瓦斯灾害事故不仅严重威胁着煤矿人员的生命，还给企业带来巨大经济损失，因此做好瓦斯灾害预防工作至关重要。精准快捷预测瓦斯涌出量，提前做好瓦斯防治措施，对矿井瓦斯治理及煤矿安全生产具有重要意义。
瓦斯涌出量预测是一个多维非线性小样本数据预测问题，其影响因素众多，且相互之间存在复杂的关系。为研究瓦斯涌出量影响因素的具体作用关系，根据分源预测法和选取原则，选取18个影响因素建立初始预测指标体系。通过试验矿井采集数据进行非线性特性分析，得到瓦斯涌出量影响因素具有非线性和存在信息重叠等特征。采用斯皮尔曼等级相关系数法明确各个影响因素与瓦斯涌出量之间的相关强度。提出了采用核主成分分析法（KPCA）进行降维，确定了最优核参数，明确了特征指标和模型输入变量。
为了实现瓦斯涌出量精准快捷预测，针对人工鱼群算法（AFSA）后期的收敛速度慢、最优解求解精度不高的问题，提出采用莱维飞行步长进行参数改进，得到了基于莱维飞行的人工鱼群算法（IAFSA），通过多峰函数寻优测试实验进行了寻优效果验证，结果表明其寻优精度和寻优速度得到提高。针对极限学习机中的权值和阈值参数是初始随机生成的问题，将IAFSA算法与极限学习机相耦合，得到IAFSA-ELM预测算法，并通过UCI经典数据集预测实验进行了预测可行性验证，结果表明该预测算法具有可行性和可信度。结合核主成分分析方法与IAFSA-ELM预测算法，构建基于KPCA-IAFSA-ELM算法的瓦斯涌出量预测模型，并利用MATLAB软件中图形用户界面设计工具，开发了具有通适性的煤矿瓦斯涌出量预测软件。
利用预测软件对试验矿井和湖南某矿、沈阳某矿进行实例应用，结果表明：分源预测法预测相对误差约为10.27%，IAFSA-ELM算法的预测精度比分源预测法提高了12.8倍左右，该预测算法比传统方法的预测精度更高；预测算法迭代次数也大幅度下降，预测差值基本不超过±0.4，预测相对误差均值均不超过4%，进一步表明IAFSA-ELM算法预测效率快，预测精度高，预测效果稳定，且预测软件具有一定的通适性，可以实现瓦斯涌出量精准快捷预测，对煤矿井下瓦斯灾害防治具有重要的现场指导意义。

Gas disaster accidents not only seriously threaten the lives of coal mine personnel, but also bring huge economic losses to enterprises, therefore, it is very important to prevent gas disasters. Precisely and quickly predict the amount of gas emission, and make gas prevention and control measures in advance, which are of great significance to mine gas control and coal mine safety production.
Gas emission prediction is a multi-dimensional nonlinear small sample data prediction problem, which has many influencing factors and complex relationships between them. In order to study the specific relationship between the influencing factors of gas emission, 18 influencing factors were selected to establish an initial predictive index system according to the source-division forecasting method and selection principle. Through the non-linear characteristic analysis of the data collected in the test mine, the influencing factors of gas emission have the characteristics of non-linearity and overlap of information. Spearman's rank correlation coefficient method was used to clarify the correlation strength between each influencing factor and the amount of gas emission. The kernel principal component analysis method was used to reduce dimensionality, the optimal kernel parameters were determined, and the characteristic indexes and model input variables were clarified.
In order to realize the accurate and quick prediction of gas emission, in view of the slow convergence speed of the artificial fish swarm algorithm and the low accuracy of the optimal solution in the later stage, the Levi flight step was proposed to improve the parameters, and the artificial fish swarm algorithm based on Levi flight was obtained, the optimization effect was verified through the multimodal function optimization test experiment, and the results show that the optimization accuracy and optimization speed have been improved. Aiming at the problem that the weight and threshold parameters in the extreme learning machine were initially randomly generated, the IAFSA algorithm and the extreme learning machine were coupled to obtain the IAFSA-ELM prediction algorithm, and through the UCI classic data set prediction experiment to verify the feasibility of the prediction, the results show that the prediction algorithm is feasible and credible. the nuclear principal component analysis method and the IAFSA-ELM prediction algorithm were combined to construct a gas emission prediction model based on the KPCA-IAFSA-ELM algorithm, and the graphical user interface design tool in MATLAB software was used to developed a universal coal mine gas emission prediction software.
Forecasting software was used to carry out example applications in test mines, a mine in Hunan and a mine in Shenyang, The results show that the prediction relative error of the split-source prediction method is about 10.27%, and the prediction accuracy of the IAFSA-ELM algorithm is about 12.8 times higher than that of the split-source prediction method, and the prediction accuracy of this prediction algorithm is higher than that of the traditional method. The number of iterations of the prediction algorithm has also dropped significantly, the prediction difference basically does not exceed ±0.4, and the average prediction relative error does not exceed 4%, this further shows that the IAFSA-ELM algorithm has fast prediction efficiency, high prediction accuracy, and stable prediction effect, and the prediction software has a certain degree of compatibility, It can realize the accurate and quick prediction of gas emission, which has important on-site guiding significance for the prevention and control of gas disasters in coal mines.

