；随后，针对矿井胶带火灾危险程度预测的难题，建立了基于粒子群算法优化支持向量机的模型，并对模型进行了最优参数与效果的研究分析，在训练集输出，PSO-SVM与SVM比较，平均绝对误差减小了36.9919，平均相对误差减小了0.3599，均方误差减小了4463.6804，R²拟合系数提高了0.0856；在测试集输出，PSO-SVM与SVM比较，平均绝对误差减小了41.3368，平均相对误差减小了0.3820，均方误差减小了5237.3317，R²拟合系数提高了0.0957。最后，开发矿井胶带火灾预警与危险程度预测系统在线监测软件，实现矿井输送机胶带火灾隐患和事故的超前监测预警，提高了矿井巷道胶带火灾指标气体信息提取的时效性、可靠性和准确性，确保了工作人员的生命安全和煤矿的安全生产。

本论文的研究成果，在金鸡滩煤矿胶带运输巷道进行了现场应用，测试了系统的可行性与稳定性，现场应用情况表明，本系统可以有效监测胶带运输巷道内胶带火灾的指标参数，并做出危险程度预测，实现了地面调度室对胶带运输巷道的精准实时动态监测。本文研究结果可为矿井胶带火灾监测预警与危险程度预测提供理论和实际依据，具有一定的现实意义。

Mine belt conveyor tape fires are one of the major hazards that seriously threaten the safety of coal mine production. Unlike normal mine combustibles, conveyor tapes are continuously distributed and have a wide area of influence. On the one hand, tape fires spread very quickly and produce a large amount of toxic gas when burning, which can easily breed secondary disasters; on the other hand, tape conveyors are mostly installed in the inlet tunnel, once a tape fire occurs, the tape fire produces a large amount of toxic gas in a short period of time with the wind flow will spread to other tunnels or coal mining face, the damage is extremely fast and widespread, which can cause heavy casualties This can result in heavy casualties and significant damage to property and resources. In order to avoid greater losses from tape fires, the focus should not only be on the prevention of fires before they occur, but also on the prediction of mine tape fires in advance, so that they can be nipped in the bud.

In this paper, we identify a system of indicators for monitoring and early warning of mine belt fires through experimental research on the pyrolysis and combustion characteristics of mine belt fires, and carry out innovative research and development in the areas of wireless self-organising networks, dynamic sensor monitoring, fire alarm and linkage control, and hazard prediction. Firstly, this paper studies the early warning indicator system for mine tape fires, and summarises the tape fire monitoring and early warning indicator system with regard to the challenges of poor intrinsic correlation of mine tape fire risk early warning indicators, unclear signature gases and characteristic temperatures at different stages of fire development, and the lack of fire risk early warning indicators, etc.; secondly, it conducts wireless intelligent monitoring technology for mine tape fires The research was carried out to develop wireless temperature and gas transmission terminals, gateways, underground substations and ground transmission interface devices with high transmission, low power consumption, anti-interference, waterproof, dustproof and explosion-proof, to realise accurate monitoring and early warning of tape transport roadways; subsequently, a model based on particle swarm algorithm optimised support vector machine was established to address the difficult problem of predicting the risk level of mine tape fires, and the optimal parameters and effects of the model were studied and analysed. In the training set, the average absolute error of PSO-SVM was reduced by 36.9919, the average relative error was reduced by 0.3599, the mean square error was reduced by 4463.6804, and the R² fitting coefficient was improved by 0.0856; in the test set, the average absolute error of PSO-SVM was reduced by 41.3368, and the average relative error was reduced by 0.0856. Finally, the development of online monitoring software for the mine tape fire warning and hazard level prediction system has improved the timeliness, reliability and accuracy of the extraction of gas information from mine tunnel tape fire indicators. This improves the timeliness, reliability and accuracy of the extraction of gas information from mine roadway tape fire indicators, ensuring the safety of staff lives and the safe production of the mine.

