我国煤矿瓦斯灾害严重，同时瓦斯资源赋存丰富，瓦斯抽采可有效防治瓦斯灾害并利用瓦斯资源。管道是瓦斯抽采的有效载体，受井下条件复杂、管道老化等影响，瓦斯抽采管道不可避免会存在破裂泄漏现象，降低瓦斯抽采效率。为进一步揭示矿井瓦斯抽采管道泄漏气体流动规律，提高瓦斯抽采管道泄漏事故的诊断效率，本文采用理论分析、数值模拟、物理实验、机器学习以及现场验证相结合的方法，分析了瓦斯抽采管道气流流动特性的影响因素，研究了不同影响因素下抽采管道泄漏气体流动规律，建立了基于集成学习的瓦斯抽采管道漏点判识模型，开发了瓦斯抽采管道泄漏判识平台。

利用流体力学等理论，建立了瓦斯抽采管道泄漏气体流动模型，分析了瓦斯抽采管道泄漏的主要形式以及影响因素。采用Comsol Multiphysics数值模拟软件，研究了瓦斯抽采管道泄漏气体流动特性，得到管道泄漏稳态条件下，管道瓦斯体积分数、流速以及负压与漏点孔径、管道直径、出口负压及入口流速的相关关系。通过分析不同泄漏时间下管道瓦斯体积分数及流速变化规律，获得瓦斯体积分数与漏点孔径呈负相关，与管道直径呈正指数相关，与出口负压以及入口流速呈负指数函数关系；气体流速与漏点孔径呈正指数函数关系，与管道直径呈负相关，与出口负压以及入口流速呈正相关。

通过自主研发的矿井瓦斯抽采管道泄漏气体流动模拟实验系统，研究了不同漏点孔径以及泄漏位置对管道气体流动的影响规律。相同泄漏位置条件下，泄漏初期漏点附近管道瓦斯浓度、负压等迅速降低，管道气体流量增大，随后达到稳定状态；随着漏点孔径增大，管道泄漏气体流动影响区域增大。相同漏点孔径下，主管道泄漏时，漏点到抽采泵之间管道气体流动影响范围及程度较大，流量变化率为8.95%；支管泄漏时，漏点到抽采泵以及漏点到抽采孔之间管道气体流动影响范围及程度均较大，流量变化率分别为8.33%以及8.67%。

建立了瓦斯抽采管道泄漏定位最优模型判识准则，构建了基于集成学习的瓦斯抽采管道泄漏定位模型。运用最小二乘支持向量机（LSSVM）、Elman神经网络和深度信念网络（DBN）等3种经典有监督机器学习算法作为基学习器，得到LSSVM、Elman、DBN、Stacking-LSSVM-Elman、Stacking-LSSVM-DBN、Stacking-Elman-DBN及Stacking -LSSVM-Elman-DBN等7种瓦斯抽采管道漏点定位算法，构建了压力、流量以及压力-流量协同等3种定位参数组合，得到21种瓦斯抽采管道漏点定位模型；采用判定系数≥0.80、五折交叉验证平均均方根误差≤0.12且平均绝对百分比误差≤0.20对21种定位模型进行初选，得到9种瓦斯抽采管道漏点定位初选模型；应用希尔不等系数≤0.1、五折交叉验证每折均方根误差均≤0.12且平均绝对百分比误差均≤0.20对9种初选定位模型进行优选，得到Stacking -LSSVM-Elman-DBN模型为最佳瓦斯抽采管道漏点定位模型。

设计开发了矿井瓦斯抽采管道泄漏判识平台，包含登录模块、数据库模块、数据处理模块以及泄漏定位模块，实现了瓦斯抽采管道泄漏定位过程及结果可视化。通过陕西黄陵二号煤矿213工作面胶带巷瓦斯抽采管道监测数据，得到该管道泄漏点位置位于距抽采口2026.65 m-2033.8 m，与井下实际情况较为吻合。

本文通过分析不同泄漏条件下瓦斯抽采管道气体流动各参数变化规律，得到了基于集成学习的管道泄漏定位模型，为提高管道泄漏定位精度，提升瓦斯抽采管道运行安全性及效率提供了一定理论基础和技术支持。

The gas disaster in China's coal mines is serious, while gas resources are abundant, and gas extraction can effectively prevent and control gas disasters and utilize gas resources. The pipeline is an effective carrier for gas extraction. Due to the complex underground conditions and aging of the pipeline, it is inevitable that the gas extraction pipeline is subject to rupture and leakage, which reduces the efficiency of gas extraction. To further clarify the gas flow law during gas extraction pipeline leakage and improve the diagnosis efficiency of gas extraction pipeline leakage accidents, a combination of theoretical analysis, numerical simulation, physical experiments, machine learning, and field validation are adopted in this paper. The influencing factors of the gas flow characteristics in the gas extraction pipeline are analyzed, the flow law of the leaking gas in the extraction pipeline under different influencing factors is studied, a leak identification model based on integrated learning is established, a leak detection platform for gas extraction pipeline is developed.

A gas flow model of gas extraction pipeline leakage is established based on fluid dynamics and other theories, and the main forms of gas extraction pipeline leakage and the influencing factors are analyzed. Comsol Multiphysics numerical simulation software is used to study the gas flow characteristics of gas extraction pipeline leaks and to obtain the correlation between gas volume fraction, flow rate and negative pressure of pipeline and leak point aperture, pipe diameter, outlet negative pressure and inlet flow rate under steady-state conditions of pipeline leaks. By analyzing the change of gas volume fraction and flow velocity under different leakage times, the gas volume fraction is negatively correlated with the leak point hole diameter, positively exponentially correlated with the pipe diameter, and negatively exponentially functioned with the negative outlet pressure and the inlet flow velocity. The gas flow rate is a positive exponential function of the leak point hole diameter, negatively related to the pipe diameter, and positively related to the negative outlet pressure and the inlet flow rate.

