助力矿山智能化建设与实现是顺应时代发展的要求，是科技发展的必然趋势。然而，作为“血液循环系统”的通风，是保证矿井安全生产的基础，因此，智能通风技术的研究和现场应用，是目前我国智慧矿山建设中的一个突出的研究热点，也是我国煤矿信息化和智能化建设的发展趋势。随着煤矿开采的继续，煤矿的通风网络结构也在发生改变。在矿山开采过程中，通风系统的各项参数处于持续变化、突变状态，必然会对其正常工作产生一定的影响，从而导致对安全生产不利和技术与经济上的不合理。因此，在隔一定的时间对矿井进行通风阻力测定，更新矿井通风阻力等参数，分析矿井通风现存问题，引入智能算法优化矿井风网解算模型，建立矿井三维可视化模型，以此来提升矿井通风系统的安全性、技术性和经济效益性。本文的研究内容主要如下：

（1）研究亭南煤业通风阻力测定和计算方法，分析矿井通风系统所存在的问题，经计算分析：测定结果满足精度要求，通风难易程度为容易，通风阻力分布合理。并以现场的实际测量以及计算结果为后续的风网解算优化提供数据支持，以及为所优化后的结果提供参考依据。

（2）对矿井通风理论、矿用风机的类型及特性以及智能优化算法理论进行了解以及分析，选用经典的Cross算法作为本文的风网解算方法。并选取了遗传算法和粒子群算法这两种典型的智能优化算法进行分析比较。从而为之后的风网解算、数学建模以及风网优化建立好理论基础。

（3）以矿井通风基本定律以及矿用风机特性曲线方程等作为约束条件，对矿井通风网络进行了数学建模。对遗传算法和粒子群算法分别进行了改进。并结合这两种算法的优点设计了基于遗传算法的粒子群算法（GA-PSO），通过三种算法的仿真结果分析验证了改进后的算法的有效性。研究表明，风网解算经本文所改进的算法优化后的风机功耗降低了16.86%，风量误差为4.85%。

（4）利用Unity3D三维建模软件与智能通风系统客户端平台工具，建立了与矿井实际相似程度高的亭南煤业三维可视化通风模型。通过风网解算优化后的数据与现场实际数据对比来验证了改进后算法的可行性，从而为建立可视化三维通风模型提供可靠数据。

       Assisting the intelligent construction and realization of mines is in line with the requirements of the times and the inevitable trend of scientific and technological development. However, as the ventilation of the "blood circulation system" is the basis for ensuring the safe production of mines, therefore, the research and field application of intelligent ventilation technology is a prominent research hotspot in the construction of China's intelligent mines and is also the development trend of China's coal mine informatization and intelligent construction. As coal mining continues, the ventilation network structure of coal mines is also changing. In the process of mining, the parameters of the ventilation system are in a state of continuous change and sudden change, which will inevitably have a certain impact on its normal work, which will lead to unfavorable production safety and technical and economic irrationality. Therefore, the ventilation resistance of the mine is measured at certain intervals, and parameters such as the ventilation resistance of the mine are updated to analyze the existing problems of mine ventilation.And the intelligent optimization algorithm is introduced to optimize the mine wind network solution, and then a three-dimensional visualization model is established, to improve the safety, technology, and economic efficiency of the mine ventilation system. The research content of this paper is mainly as follows:

(1) Measurement and calculation of ventilation resistance were carried out in Tingnan Coal Mine to analyze the problems existing in the mine ventilation system, and after calculation and analysis: the measurement results meet the requirements of accuracy, the degree of ventilation difficulty is easy, and the distribution of ventilation resistance is reasonable. The actual measurement and calculation results on site provide data support for the subsequent optimization of the wind network solution, and provide a reference basis for the optimized results.

(2) Understanding and analyzing the theory of mine ventilation, the types and characteristics of mine fans, and the theory of intelligent optimization algorithm, the classical Cross algorithm is used as the wind network solving method in this paper. And two typical intelligent optimization algorithms, the genetic algorithm and particle swarm algorithm, are selected for analysis and comparison. Thus, a good theoretical foundation is established for the subsequent wind network solving, mathematical modeling, and wind network optimization.

(3) The mine ventilation network was mathematically modeled using the basic laws of mine ventilation and the characteristic curve equations of m ine fans as constraints. The genetic algorithm and particle swarm algorithm are improved respectively. Combined with the advantages of these two algorithms, the particle swarm algorithm is designed to improve the particle swarm algorithm, that is, the particle swarm algorithm based on the genetic algorithm (GA-PSO), through the three algorithms of the simulation results of the analysis of the improved algorithm to verify the effectiveness of the algorithm. The study shows that the wind network optimized by the algorithm of this paper reduces the power consumption of the fan by 16.86%, and the error of the wind volume is 4.85%.