The results of this thesis have been applied to the tape transport roadway in Jinjitan coal mine to test the feasibility and stability of the system. The field application shows that the system can effectively monitor the indicator parameters of tape fires in the tape transport roadway and make hazard level prediction, realising accurate real-time dynamic monitoring of the tape transport roadway in the ground dispatching room. The results of this study provide a theoretical and practical basis for monitoring and predicting the danger level of tape fires in mines, and are of some practical significance.

参考文献

[1] 顾海荣, 郭项伟, 徐信芯， 等. 基于最小二乘圆法的救援井井径动态测量系统设计[J]. 实验室研究与探索, 2021, 40(08):78-82.

[2] 李伟荣, 孙轩, 杨小龙， 等. 浅析控制和减少煤矿职工不安全行为的重要意义[J]. 内蒙古煤炭经济, 2021, No.321(04):84-85.

[3] 王洋, 刘广新, 李焕忠. 抚顺东露天矿采场火灾辨识分析及防治方案[J]. 露天采矿技术, 2021, 36(01):102-105.

[4] 王国法, 庞义辉, 李爽, 等. 基于煤矿时空多源信息感知的智能安控闭环体系[J]. 矿业安全与环保, 2022, 49(04):1-11.

[5] 白光星, 陈炜乐, 孙勇, 等. 煤矿带式输送机运输火灾风险智能监测与早期预警技术研究进展[J]. 煤矿安全, 2022,53(09):47-54.

[6] 袁广忠, 徐长友, 平彦军, 等. 国家电投集团内蒙古能源有限公司智能化建设探索与实践[J]. 中国煤炭, 2021, 47(S1):45-49.

[7] 陈晓. 基于数据挖掘的煤矿安全管理知识可视化研究[D]. 中国矿业大学(北京), 2017.

[8] 潘科, 秦华礼, 郑晓云, 等. 基于气味探测技术的矿井输送机胶带火灾监测[J]. 安全与环境学报, 2007(01):118-121.

[9] 苏墨. 矿井胶带火灾灾变规律数值模拟及自动灭火系统设计研究[D]. 太原理工大学, 2017.

[10] 苏墨, 王飞. 矿井胶带火灾模拟与逃生影响因素分析研究[J]. 中国矿业, 2017, 26(07):168-172.

[11] 郭军, 刘荫, 金永飞, 等. 矿井胶带火灾巷道环境多参数时空演化规律[J]. 西安科技大学学报, 2019, 39(01):21-27.

[12] 刘永泰, 方文韬, 黄宇, 等. 带式输送机封闭通廊火灾特性研究[J]. 安全与环境工程, 2021, 28(04):21-28.

[13] Perera I E, Litton C D. Impact of Air Velocity on the Detection of Fires in Conveyor Belt Haulageways [J]. Fire Technology, 2012, 48(2):405-418.

[14] Krawiec P, Warguła Ł, Czarnecka-Komorowska D, et al. Chemical compounds released by combustion of polymer composites flat belts[J]. Scientific Reports, 2021, 11(1): 1-10.

[15] Hoff H. Using distributed fibre optic sensors for detecting fires and hot rollers on conveyor belts[C]//2017 2nd International Conference for Fibre-optic and Photonic Sensors for Industrial and Safety Applications (OFSIS). IEEE, 2017: 70-76.

[16] 张泽. 矿井胶带火灾烟气流动模拟及危险区域划分[D]. 西安科技大学, 2017.

[17] Krawiec P, Warguła Ł, Czarnecka-Komorowska D, et al. Chemical compounds released by combustion of polymer composites flat belts[J]. Scientific Reports, 2021,11(1): 1-10.

[18] 马恒, 姚鹏媛, 方博. 矿井通风测试系统的无线传感器网络应用[J]. 辽宁工程技术大学学报(自然科学版), 2016, 35(08):826-830.

[19] 何伟刚, 李政林, 章帆, 等. 基于ZigBee的煤矿井下无线传感器节点设计[J]. 现代电子技术, 2017, 40(02):122-124.

[20] 张美金, 田宇驰, 方志朋. 矿井主运输系统火灾预测的RS-SVM模型[J]. 测控技术, 2018, 37(09):29-32.