The influence law of different leakage point diameter and leakage location on the gas flow in the pipeline is studied through independent research and development of mine gas extraction pipeline leakage gas flow simulation experiment system. Under the same leak location conditions, the gas concentration and negative pressure of the pipeline near the leak point decrease rapidly at the beginning of the leak, and the gas flow of the pipeline increases, and then reaches a stable state. As the aperture of the leak hole increases, the area affected by the flow of gas from the pipe leak increases. Under the same leak point hole diameter, the scope and degree of influence of gas flow in the pipeline between the leak point and the extraction pump is large when the main line is leaking, and the rate of change of flow is 8.95%. When the branch pipe leaks, the range and degree of influence of gas flow in the pipe between the leak point and the extraction pump and between the leak point and the extraction hole are large, and the rate of change of flow is 8.33% and 8.67% respectively.

The optimal model discrimination criterion for pipeline leakage location is constructed, and an integrated learning-based extraction pipeline leakage location model is obtained. Three classical supervised machine learning algorithms such as Least Squares Support Vector Machine (LSSVM), Elman neural network and Deep Belief Network (DBN) are used as base learners to obtain seven gas extraction pipeline leak location algorithms such as LSSVM, Elman, DBN, Stacking-LSSVM-Elman, Stacking-LSSVM-DBN, Stacking-Elman-DBN and Stacking -LSSVM-Elman-DBN. Three combinations of locating parameters, such as pressure, flow rate and pressure-flow cooperative, are constructed to obtain 21 types of leak locating models for gas extraction pipelines. The 21 localization models are evaluated by using the coefficient of determination ≥0.80, the average root mean square error ≤0.12 and the average absolute percentage error ≤0.20, and 9 primary models for locating gas extraction pipeline leakage points are obtained. The Hill's inequality coefficient ≤0.1, the root mean square error per fold ≤0.12 and the mean absolute percentage error ≤0.20 are applied to optimize the nine primary locating models, and the Stacking -LSSVM-Elman-DBN model is obtained to be the best gas extraction pipeline leak locating model.

The platform is designed and developed to identify the leakage of gas extraction pipes in mines, including the login module, database module, data processing module and leakage location module, which visualizes the process and results of locating the leakage of gas extraction pipes. Through the monitoring data of the gas extraction pipeline in the tape lane of 213 working face of Shaanxi Huangling No. 2 coal mine, the location of the leakage point of this pipeline is located at 2026.65 m-2033.8 m from the extraction port, which matches with the actual situation of the underground.

This paper analyzes the variation law of each parameter in the pipeline under different leakage conditions and obtains a pipeline leakage localization model based on integrated learning, which provides a certain theoretical basis and technical support to improve the accuracy of pipeline leakage localization and enhance the safety and efficiency of gas extraction pipeline operation.

[1] 国家统计局. 中华人民共和国2022年国民经济和社会发展统计公报[R]. 北京:国家统计局, 2023.

[2] 潘继平. 中国非常规天然气开发现状与前景及政策建议[J]. 国际石油经济, 2019, 27(2): 51-59.

[3] 李树刚, 张静非, 尚建选, 等. 双碳目标下煤气同采技术体系构想及内涵[J]. 煤炭学报, 2022, 47(4): 1416-1429.

[4] 黄中伟, 李国富, 杨睿月, 等. 我国煤层气开发技术现状与发展趋势[J]. 煤炭学报, 2022, 47(9): 3212-3238.

[5] Fan J, Wang J, Liu M, et al. Scenario simulations of China's natural gas consumption under the dual-carbon target[J]. Energy, 2022, 252: 124106.

[6] 林海飞, 周捷, 高帆, 等. 基于特征选择和机器学习融合的煤层瓦斯含量预测[J]. 煤炭科学技术, 2021, 49(5): 44-51.

[7] 林海飞, 刘时豪, 周捷, 等. 基于STL-EEMD-GA-SVR的采煤工作面瓦斯涌出量预测方法及应用[J]. 煤田地质与勘探, 2022, 50(12): 131-141.

[8] 祝钊, 贾振元, 王魁军. 煤矿阻爆快速蝶阀系统静力学设计及其动态特性仿真分析[J]. 煤炭学报, 2013, 38(1): 161-166.

[9] 王国法, 杜毅博. 煤矿智能化标准体系框架与建设思路[J]. 煤炭科学技术, 2020, 48(1): 1-9.

[10] 刘见中, 孙海涛, 雷毅, 等. 煤矿区煤层气开发利用新技术现状及发展趋势[J]. 煤炭学报, 2020, 45(1): 258-267.

[11] 王杰峰, 吕伟, 张帅, 等. 煤矿瓦斯抽采管道泄漏监测预警技术发展现状与展望[J]. 矿业装备, 2020, 1(6): 42-43.

[12] 佘小广, 周厚权, 杨利平. 煤矿井下瓦斯抽采管网泄漏检测技术[J]. 煤矿安全, 2013, 44(10): 75-77.

[13] 司春风, 袁树杰. 煤矿井下瓦斯抽采PVC管道爆炸原因分析及预防[J]. 安徽理工大学学报: 自然科学版, 2011, 31(3): 48-51.

[14] 李润之, 司荣军, 张延松, 等. 输送管道内低浓度瓦斯爆炸传播实验研究[J]. 山东科技大学学报：自然科学版, 2009, 28(1): 35-39.

[15] 金晶. 基于SVM的煤矿瓦斯抽采系统火灾隐患判识研究[D]. 淮南: 安徽理工大学, 2014.

[16] 李松涛, 孙玉宁, 王永龙, 等. 基于Hoke-Brown准则的瓦斯抽采钻孔稳定性分析及封孔技术[J]. 安全与环境学报, 2016, 16(3): 135-139.

[17] 许江, 宋肖徵, 彭守建, 等. 顺层钻孔布置间距对煤层瓦斯抽采效果影响的物理模拟试验研究[J]. 岩土力学, 2019, 40(12): 4581-4589.

[18] 王志亮, 朱锴. 瓦斯抽采管路摩擦阻力计算方法及应用[J]. 煤矿安全, 2014, 45(4): 132-137.

[19] 马志远. 瓦斯抽放系统管路摩擦阻力计算公式的探讨[J]. 矿业安全与环保, 2008, 35(5): 73-83.

[20] 李国雄, 孙德宁, 王洪存, 等. 瓦斯抽放管路系统的设计及其设备的配套选型[J]. 工矿自动化, 2012, 38(2): 78-81.

[21] Yu Q, Hou L, Li Y, et al. Numerical study on harmful boundary of above-ground section leakage of natural gas pipeline[J]. Journal of Loss Prevention in the Process Industries, 2022, 80: 104901.