[1]钱鸣高,缪协兴,许家林.资源与环境协调(绿色)开采[J].煤炭学报,2007(01):1-7.

[2]谢和平,周宏伟,薛东杰,等.煤炭深部开采与极限开采深度的研究与思考[J].煤炭学报,2012,37(04):535-542.

[3]钱鸣高.煤炭的科学开采[J].煤炭学报,2010,35(04):529-534.

[4]范立民.陕西省煤矿瓦斯事故分析及预防对策研究[J].煤炭工程,2015,47(09):71-73.

[5]秦玉金,苏伟伟,姜文忠,等.我国矿井瓦斯涌出量预测技术研究进展及发展方向[J].煤矿安全,2020,51(10):52-59.

[6]肖鹏,谢行俊,双海清,等.基于KPCA-CMGANN算法的瓦斯涌出量预测研究[J].中国安全科学学报,2020,30(05):39-47.

[7]王晓蕾,姬治岗,谢怡婷,等.采煤工作面瓦斯涌出量预测技术现状及发展趋势[J].科学技术与工程,2019,19(33):1-9.

[8]Frodsham K,Gayer RA.The impact of tectonic deformation upon coal seams' in the South Wales coalfield,UK[J].Int J. Coal Geol.1999,17(38):297-332.

[9]Shepherd J.Outbursts and geological structures in coal mines[J]. Int J Rock Mech Min Sci&Geomech,1981,18(4):267.

[10]徐青伟,王兆丰.矿山统计法瓦斯涌出量预测中存在的错误及修正[J].中国煤炭,2015,41(10):118-120.

[11]刘彦伟,薛文涛,李志强.矿山统计法瓦斯涌出量预测模型存在的问题与校正[J].煤矿安全,2015,46(05):176-178+182.

[12]陈洋,刘恩,陈大力,等.瓦斯涌出量分源预测法的发展与实践研究[J].煤矿安全,2010,41(02):73-76.

[13]王孔善.关于分源预测法预测矿井瓦斯涌出量准确性和适用性的探讨[J].煤矿安全,2011,42(11):93-96.

[14]靳晓华,顾北方,郭昕曜,等.基于瓦斯地质理论的矿井瓦斯含量与涌出量预测[J].煤炭技术,2014,33(07):78-80.

[15]陈向军,王兆丰,贾东旭.史山煤矿回采工作面瓦斯涌出量预测研究[J].煤炭科学技术,2007(05):87-89.

[16]伍爱友,田云丽,宋译,等.灰色系统理论在矿井瓦斯涌出量预测中的应用[J].煤炭学报,2005(05):47-50.

[17]Dong Dingwen. Mine Gas Emission Prediction based on Gaussian Process Model[J]. Procedia Engineering,2012,45:334-338.

[18]Pan Yumin, Deng Yonghong, Zhang Quanzhu,et al. Dynamic prediction of gas emission based on wavelet neural network toolbox [J]. Journal of Coal Science and Engineering (China), 2013, 19(02):174-181.

[19]田世祥,林华颖,马瑞帅,等.瓦斯涌出量与构造煤关联性预测研究[J].中国安全科学学报,2019,29(10):105-109.