[21] 岳宁芳, 蔡国斌, 高文静, 等. 矿井胶带蔓延火灾的细水雾抑制影响因素研究[J]. 中国安全生产科学技术, 2022, 18(04):92-97.

[22] 张圣柱, 程卫民, 张如明, 等. 矿井胶带巷火灾风流稳定性模拟与控制技术研究[J]. 煤炭学报, 2011, 36(05):812-817.

[23] 成聪. 特大型高瓦斯矿井综放工作面瓦斯治理数值模拟研究[D]. 太原理工大学, 2013.

[24] 齐庆杰, 王欢, 董子文, 等. 矿井胶带运输巷火灾蔓延规律的数值模拟研究[J]. 中国安全科学学报, 2016, 26(10):36-41.

[25] 颜国强, 黄启铭, 杜文州, 等. 孔庄煤矿胶带巷火灾预警与控制系统设计[J]. 煤炭工程, 2015, 47(03):20-22+25.

[26] 张李荣. 平直巷道胶带火灾温度场及烟气流动规律实验研究[D]. 西安科技大学, 2016.

[27] 莫志刚, 李军. 胶带运输巷火灾烟流和温度变化的数值模拟[J]. 能源与环保, 2018, 40(01):15-20.

[28] 高江涛, 冉小波, 杨博. 不同氧气浓度下采空区煤自燃极限参数研究[J]. 煤, 2022, 31(04):9-12

[29] 肖国强, 张鹏宇, 马砺, 等. 矿用胶带火灾燃烧特性预测模型[J]. 湖南科技大学学报(自然科学版), 2021, 36(03):9-15.

[30] 马砺, 张鹏宇, 李超华, 等. 不同封堵条件下巷道火灾烟气温度场预测模型[J]. 西安科技大学学报, 2021, 41(02):213-220.

[31] Yang Y, Hou C, Qiao T, et al. Longitudinal tear early-warning method for conveyor belt based on infrared vision[J]. Measurement, 2019, 147: 106817.

[32] Yang R, Qiao T, Pang Y, et al. Infrared spectrum analysis method for detection and early warning of longitudinal tear of mine conveyor belt[J]. Measurement, 2020, 165: 107856.

[33] Amruthnath N, Gupta T. A research study on unsupervised machine learning algorithms for early fault detection in predictive maintenance[C]//2018 5th International Conference on Industrial Engineering and Applications (ICIEA),2018: 355-361.

[34] Ahmad S, Lavin A, Purdy S, et al. Unsupervised real-time anomaly detection for streaming data[J]. Neurocomputing, 2017, 262: 134-147.

[35] Dey P , Saurabh K , Kumar C , et al. t-SNE and variational auto-encoder with a bi-LSTM neural network-based model for prediction of gas concentration in a sealed-off area of underground coal mines[J]. Soft Computing, 2021, 25(22):14183-14207.

[36] 李庆龙, 华炜, 姜洪涛. 热重-红外联用技术在各个领域的应用[J]. 辽宁化工, 2013, 42(09):1086-1088+1099.

[37] 任晓伟, 王振兴, 王锐, 等. 煤矿电缆火灾危险性研究[J]. 煤矿安全, 2022, 53(09):151-156.

[38] 李胜, 张广鑫, 王文博, 等. 基于锥形量热仪法对环氧树脂燃烧性能的研究[J]. 化学与粘合, 2019, 41(06):457-459+483.

[39] Barros-Daza M J, Luxbacher K D, Lattimer B Y, et al. Mine conveyor belt fire classification[J]. Journal of fire sciences, 2022, 40(1): 44-69.

[40] 郑旋. 南屯煤矿相邻采空区自燃隐患监测及防治技术[D]. 西安科技大学, 2017.

[41] 王振平. 基于指标气体的煤自燃程度判定技术基础研究[D]. 西安科技大学, 2006.

[42] Sharma R, Rani S, Memon I. A smart approach for fire prediction under uncertain conditions using machine learning[J]. Multimedia Tools and Applications, 2020, 79(37): 28155-28168.