[22] 黄雪驰, 马贵阳, 杨奇睿, 等. 天然气管道非稳态泄漏扩散的数值模拟[J]. 安全与环境学报, 2017, 17(1): 183-188.

[23] 姚雪蕾, 袁成清, 付宜风, 等. 管道内壁粗糙度对沿程阻力影响的FLUENT数值模拟分析[J]. 船海工程, 2015, 44(6): 101-110.

[24] 周志军, 林震, 周俊虎, 等. 不同湍流模型在管道流动阻力计算中的应用和比较[J]. 热力发电, 2007, 36(1): 18-23.

[25] 张涛, 朱晓军, 彭飞, 等. 近壁面处理对湍流数值计算的影响分析[J]. 海军工程大学学报, 2013, 25(6): 104-108.

[26] 邵杰, 李晓花, 郭振江, 等. k-ω湍流模型在流动阻力数值模拟中的应用研究[J]. 青岛大学学报：工程技术版, 2016, 31(1): 120-124.

[27] 付建民, 赵洪祥, 陈国明, 等. 裂口几何形态对输气管道小孔泄漏的影响[J]. 天然气工业, 2014, 34(11): 128-133.

[28] 于菲菲, 王世杰, 陈先锋, 等. 受限空间漏点孔径对气体扩散影响的模拟研究[J]. 安全与环境学报, 2015, 15(4): 159-162.

[29] 蔡继涛, 张志晶, 王杰峰, 等. 基于CFX的煤矿瓦斯抽采主系统管道泄漏数值模拟[J]. 矿业科学学报, 2021, 6(3): 342-347.

[30] Cai J, Wu J, Yuan S, et al. Numerical analysis of multi-factors effects on the leakage and gas diffusion of gas drainage pipeline in underground coal mines[J]. Process Safety and Environmental Protection, 2021, 151: 166-181.

[31] 刘中良, 罗志云, 王皆腾, 等. 天然气管道泄漏速率的确定[J]. 化工学报, 2008, 59(8): 2121-2126.

[32] 董刚, 唐维维, 杜春, 等. 高压管道天然气泄漏扩散过程的数值模拟[J]. 中国安全生产科学技术, 2009, 5(6): 11-15.

[33] Cassa A M, Zyl J, Laubscher R F. A numerical investigation into the effect of pressure on holes and cracks in water supply pipes[J]. Urban water journal, 2010, 7(2): 109-120.

[34] Chen Q, Xing X, Jin C, et al. A novel method for transient leakage flow rate calculation of gas transmission pipelines[J]. Journal of Natural Gas Science and Engineering, 2020, 77: 103261.

[35] Fu H, Ling K, Pu H. Identifying two-point leakages in parallel pipelines based on flow parameter analysis[J]. Journal of Pipeline Science and Engineering, 2022, 2(2): 100052.

[36] Zhang J, Lian Z, Zhou Z, et al. Acoustic method of high-pressure natural gas pipelines leakage detection: Numerical and applications[J]. International Journal of Pressure Vessels and Piping, 2021, 194: 104540.

[37] 赵洪祥, 付建民, 陈国明, 等. 气相管道小孔泄漏压力响应试验与仿真研究[J]. 安全与环境学报, 2014, 14(1): 47-50.

[38] 李兵, 王浩全, 鹿国培, 等. 压力气体管道漏点孔径当量估算方法研究[J]. 电子测量技术, 2021, 44(14): 135-141.

[39] 宋琪. 复杂管网泄漏诊断及基于神经网络的定位研究[D]. 吉林: 东北电力大学, 2022.

[40] Zyl J , Clayton C . The effect of pressure on leakage in water distribution systems[J]. Proceedings of the ICE - Water Management, 2007, 160(2):109-114.

[41] Zhu JL, Pan J, Zhang YX, et al. Leakage and diffusion behavior of a buried pipeline of hydrogen-blended natural gas[J]. International Journal of Hydrogen Energy, 2022, 48(30): 11592-11610.

[42] 曹宝生, 玉建军, 虞湘菲, 等. 基于相似准则的燃气中压管网水力工况实验研究[J]. 天津城建大学学报, 2018, 24(5): 351-354.

[43] Li XJ, Xue Y, Du HM, et al. Investigation on leakage detection and localization in gas-liquid stratified flow pipelines based on acoustic method[J]. Journal of Pipeline Science and Engineering, 2022, 2(4): 100089.

[44] 于晓龙. 室内天然气管道泄漏实验和数值模拟研究[D]. 哈尔滨: 哈尔滨工业大学, 2019.

[45] Fu H, Wang S, Ling KG. Detection of two-point leakages in a pipeline based on lab investigation and numerical simulation[J]. Journal of Petroleum Science and Engineering, 2021, 204: 108747.

[46] 方丽萍, 梁金禄, 莫昌县, 等. 多点泄漏对天然气管道沿线压力的影响研究[J]. 中国安全生产科学技术, 2020, 16(2): 104-109.

[47] 韩宝坤, 闫成稳, 鲍怀谦, 等. 输气管道泄漏流场特性分析[J]. 山东科技大学学报（自然科学版）, 2017, 36(6): 32-38.

[48] 李凤, 王文和, 游赟, 等. 天然气管道泄漏的声-压耦合识别方法[J]. 应用声学, 2020, 39(3): 402-408.

[49] Li F, Zhang LB, Dong SH, et al. Noise-Pressure interaction model for gas pipeline leakage detection and location[J]. Measurement, 2021, 184: 109906.

[50] Zhou J, Lin HF, Li SG, et al. Leakage diagnosis and localization of the gas extraction pipeline based on SA-PSO BP neural network[J]. Reliability Engineering & System Safety, 2023, 232: 109051.

[51] Lu HF, Iseley T, Behbahani S, et al. Leakage detection techniques for oil and gas pipelines: State-of-the-art[J]. Tunnelling and Underground Space Technology, 2020, 98: 103249.

[52] 吴同, 邓忠华, 沈亮, 等. 长距离输油管道泄漏监测技术研究进展及评价体系建立[J/OL]. 油气储运: 1-22[2023-03-21].

[53] 杨荣根. 长输石油管道泄漏检测与定位技术研究[D]. 南京: 南京理工大学, 2011.