(4) Using Unity3D 3D modeling software and intelligent ventilation system client platform tools, a 3D visualized ventilation model of Tingnan Coal Mine, which has a high degree of similarity with the actual mine, was established. The feasibility of the improved algorithm is verified by comparing the optimized data from the wind network solution with the actual data on site, thus providing reliable data for the establishment of the visualized 3D ventilation model.

[1] 郑欢. 中国煤炭产量峰值与煤炭资源可持续利用问题研究[D]. 成都: 西南财经大学, 2014.

[2] 包兴. 煤炭行业两化融合发展现状和趋势分析[J]. 煤炭经济研究, 2019, 39(07): 74-78.

[3] 本刊讯. 国家发改委、国家能源局下发《能源技术革命创新行动计划(2016-2030年)》和《能源技术革命重点创新行动路线图》[J]. 电力与能源, 2016, 37(05): 609.

[4] GB/T 51272-2018, 煤炭工业智能化矿井设计标准[S].

[5] 任振兴. 我国矿井通风技术现状及智能化发展展望[J]. 当代化工研究, 2021, (17): 19-20.

[6] 刘虎璋. 矿井通风系统中的可靠性优化技术应用[J]. 世界有色金属, 2022, (05): 94-96.

[7] Wang Q, Dai W, Ma X, et al. Multiple models and neural networks based adaptive PID decoupling control of mine main fan switchover system[J]. LET Control Theory&Applications, 2018, 12(4): 446-455.

[8] 魏连江, 周福宝, 朱华新. 通风网络拓扑理论及通路算法研究[J]. 煤炭学报, 2008, 33(8)：926-930.

[9] 魏连江, 汪云甲, 方宗武. 复杂通风网络简化过程与原理研究[J]. 中国矿业大学学报, 2010, 39(4): 480-483.

[10] 周福宝, 魏连江, 夏同强, 等. 矿井智能通风原理、关键技术及其初步实现[J]. 煤炭学报, 2020, 45(06): 2225-2235.

[11] 斯阔成斯基, 阔马罗夫. 矿内通风学[M]. 北京: 燃料工业出版社, 1954.

[12] Scott D R, Hinsey F B, Hudson R F. A calculator for the solution of ventilation network problems[M]. Trans Inst Min Engrs, 1953: 112-623.

[13] Cross H analysis of flow i network of conduits or conductors[R]. Engineering Experiment Staton of University oflllinis, 1936.

[14] 程磊, 党海波, 彭文山. 矿井通风网络分析研究现状及趋势[J]. 煤炭工程, 2011(03): 90-92.

[15] 李恕和, 王义章. 矿井通风网络图论[M]. 北京：煤炭工业出版社, 1984: 17-38.

[16] 沈斐敏, 刘绍权, 陈文礼. 矿井通风微机程序设计与应用[M]. 北京: 煤炭工业出版社, 1995: 31-67.

[17] 谭国运. 矿井通风网络分析及电算方法[M]. 北京: 煤炭工业出版社, 1991: 165-173.

[18] 吴奉亮, 周澎. 基于智能对象的矿井通风CAD模型研究[J]. 煤炭科学技术, 2009, 37(05): 54-57.

[19] 吴奉亮. 矿井复杂风网灵敏度求解及其稳定性分析[J]. 科技导报, 2011, 29(19): 62-65.

[20] 吴奉亮, 李文福. 基于最小二乘法的优化组合权重模型在矿井环境舒适度评价中的应用[J]. 安全与环境工程, 2020, 27(05): 177-183.

[21] 张博, 王伟. 基于矿井通风网路解算的优化计算方法[J]. 安全与环境学报, 2022, 22(03): 1240-1246.

[22] 吴奉亮, 高佳南. 矿井风网雅可比矩阵对称特性及并行求解模型[J]. 煤炭学报,2016, 41(06): 1454-1459.

[23] 黄旭. 基于粒子系统算法的矿井火灾可视化研究[J]. 系统仿真学报,2021(S2): 292-294.

[24] 马恒, 高巍, 周西华. 矿井气候多参数预测与通风网络自动解算算法研究[J]. 中国安全生产科学技术, 2022, 13(11): 110-116.

[25] Chatterjee A, Xia X, Zhang L.Optimisation of mine ventilation fan speeds on demand[C]. International Conference on the Industrial&Commercial Use of Energy, 2014: 1-7.

[26] Hu W,Longson I. A computer method for the generalized controlled flow problem in ventilation networks[J]. Mining Science and Technology, 1989, 8(2): 153-167.

[27] Guang X, Jinxin H, Baisheng N, et al. Calibration of mine ventilation network models Using the Non-Linear Optimization Algorithm[J]. Energies, 2017, 11(1): 31-39.