[43] Barros-Daza M J, Luxbacher K D, Lattimer B Y, et al. Fire Size and Response Time Predictions in Underground Coal Mines Using Neural Networks[J]. Mining, Metallurgy & Exploration, 2022: 1-12.

[44] 王伟峰, 侯媛彬, 邓军, 等. 矿井采空区气体-温度-压差无线传感器的设计及应用[J]. 现代电子技术, 2017, 40(18):117-119.

[45] 陈伟. 一种PCBA自动化测试系统设计[J]. 电子测试, 2022,36(21):114-117.

[46] 曾文琦. 基于单片机的照度稳定可调台灯设计[J]. 电脑与电信, 2022(07):71-76.

[47] 黄磊, 秦耀泽, 郭迎九. 装载机械臂的智能轮式环卫机器人[J]. 物联网技术, 2023, 13(01):77-79.

[48] 叶昌, 王晨, 刘斌, 等. 三相降压/升压/升降压型多功能并网逆变电路[J]. 电力电子技术, 2021, 55(11):25-29.

[49] 万雪芬, 郑涛, 崔剑, 等. 中小型规模智慧农业物联网终端节点设计[J]. 农业工程学报, 2020, 36(13):306-314..

[50] 赵全, 徐光, 郝龙, 等. 基于LoRa的无线多参数环境监测系统设计[J]. 国外电子测量技术, 2019, 38(06):120-124.

[51] 魏源通, 戴亚文. 基于LoRa的工业监测自组网系统设计[J]. 计算机测量与控制, 2019, 27(02):225-228.

[52] 王烨. 矿井胶带火灾烟流蔓延特性与监测方法研究[D]. 西安科技大学, 2021.

[53] 孙英才. 煤矿井下变电所自动防灭火系统设计与应用[J]. 能源技术与管理, 2021, 46(04):126-128.

[54] Carreno A, Inza I, Lozano J A. Analyzing rare event, anomaly, novelty and outlier detection terms under the supervised classification framework[J]. Artificial Intelligence Review, 2019: 1-20.

[55] 陈嘉诚. 基于IFRA和PSO-SVM的干式空心电抗器匝间短路故障检测方法研究[D]. 重庆大学, 2021.

[56] 王珏, 张秀英, 蔡玉芳, 等. 联合小波变换和RSF模型的CT图像分割方法[J]. 光学学报, 2020, 40(21):57-65..

[57] Raffei A F M, Awang N S, Rahman N S A, et al. Internet of Things (IoT) Based Fire Alert Monitoring System for Car Parking[C]//2020 7th International Conference on Electrical and Electronics Engineering (ICEEE). IEEE, 2020: 290-293.

[58] 崔永强. 基于LIF的海面溢油连续区域油膜厚度反演算法研究[D]. 燕山大学, 2021.

[59] Sarwar B, Bajwa I S, Jamil N, et al. An intelligent fire warning application using IoT and an adaptive neuro-fuzzy inference system[J]. Sensors, 2019, 19(14): 3150.

[60] 夏存江, 王文博. 利用组合核函数建立VSV系统回归预测模型[J]. 计算技术与自动化, 2021, 40(02):106-109.

[61] Chen Kang,Peng Huaiwu,Gao Zhenxin, et al. Day-Ahead Operation Analysis of Wind and Solar Power Generation Coupled with Hydrogen Energy Storage System Based on Adaptive Simulated Annealing Particle Swarm Algorithm[J]. Energies, 2022, 15(24).

[62] Chai Wong Siu,Romli Muhammad Izuan Fahmi bin,Yaakob Shamshul Bahar, et al. Regenerative Braking Optimization Using Particle Swarm Algorithm for Electric Vehicle[J]. jaciii, 2022, 26(6).

[63] Deqing Yang. An improved particle swarm optimization algorithm for parameter optimization[J]. Computer Informatization and Mechanical System, 2022, 5(4).

[64] Xu Honglei, Wang Linhuan,Zhang Dalin, et al. Dynamic simulation of wind field in three-dimensional display space considering particle swarm algorithm fuzzy logic[J]. Journal of Intelligent & Fuzzy Systems, 2021, 41(4).