[54] 贾莹. 基于智能算法的油田天然气管道泄漏检测研究[J]. 大庆: 东北石油大学, 2014,

[55] 方丽萍, 李玉星, 刘翠伟, 等. 气液管道泄漏检测及信号处理技术[J]. 电子测量与仪器学报, 2018, 32(11): 26-34.

[56] 蔡晓龙, 刘永军, 董晓琪. 油气管道泄漏检测技术的选择和应用[J]. 石油天然气学报, 2021, 43(2): 120-125.

[57] Chalgham W, Wu KY, Mosleh A. System-level prognosis and health monitoring modeling framework and software implementation for gas pipeline system integrity management[J]. Journal of Natural Gas Science and Engineering, 2020, 84: 103671.

[58] 袁满, 高宏宇, 路敬祎, 等. 油气管道泄漏检测技术综述[J]. 吉林大学学报(信息科学版), 2022, 40(2): 159-173.

[59] 韩玲娟, 王强, 杨其华, 等. 基于分布式光纤传感的水下输气管道泄漏检测与定位分析[J]. 传感技术学报, 2015, 28(7): 1097-1102.

[60] 曾周末, 安靳, 冯封. 基于相干瑞利散射的管道安全光纤预警系统[J]. 天津大学学报：自然科学与工程技术版, 2015, 48(1): 70-75.

[61] 刘翠伟, 李雪洁, 李玉星, 等. 基于音波法的输气管道泄漏检测与定位[J]. 化工学报, 2014, 65(11): 4633-4642.

[62] Ning FL, Cheng ZH, Meng D, et al. A framework combining acoustic features extraction method and random forest algorithm for gas pipeline leak detection and classification[J]. Applied Acoustics, 2021, 182: 108255.

[63] Meng LY, Li YX, Wang WC, et al. Experimental study on leak detection and location for gas pipeline based on acoustic method[J]. Journal of Loss Prevention in the Process Industries, 2012, 25(1): 90-102.

[64] Banjara N K, Sasmal S, Voggu S. Machine learning supported acoustic emission technique for leakage detection in pipelines[J]. International Journal of Pressure Vessels and Piping, 2020, 188: 104243.

[65] 刘占宇. 矿井瓦斯抽采管网运行优化方法研究[D]. 北京: 中国矿业大学（北京）, 2016.

[66] Flohr A, Matter JM, James RH, et al. Utility of natural and artificial geochemical tracers for leakage monitoring and quantification during an offshore controlled CO2 release experiment[J]. International Journal of Greenhouse Gas Control, 2021, 111: 103421.

[67] Li M, Liu B, Chen TT, et al. On-site leakage locating of underground natural gas pipeline based on Ne tracer by miniature time-of-flight mass spectrometry[J]. Talanta, 2023, 254: 124170.

[68] 高相铭, 李研达, 杨世凤, 等. 基于物联网的燃气管网泄漏检测系统研究[J]. 仪表技术与传感器, 2016, 407(12): 110-114.

[69] 周琰, 靳世久, 张昀超, 等. 分布式光纤管道泄漏检测和定位技术[J]. 石油学报, 2006, 27(2): 121-124.

[70] Qiang F, Wan HJ, Qiu FP. Pipeline leak detection based on fiber optic early-warning system[J]. Procedia Engineering, 2010, 7(1): 88-93.

[71] 陈朋超, 蔡永军, 李俊, 等. 基于改进型马赫-曾德干涉仪原理的管道安全预警系统研究[J]. 传感技术学报, 2009, 22(11): 1611-1664.

[72] 王宇, 吴瑞东, 董齐, 等. 用于燃气管道破坏预警的Φ-OTDR技术[J]. 煤炭技术, 2016, 35(2): 225-227.

[73] Peng F, Wu H, Jia XH, et al. Ultra-long high-sensitivity Φ-OTDR for high spatial resolution intrusion detection of pipelines[J]. Optics Express, 2014, 22(11): 13804-13810.

[74] 卞庞, 吴媛, 贾波, 等. 基于改进型sagnac干涉仪的扰动定位系统[J]. 仪器仪表学报, 2012, 33(12): 2870-2874.

[75] Zhao F, Zhang SF, Zhao HZ, et al. An intelligent optical fiber-based prewarning system for oil and gas pipelines[J]. Optical Fiber Technology, 2022, 71: 102953.

[76] 孙宇, 李文琦, 周俊杰, 等. 新型光纤传感器在管道渗漏监测中的应用研究[J]. 测控技术, 42(1): 35-39.

[77] 袁文强, 郎宪明, 曹江涛, 等. 基于声波法的管道泄漏检测技术研究进展[J]. 油气储运, 2023, 42(2): 141-151.

[78] 李帅永, 夏传强, 杨丽丽. 不同方向的气体管道泄漏声发射信号模态特性分析[J]. 仪器仪表学报, 2018, 39(5): 195-204.

[79] 纪健, 傅晓宁, 纪杰, 等. 多相流管道声波泄漏检测技术[J]. 油气储运, 2020, 39(12): 1408-1415.

[80] Muggleton JM, Brennan MJ. The design and instrumentation of an experimental rig to investigate acoustic methods for the detection and location of underground piping systems[J]. Applied Acoustics, 2008, 69(11): 1101-1107.

[81] Kim MS, Lee SK. Detection of leak acoustic signal in buried gas pipe based on the time–frequency analysis[J]. Journal of Loss Prevention in the Process Industries, 2009, 22(6): 990-994.

[82] 潘碧霞, 徐长航, 曹国梁, 等. 管道泄漏声发射信号的传播特性[J]. 油气储运, 2013, 32(10): 1141-1145.

[83] 刘延保. 煤矿瓦斯负压抽采管网检漏技术及现场应用[J]. 中国矿业, 2016, 25(5): 156-159.

[84] 郭寿松. 一种基于超声波检测的瓦斯抽采管道检漏技术[J]. 矿业安全与环保, 2014, 41(3): 88-91.

[85] 刘翠伟, 李玉星, 王武昌, 等. 输气管道声波法泄漏检测技术的理论与实验研究[J]. 声学学报, 2013, 38(3): 372-381.

[86] 韩宝坤, 蒋相广, 刘西洋, 等. 基于声波法的天然气管道泄漏检测与定位系统研究[J]. 山东科技大学学报:自然科学版, 2018, 37(4): 102-110.