[28] X.She, Y.Sun. Research on optimization algorithm wind quantity distribution in ventilation networks based on generic algorithm[C]. International Conference on Computational Intelligence and Natural Computing(CINC), 2010: 154-158.

[29] 张大斌, 刘桂琴. 基于群体编码方式的遗传算法求解装箱问题[J]. 计算机工程与设计, 2008, (12): 3154-3156.

[30] 肖胤喆. 基于改进粒子群优化算法的特征选择方法研究[D]. 吉林: 吉林大学, 2022.

[31] 赵迪, 何克勤. 基于改进粒子群优化算法的移动机器人路径规划[J]. 传感器与微系统, 2023, 42(06): 150-153.

[32] 胡浩鹏, 葛佳蓓, 魏云冰. 基于改进多目标粒子群算法的电动汽车充电优化策略[J]. 电气工程学报, 2024,52(03): 13-22.

[33] Mingqi Bai, Yi Liu, Lu Liu, et al. Kinetics of polyethylene pyrolysis in the atmosphere of ethylene[J]. Journal of Thermal Analysis and Calorimetry, 2021(04): 115-119.

[34] Peterson J D, Vyazovkin S, Wight C A. Kinetics of the thermal and thermo - oxdative degradation of polystyrene, polyethylene and Poly (propylene)[J]. Macromol Chem Phys, 2001, 202(06): 775-784.

[35] 刘通海. 矿井局部通风机不同控制方式对风量调节效果的对比分析[J]. 机械管理开发, 1980, 37(05): 178-179.

[36] 王德明. 矿井通风机自动调节监控系统的设计与应用[J]. 机械管理开发, 2000, 36(08): 241-242.

[37] 吴兵, 周心权. 矿井火灾风流的远程自动控制[J]. 煤矿安全, 2003, (10): 13-15.

[38] 陈小平. 矿井通风安全智能监测监控系统研制[J]. 数码设计, 2017, 6(09): 82.

[39] 杨战旗, 郝天轩. 矿井通风安全智能监测监控系统研制[J]. 工矿自动化, 2017, 43(09): 110-114.

[40] 康志国. 矿井通风系统的优化控制策略研究[J]. 机械管理开发, 2021, 36(08): 243-244+324.

[41] 李俊桥. 矿井通风参数采集算法及决策支持系统研究[D]. 辽宁: 辽宁工程技术大学, 2019.

[42] 刘红英, 王秋里. 煤矿智能通风系统研究[J]. 煤矿机械, 2019, 40(03): 37-38.

[43] 阮德超. 矿井通风系统远程监控的研究与实施[D]. 湖北: 武汉工程大学, 2013.

[44] 程晓之, 王凯. 矿井局部通风智能调控系统及关键技术研究[J]. 工矿自动化, 2021, 47(09): 18-24.

[45] 王振平. 矿井通风安全智能管控平台[J]. 技术与创新管理, 2021,42(03): 234.

[46] 张浪, 刘彦青. 矿井智能通风与关键技术研究[J]. 煤炭科学技术, 2024, 52(1): 178-195.

[47] 马文新, 陈梦乔. 基于WiFi通信技术的矿井通风监测系统分析[J]. 内蒙古煤炭经济, 2024(01): 40-42.

[48] 王晋茂. 矿井通风阻力测定及通风系统优化研究[J]. 能源与节能, 2021, (08): 158-160.

[49] 张卫亮, 张子军, 赵丹丹. 多水平密集采煤法矿井通风阻力测定分析[J]. 煤矿安全, 2018, 49(11): 180-182+189.

[50] 王兵建, 刘煜成, 高运增, 等. 基于Ventsim的王家塔煤矿通风系统优化研究[J]. 煤炭技术, 2024, 43(02): 145-149.

[51] 乔伟胜, 王峥, 周钰博. 基于层次分析法的煤矿通风系统可靠性评价及优化[J]. 煤炭技术, 2022, 41(12): 172-175.

[52] 王孝东, 陈书鹏, 蒋梦娇, 等. 某铅锌矿通风系统阻力测定分析与可靠性评价[J]. 有色金属(矿山部分), 2022, 74(03): 78-84.

[53] 武志远. 矿井通风阻力测定及改进分析[J]. 能源与节能, 2021(5): 209-210.

[54] 宿敬肖, 江春然, 吕晓华, 等. 基于GA-BP神经网络的矿井节能通风控制系统设计[J]. 煤炭技术, 2022, 41(12): 232-234.

[55] 魏连江, 周福宝, 夏同强, 等. 矿井智能通风与灾变应急决策平台[J]. 中国安全科学学报, 2022, 32(09): 158-167.

[56] 张景钢, 何鑫, 王清焱. 矿井通风网络解算研究现状与发展趋势[J]. 华北科技学院学报, 2021, 18(06): 1-8.