[87] Wang WM, Mao XX, Liang HG, et al. Experimental research on in-pipe leaks detection of acoustic signature in gas pipelines based on the artificial neural network[J]. Measurement, 2021, 183: 109875.

[88] 王建夫, 张志胜, 安国印, 等. 气体示踪技术在盐穴地下储气库微泄漏监测中的应用[J]. 天然气工业, 2021, 41(12): 156-164.

[89] Stalker L, Boreham C, Underschultz J, et al. Geochemical monitoring at the CO2CRC Otway Project: Tracer injection and reservoir fluid acquisition[J]. Energy Procedia, 2009, 1(1): 2119-2125.

[90] 张二勇. 澳大利亚Otway盆地二氧化碳地质封存示范工程[J]. 水文地质工程地质, 2012, 39(2): 131-137.

[91] 金显杭, 方佳伟, 王永胜, 等. 咸水层CO2地质封存泄漏监测的示踪剂优选[J]. 天然气化工（C1化学与化工）, 2020, 45(5): 72-76.

[92] 刘振华. 示踪气体在工作面漏风通道和漏风量测定的应用[J]. 煤矿现代化, 2021, 30(3): 145-150.

[93] 张伟龙. 潞宁煤业31102工作面示踪气体测漏风技术研究[J]. 煤, 2019, 28(9): 92-95.

[94] 孙珍平. 基于示踪气体技术的特厚煤层综放工作面漏风通道试验研究[J]. 煤矿安全, 2019, 50(11): 14-17.

[95] 税爱社, 周绍骑, 李生林, 等. 输油管线泄漏诊断的SCADA系统实现[J]. 仪器仪表学报, 2001, S2: 229-230.

[96] 裴为华. 瓦斯抽采主管道泄漏监测与漏点定位系统实验研究[D]. 徐州: 中国矿业大学, 2015.

[97] 刘恩斌, 彭善碧, 李长俊. 现代管道泄漏检测技术探讨[J]. 管道技术与设备, 2004, 5(1): 17-19.

[98] 张弢甲, 富宽, 刘胜楠, 等. 基于流量平衡法的泄漏识别改进算法[J]. 管道技术与设备, 2017, 4(1): 19-22.

[99] 王晓丹. 天然气管线动态模型压力分布泄漏检测技术研究[D]. 西安: 西安石油大学, 2016.

[100]崔谦, 靳世久, 王立坤. 多尺度相关分析在管道泄漏检测中的应用[J]. 电子测量与仪器学报, 2005, 19(5): 50-53.

[101]Liu CW, Wang YZ, Li YX, et al. Experimental study on new leak location methods for natural gas pipelines based on dynamic pressure waves[J]. Journal of Natural Gas Science and Engineering, 2018, 54(1): 83-91.

[102]Isermann R. Process fault detection based on modeling and estimation methods—A survey[J]. Automatica, 1984, 20(4): 387-404.

[103]邓勇, 曹敏, 赖治屹. 基于深度学习的天然气管道气体压力超声检测模式识别方法[J]. 电子测量与仪器学报, 2021, 35(10): 176-183.

[104]唐恂, 张琳, 苏欣, 等. 长输管道泄漏检测技术发展现状[J]. 油气储运, 2007, 26(7): 11-14.

[105]王洪超, 李强, 罗毅, 等. 基于相似度的管道泄漏负压波定位算法[J]. 油气储运, 2021, 40(6): 679-684.

[106]孙良, 王建林, 赵利强. 负压波法在液体管道上的可检测泄漏率分析[J]. 石油学报, 2010, 31(4): 654-658.

[107]Li J, Zheng Q, Qian ZH, et al. A novel location algorithm for pipeline leakage based on the attenuation of negative pressure wave[J]. Process Safety and Environmental Protection, 2019, 123: 309-316.

[108]Capponi C, Meniconi S, Lee PJ, et al. Time-domain Analysis of Laboratory Experiments on the Transient Pressure Damping in a Leaky Polymeric Pipe[J]. Water Resources Management, 2020, 34(8): 501-514.

[109]秦程, 任亮, 王嘉健, 等. 基于LabVIEW的管道泄漏监测与定位系统[J]. 电子测量技术, 2021, 44(13): 23-30.

[110]da Silva H V, Morooka C K, Guilherme I R, et al. Leak detection in petroleum pipelines using a fuzzy system[J]. Journal of Petroleum Science and Engineering, 2005, 49(3): 223-238.

[111]Olijnyk A, Shtayer L. Modelling of the pressure distribution in the pipeline having leakages using d'Alembert formula[J]. Transactions of Kremenchuk Mykhailo Ostrohradskyi National University, 2013, 78(2): 66-71.

[112]蒋蓉. 基于模型法的天然气管道泄漏检测及定位研究[D]. 北京: 北京理工大学, 2015.

[113]赵亚, 王强, 翟永军, 等. 基于小波包能量谱的分布式光纤燃气管道泄漏监测及实验分析[J]. 应用光学, 2018, 39(2): 295-300.

[114]Kim K, Park S. Study on the applicability of the principal component analysis for detecting leaks in water pipe networks[J]. Journal of The Korean Society of Water and Wastewater, 2019, 33(2): 159-167.

[115]郎宪明, 李平, 曹江涛, 等. 长输油气管道泄漏检测与定位技术研究进展[J]. 控制工程, 2018, 25(4): 621-629.

[116]张逸斌, 张浪, 张慧杰, 等. 基于瞬态模型的井下抽采主管道泄漏定位方法研究[J]. 工矿自动化, 2021, 47(1): 55-60.

[117]郝永梅, 杜璋昊, 杨文斌, 等. 基于改进ELMD和多尺度熵的管道泄漏信号识别[J]. 中国安全科学学报, 2019, 29(8): 105-111.

[118]Sun JD, Xiao QY, Wen JT, et al. Natural gas pipeline leak aperture identification and location based on local mean decomposition analysis[J]. Measurement, 2016, 79(1): 147-157.

[119]张来斌, 王朝晖, 陈茜. 输油管道故障诊断中的实时模型法[J]. 油气储运, 2003, 9(1): 52-55.

[120]Syed MM, Lemma TA, Vandrangi SK, et al. Recent developments in model-based fault detection and diagnostics of gas pipelines under transient conditions[J]. Journal of Natural Gas Science and Engineering, 2020, 83: 103550.

[121]Fu H, Ling KG, Pu H. Identifying two-point leakages in parallel pipelines based on flow parameter analysis[J]. Journal of Pipeline Science and Engineering, 2022, 2(2): 100052.

[122]王朝晖, 李文苓. 管道泄漏检测中实时模型法的研究[J]. 石油机械, 2005, 33(4): 41-43.

[123]张红兵, 李长俊, 彭善碧. 输气管道故障诊断中的实时模型法[J]. 天然气工业, 2005, 25(10): 127-129.

[124]孙良, 王建林. 基于稳态模型的气体管道泄漏定位方法的研究[J]. 仪器仪表学报, 2010, 31(3): 565-570.

[125]Colombo AF, Lee P, Karney BW. A selective literature review of transient-based leak detection methods[J]. Journal of Hydro-environment Research, 2009, 2(4): 212-227.

[126]Diao X, Jiang J, Lei N, et al. Leak detection and location in liquid pipelines by analyzing the first transient pressure wave with unsteady friction[J]. Journal of Loss Prevention in the Process Industries, 2019, 60(1): 303-310.

[127]Meniconi S, Brunone B, Ferrante M, et al. Transient tests for locating and sizing illegal branches in pipe systems[J]. Journal of Hydroinformatics, 2011, 13(3): 334-345.

[128]阳子轩. 复杂管道泄漏检测技术研究[D]. 武汉: 武汉理工大学, 2011.

[129]许凌云, 朱月敏, 宋建英, 等. 基于Kalman滤波器的管道泄漏检测自动控制的研究[J]. 自动化与仪器仪表, 2019, 12(1): 91-94.

[130]Torres L, Verde C, Vazquez-Hernandez O. Parameter identification of marine risers using Kalman-like observers[J]. Ocean Engineering, 2015, 93(1): 84-97.

[131]Delgado-Aguinaga JA, Besancon G, Begovich O, et al. Multi-leak diagnosis in pipelines based on Extended Kalman Filter[J]. Control Engineering Practice, 2016, 49(4): 139-148.

[132]刘恩斌, 彭善碧, 李长俊, 等. 基于瞬态模型的油气管道泄漏检测[J]. 天然气工业, 2005, 25(6): 102-104.

[133]陈传胜, 李俊, 吴瑶晗, 等. 实时瞬态模型法在长输天然气管道泄漏检测中的应用[J]. 天然气技术与经济, 2019, 13(3): 58-62.

[134]刘明亮. 基于SCADA系统的天然气管道瞬态仿真及负荷预测[D]. 天津: 天津大学, 2008.

[135]郭新蕾, 马慧敏, 王涛, 等. 管网故障水力瞬变检测实验系统研发[J]. 水利学报, 2019, 50(3): 305-314.

[136]Liang X, Liang W, Xiong J. Intelligent diagnosis of natural gas pipeline defects using improved flower pollination algorithm and artificial neural network[J]. Journal of Cleaner Production, 2020, 264(10): 121655.

[137]Selvaggio A Z, Sousa F MM, Silva FV d, et al. Application of long short-term memory recurrent neural networks for localisation of leak source using 3D computational fluid dynamics[J]. Process Safety and Environmental Protection, 2022, 159(3): 757-767.

[138]刘炜, 刘宏昭. 检测与定位管道泄漏的图像处理方法研究[J]. 控制工程, 2014, 21(2): 294-297.

[139]王云飞, 梁伟, 张来斌. 多层融合的管道泄漏诊断技术研究[J]. 中国安全科学学报, 2013, 23(8): 171-176.

[140]陈斌, 万江文, 吴银锋, 等. 神经网络和证据理论融合的管道泄漏诊断方法[J]. 北京邮电大学学报, 2009, 32(1): 5-9.

[141]Rahmati M. Modeling of gas pipeline in order to implement a leakage detection system using artificial neural networks based on instrumentation[J]. International Journal of Numerical Modelling: Electronic Networks, Devices and Fields, 2019, 32(2): e2520.

[142]Miao X, Zhao H, Xiang Z. Leakage detection in natural gas pipeline based on unsupervised learning and stress perception[J]. Process Safety and Environmental Protection, 2023, 170(2): 76-88.

[143]Tian X, Jiao W, Liu T, et al. Leakage detection of low-pressure gas distribution pipeline system based on linear fitting and extreme learning machine[J]. International Journal of Pressure Vessels and Piping, 2021, 194(2): 104553.

[144]Chuang W Y, Tsai Y L, Wang L H. Leak Detection in Water Distribution Pipes Based on CNN with Mel Frequency Cepstral Coefficients[C]. 2018 Second International Conference on Intelligent Computing and Control Systems.

[145]王新颖, 杨泰旺, 宋兴帅, 等. 城市燃气管道泄漏诊断方法[J]. 消防科学与技术, 2018, 37(6): 834-838.

[146]马广兴, 曲波, 常琛, 等. 基于CNN的供热管道泄漏识别方法研究[J]. 电子测量技术, 2022, 45(16): 34-41.

[147]Zuo ZL, Ma L, Liang S, et al. A semi-supervised leakage detection method driven by multivariate time series for natural gas gathering pipeline[J]. Process Safety and Environmental Protection, 2022, 164(8): 468-478.

[148]高琳, 曹建国. 管道泄漏检测方法研究综述[J]. 现代制造工程, 2022, 2(1): 154-162.

[149]Qu ZG, Feng H, Zeng ZM, et al. A SVM-based pipeline leakage detection and pre-warning system[J]. Measurement, 2010, 43(4): 513-519.

[150]Butterfield J D, Meruane V, Collins R P, et al. Prediction of leak flow rate in plastic water distribution pipes using vibro-acoustic measurements[J]. Structural Health Monitoring, 2018, 17(4): 959-970.

[151]文玉梅, 张雪园, 文静, 等. 依据声信号频率分布和复杂度的供水管道泄漏辨识[J]. 仪器仪表学报, 2014, 35(6): 1223-1229.

[152]Xiao R, Hu Q, Li J. Leak detection of gas pipelines using acoustic signals based on wavelet transform and Support Vector Machine[J]. Measurement, 2019, 146(11): 479-489.