[57] 桑聪, 张建中, 富佳兴, 等. 基于智能通风的自然风压与主通风机特性曲线的耦合[J]. 矿业安全与环保, 2023, 50(04): 105-109.

[58] 钟捷芳. 基于物联网的矿用换风机监测系统[J]. 煤炭技术, 2023, 42(01): 268-270.

[59] 陈方方. 不同叶片设计方式的轴流式通风机性能对比分析[J]. 机械管理开发, 2021, 36(11): 22-23+34.

[60] 吴柯, 代元军, 王阳旭, 等. 矿用通风机二级叶轮尾迹区域涡量与气动噪声分析[J]. 机械制造, 2021, 59(10): 21-25+61.

[61] 韩江飞. 矿用通风机运行过程中振动故障分析及检测研究[J]. 机械管理开发, 2021, 36(02): 131-132+188.

[62] 李学哲, 王菲,付永钦, 等. 基于振动分析的矿用通风机故障预警技术研究[J]. 煤矿机械, 2021, 42(4): 171-174.

[63] 张树丰, 李博伦, 赵晓涛. 智能决策支持系统在赵庄矿通风系统优化中的应用[J]. 现代矿业, 2018, 34(08): 118-122.

[64] 任祺. 基于智能优化算法的航空器试飞效率提升[J]. 中国科技信息, 2022, (24): 43-47.

[65] 高岳林, 杨钦文, 王晓峰, 等. 新型群体智能优化算法综述[J]. 郑州大学学报（工学版）, 2022, 43(3): 21-30.

[66] 丁志成, 王甜甜. 粒子群优化算法在智能车辆轨迹跟踪的应用[J]. 机械设计与制造, 2024, 1-14.

[67] 邵良杉, 王振, 李昌明. 基于模拟退火与改进粒子群的矿井通风优化算法[J]. 系统仿真学报, 2021, 33(9): 2085-2094.

[68] 魏先民. 多态蚁群算法在煤矿机械中的研究及其应用[J]. 煤矿机械, 2012, 33(10): 213-214.

[69] 侯赓舜, 徐永利, 徐志刚, 等. 基于Kriging算法与PSO算法的桁架机器人横梁模块智能优化设计方法[J]. 科学技术与工程, 2023, 23(18): 7758-7763.

[70] 任子晖, 李昂, 吴新忠, 等. 矿井通风网络风量智能调控研究[J]. 工矿自动化, 2022, 48(11): 110-118.

[71] Guesmi H, Salem S B, Bacha K.Smart wireless sensor networks for online faults diagnosis in induction machine[J]. Computers&Electrical Engineering, 2015.

[72] Palacios R,Silva I, Goedtel A, et al.Diagnosis of stator faults severity in induction motors using two intelligent approaches[J]. IEEE Transactions on Industrial Informatics, 2017, 13(4): 1-1.

[73] Mingqi Bai, Yi Liu, Lu Liu, et al. Kinetics of polyethylene pyrolysis in the atmosphere of ethylene[J]. Journal of Thermal Analysis and Calorimetry, 2021(04): 115-119.

[74] Peterson J D, Vyazovkin S, Wight C A. Kinetics of the thermal and thermo - oxdative degradation of polystyrene, polyethylene and Poly (propylene)[J].Macromol Chem Phys,2001, 202(06): 775-784.

[75] Matala A, HOSTIKKA S. Pyrolysis modelling of PVC cable materials[J]. Fire Safety Science Proceedings of the Tenth International Symposium, 2017, 10: 917-930.

[76] Wang Z,WANG J.Comparative thermal decomposition characteristics and fire hehaviors of commercial cables[J]. Journal of Thermal Analysis and C'alorimetry, 2020, 20: 150-151.

[77] Mun S Y.Hwang C H. Experimental and numerical studies on major pyrolysis properties of flame retardant PVC cables composed ofmultiple materials[J]. Materials, 2020, 13(07): 1712.

[78] 田津休, 董航. 基于改进自适应PSO与GA的车辆检查点路径规划设计[J]. 电子技术, 2023, 52(11): 6-8.

[79] 任子晖, 李昂, 吴新忠, 等. 矿井通风网络风量智能调控研究[J]. 工矿自动化, 2022, 48(11): 110-118.

[80] 陈宇熙. 基于小生境粒子群算法的矿井按需调风优化研究[D]. 徐州: 中国矿业大学,2023.

[81] 索艳春. 基于GA-PSO-BP混合优化算法的矿井CO气体监测系统设计[J]. 矿业安全与环保, 2022, 49(06): 28-33.

[82] 童铸, 欧仲曦, 刘超, 等. 遗传算法优化粒子群的分布式光伏并网控制方法研究[J]. 自动化仪表, 2023, 44(10): 39-43.