[153]刘浩宇. 基于超声波波速和支持向量机的管道泄漏检测[D]. 抚顺: 辽宁石油化工大学, 2019.

[154]Sim HY, Ramli R, Saifizul A, et al. Detection and estimation of valve leakage losses in reciprocating compressor using acoustic emission technique[J]. Measurement, 152(2): 107315.

[155]肖启阳, 李健, 孙洁娣, 等. 基于EWT及模糊相关分类器的管道微小泄漏检测[J]. 振动与冲击, 2018, 37(14): 122-129.

[156]Liu CW, Wang YZ, Li XH, et al. Quantitative assessment of leakage orifices within gas pipelines using a Bayesian network[J]. Reliability Engineering & System Safety, 2021, 209(3): 107438.

[157]李卫龙, 汪青, 刘欣, 等. 煤矿瓦斯抽采智能系统设计[J]. 煤矿机械, 2021, 42(8): 14-17.

[158]Li X, Zhao T, Sun QH, et al. Frequency response function method for dynamic gas flow modeling and its application in pipeline system leakage diagnosis[J]. Applied Energy, 2022, 324(10): 119720.

[159]张丽娜, 白珊. 基于元胞自动机数学模型的瓦斯抽采管道漏点定位研究[J]. 中国安全生产科学技术, 2019, 15(5): 99-104.

[160]焦志远, 王凯, 丁超南, 等. 基于元胞自动机的瓦斯抽采管网漏点精确定位研究[J]. 能源技术与管理, 2019, 44(3): 7-9.

[161]孙洁娣, 肖启阳, 温江涛, 等. 局域均值分解分析的管道漏点孔径识别及定位[J]. 仪器仪表学报, 2014, 35(12): 2835-2842.

[162]Zhu SB, Li ZL, Zhang SM, et al. Natural gas pipeline valve leakage rate estimation via factor and cluster analysis of acoustic emissions[J]. Measurement, 2018, 125(9): 48-55.

[163]徐鹏, 潘丹丹, 袁勋, 等. 燃气管道泄漏扩散研究进展[J]. 油气储运, 2022, 41(1): 21-28.

[164]顾帅威, 李玉星, 滕霖, 等. 小尺度超临界CO2管道小孔泄漏减压及温降特性[J]. 化工进展, 2019, 38(2): 805-812.

[165]胡杰, 隆清明, 李建功, 等. 顺煤层钻孔瓦斯抽采时空演化规律研究[J]. 煤炭科学技术, 2017, 45(2): 83-88.

[166]蔡正敏, 彭飞, 易发新, 等. 长输管道泄漏故障诊断方法的研究[J]. 应用力学学报, 2002, 2(1): 38-43.

[167]Yin X, Wen K, Huang WH, et al. A high-accuracy online transient simulation framework of natural gas pipeline network by integrating physics-based and data-driven methods[J]. Applied Energy, 2023, 333(1): 120615.

[168]侯庆民. 燃气长直管道泄漏检测及定位方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2014.

[169]张毅鹏. 管道瞬变流特性与泄漏检测数值模拟和试验研究[D]. 武汉: 武汉大学, 2018.

[170]谢海英. 圆断面90°弯管局部水头损失的数值模拟[J]. 水资源与水工程学报, 2014, 25(5): 190-192.

[171]Duarte C A R, de Souza F J, Venturi D N, et al. A numerical assessment of two geometries for reducing elbow erosion[J]. Particuology, 2020, 49(4): 117-133.

[172]范孟亮. 通风空调管道系统中渐缩、渐扩管段的减阻优化[D]. 西安: 西安建筑科技大学, 2020.

[173]陈佑乾, 崔旭阳, 杨迪, 等. 较大管径合流三通局部阻力系数模拟计算[J]. 煤气与热力, 2020, 40(4): 1-6.

[174]石保同, 张希斌, 黄文锋. 基于标准k-ε模型的平衡大气边界层研究[J]. 合肥工业大学学报（自然科学版）, 2019, 42(8): 1106-1113.

[175]Wang XM, Tan YF, Zhang TT, et al. Diffusion process simulation and ventilation strategy for small-hole natural gas leakage in utility tunnels[J]. Tunnelling and Underground Space Technology, 2020, 97(3): 103276.

[176]裴为华. 瓦斯抽采主管道泄漏监测与漏点定位系统实验研究[D]. 徐州: 中国矿业大学, 2014.

[177]周西华, 董强, 李昂, 等. 下沟矿瓦斯抽采系统仿真模拟及优化分析[J]. 辽宁工程技术大学学报（自然科学版）, 2017, 36(6): 561-565.

[178]娄振. 煤层抽采钻孔周边裂隙填充堵漏机理及试验研究[D]. 北京: 中国矿业大学（北京）, 2021.

[179]薛霄, 于湘凝, 周德雨, 等. 计算实验方法的溯源、现状与展望[J]. 自动化学报, 2023, 49(2): 246-271.

[180]陈雪锋. 天然气长输管道定量风险评价方法及其应用研究[D]. 北京: 北京科技大学, 2020.

[181]玉建军, 王帅, 郭敏, 等. 基于相似理论的燃气管网水力工况分析[J]. 中国安全生产科学技术, 2018, 14(7): 128-134.

[182]李全贵, 邓羿泽, 胡千庭, 等. 煤岩水力压裂物理实验研究的综述及展望[J]. 煤炭科学技术, 2022, 50(12): 62-72.

[183]Osiptsov A A. Fluid Mechanics of Hydraulic Fracturing: a Review[J]. Journal of Petroleum Science and Engineering, 2017, 156(7): 513-535.

[184]王旭冕, 黄廷林, 刘勇, 等. 管流变态模拟的相似理论研究[J]. 西安建筑科技大学学报（自然科学版）, 2006, 2(1): 294-296.

[185]彭亚, 蒋仲安. 矿井防尘供水管网相似试验模型构建与测点优化[J]. 煤炭科学技术, 2020, 48(1): 182-188.

[186]韩硕, 蒋仲安, 邓权龙. 矿井防尘供水管网水力特性的相似性研究[J]. 煤矿安全, 2017, 48(6): 40-43.

[187]袁亮, 薛阳, 王汉鹏, 等. 煤与瓦斯突出物理模拟试验研究新进展[J]. 隧道与地下工程灾害防治, 2020, 2(1): 1-10.

[188]苏屹, 李文宝壮, 雷家骕. 基于流体力学的知识流动沿程损失研究[J]. 科技管理研究, 2021, 41(5): 104-111.

[189]Lu WQ, Liang W, Zhang LB, et al. A novel noise reduction method applied in negative pressure wave for pipeline leakage localization[J]. Process Safety and Environmental Protection, 2016, 104(11): 142-149.

[190]He Y, Wang Y. Short-term wind power prediction based on EEMD–LASSO–QRNN model[J]. Applied Soft Computing, 2021, 105(7): 107288.

[191]Wang T, Zhang MC, Yu QH, et al. Comparing the applications of EMD and EEMD on time–frequency analysis of seismic signal[J]. Journal of Applied Geophysics, 2012, 83(8): 29-34.

[192]郑旭东. 基于EEMD-PCA模型的大坝变形数据消噪分析[D]. 桂林: 桂林理工大学, 2019.

[193]周怡娜, 路敬祎, 张勇, 等. VMD-SG-WT去噪法及其在混沌去噪中的应用[J]. 东北石油大学学报, 2020, 44(4): 113-120.

[194]杨杰, 陈捷, 洪荣晶, 等. 基于EEMD-多尺度主元分析的回转支承信号降噪方法研究[J]. 中南大学学报（自然科学版）, 2016, 47(4): 1173-1180.

[195]Guo XF, Gao Y, Zheng D, et al. Study on short-term photovoltaic power prediction model based on the Stacking ensemble learning[J]. Energy Reports, 2020, 6(9): 1424-1431.

[196]Hou H, Chen X, Li M, et al. Prediction of user outage under typhoon disaster based on multi-algorithm Stacking integration[J]. International Journal of Electrical Power & Energy Systems, 2021, 131(10): 107123.

[197]谭文侃, 胡南燕, 叶义成, 等. 基于四大集成学习的岩爆烈度分级预测[J]. 岩石力学与工程学报, 2022, 41(S2): 3250-3259.

[198]朱文广, 李映雪, 杨为群, 等. 基于K折交叉验证和Stacking融合的短期负荷预测[J]. 电力科学与技术学报, 2021, 36(1): 87-95.

[199]史佳琪, 张建华. 基于多模型融合Stacking集成学习方式的负荷预测方法[J]. 中国电机工程学报, 2019, 39(14): 4032-4042.

[200]Yan T, Shen SL, Zhou A, et al. Prediction of geological characteristics from shield operational parameters by integrating grid search and K-fold cross validation into stacking classification algorithm[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2022, 14(4): 1292-1303.

[201]刘德军, 戴庆庆, 左建平, 等. 基于Stacking集成算法的岩爆等级预测研究[J]. 岩石力学与工程学报, 2022, 41(S1): 2915-2926.

[202]Zhang YG, Li RX. Short term wind energy prediction model based on data decomposition and optimized LSSVM[J]. Sustainable Energy Technologies and Assessments, 2022, 52(8): 102025.

[203]葛磊蛟, 赵康, 孙永辉, 等. 基于孪生网络和长短时记忆网络结合的配电网短期负荷预测[J]. 电力系统自动化, 2021, 45(23): 41-50.

[204]姜静清. 最小二乘支持向量机算法及应用研究[D]. 长春: 吉林大学, 2007.

[205]向玲, 邓泽奇. 基于改进经验小波变换和最小二乘支持向量机的短期风速预测[J]. 太阳能学报, 2021, 42(2): 97-103.

[206]李锡杰, 师硕, 王旭. 基于Elman神经网络的肌电信号分类[J]. 微计算机信息, 2006, 23(1): 305-309.

[207]Li L, Xie XT, Gao T, et al. A modified conjugate gradient-based Elman neural network[J]. Cognitive Systems Research, 2021, 68(8): 62-72.

[208]包满. 基于Elman神经网络模型的短期电力负荷预测模型[J]. 电子设计工程, 2022, 30(1): 121-126.

[209]Guo Y, Wang H, Guo Y, et al. System operational reliability evaluation based on dynamic Bayesian network and XGBoost[J]. Reliability Engineering & System Safety, 2022, 225(11): 108622.

[210]刘建伟, 王园方, 罗雄麟. 深度记忆网络研究进展[J]. 计算机学报, 2021, 44(8): 1549-1589.

[211]刘展程, 王爽, 唐波. 基于布谷鸟搜索算法和DBN模型的变压器故障识别[J]. 电力科学与技术学报, 2022, 37(2): 3-11.

[212]Peng R, Lu ZD. Semiparametric Averaging of Nonlinear Marginal Logistic Regressions and Forecasting for Time Series Classification[J]. Econometrics and Statistics, 2021, 11:1-19.

[213]王旭坪, 于秀丽, 王天腾. 基于集成学习策略的化工园区大气污染影响预测[J]. 运筹与管理, 2021, 30(11): 127-134.

[214]游文霞, 李清清, 杨楠, 等. 基于多异学习器融合Stacking集成学习的窃电检测[J]. 电力系统自动化, 2022, 46(24): 178-186.

[215]高晓红, 李兴奇. 多元线性回归模型中无量纲化方法比较[J]. 统计与决策, 2022, 38(6): 5-9.

[216]Fu H, Yang L, Liang H, et al. Diagnosis of the single leakage in the fluid pipeline through experimental study and CFD simulation[J]. Journal of Petroleum Science and Engineering, 2020, 193(10): 107437.

[217]钱涛. 基于卷积神经网络的多作物叶片病害识别系统研究[D]. 合肥: 安徽农业大学, 2021.

[218]任丽垒. 基于PYQT的水压致裂地应力测量软件设计与实现[D]. 北京: 中国地质大学（北京）, 2021.

[219]练学辉. 一种基于Qt的被动雷达显控软件设计[J]. 雷达与对抗, 2014, 34(3): 61-64.

[220]王生龙, 景博, 焦晓璇, 等. 测试性设计策略优化与建模的可视化研究[J]. 电子测量与仪器学报, 2019, 33(12): 109-115.

[221]孙洁茹. 基于Qt的探测器寿命试验上位机系统设计与实现[D]. 合肥: 安徽大学, 2021.