[20]刘卫方,陈健.改进的R/S分析方法及矿井瓦斯涌出量预测[J].能源技术与管理,2020,45(01):48-49+144.

[21]孙建华,张志立,石茜,等.基于主成分-逐步回归分析法的瓦斯涌出量预测研究[J].煤炭工程,2020,52(01):89-94.

[22]程加堂,艾莉,熊燕.基于IQPSO-BP算法的煤矿瓦斯涌出量预测[J].矿业安全与环保,2016,43(04):38-41.

[23]Lu Guobin, Kang Jinkai, Bai Gang,et al. Application of PCA-BP to gas emission prediction of mining working face[J]. Journal of Liaoning Technical University(Natural Science), 2015,34(12):1329-1334.

[24]徐耀松,齐翠玉,丰胜成.基于IGSA-BP网络的瓦斯涌出量预测模型[J].电子测量与仪器学报,2019,33(05):111-117.

[25]张宝,何健.基于BP神经网络的小断层构造区域瓦斯涌出预测方法研究[J].煤炭工程,2020,52(09):106-110.

[26]Liu Yang, Shi Qingjun, Li Jing,et al. Study on Gas Emission Rate Prediction Based on Chaos Analysis[J]. International Conference On Advances In Engineering 2011,2011, 24:106-110.

[27]徐刚,王磊,金洪伟,等.因子分析法与BP神经网络耦合模型对回采工作面瓦斯涌出量预测[J].西安科技大学学报,2019,39(06):965-971.

[28]张强,贾宝山,董晓雷,等.PCA-GA-SVM的回采工作面瓦斯涌出量预测[J].辽宁工程技术大学学报(自然科学版),2015,34(05):572-577.

[29]Fan Baolong, Bai Chunhua, Li Jianping. Forecasting model of coalface gas emission based on LMD-SVM method[J]. Journal of Mining and Safety Engineering, 2013,30(6):946-952.

[30]Feng Yuxi, Zhang Kaizhi, Yu Xizhan,et al. Prediction for Gas Emission Quantity of the Working Face Based on LSSVM Optimized by Improved Particle Swarm Optimization[J]. Advanced Materials Research, 2014, 1051:1028-1031.

[31]李超群,李宏伟.一种基于支持向量机和模型树的回归模型及其在采煤工作面瓦斯涌出量预测中的应用[J].应用基础与工程科学学报,2011,19(03):370-378.

[32]乔美英,马小平,兰建义,等.基于加权LS-SVM时间序列短期瓦斯预测研究[J].采矿与安全工程学报,2011,28(02):310-314.

[33]Gao Li, Yu Hongzhen. Prediction of gas emission based on information fusion and chaotic time series[J]. Journal of China University of Mining and Technology, 2006,16(1):94-96.

[34]王晓路,刘健,卢建军.基于虚拟状态变量的卡尔曼滤波瓦斯涌出量预测[J].煤炭学报,2011,36(01):80-85.

[35]付华,代巍.基于LLE与BA-Elman的瓦斯涌出量动态预测研究[J].传感技术学报,2016,29(09):1383-1388.

[36]王雨虹,付华,侯福营,等.基于混沌免疫粒子群优化和广义回归神经网络的回采工作面瓦斯涌出量预测模型[J].计算机应用,2014,34(11):3348-3352.

[37]Rocha A M A C, Costa M F P, Fernandes E M G P. A filter-based artificial fish swarm algorithm for constrained global optimization: theoretical and practical issues[J]. Journal of Global Optimization, 2014,60(2):239-263.

[38]张玉春,程春英.关于人工鱼群算法的探讨[J].内蒙古民族大学学报(自然科学版), 2016,31(03):203-205.

[39]Xiang Wanli, Meng Xuelei, Li Yinzhen, et al. An improved artificial bee colony algorithm based on the gravity model[J]. Information Sciences, 2018,429:49-71.

[40]倪中华.人工蜂群算法在云计算系统中的应用[J].数学的实践与认识, 2020, 50(24):275-284.

[41]Zeng Rui, Wang Yingyan. A chaotic simulated annealing and particle swarm improved artificial immune algorithm for flexible job shop scheduling problem[J]. EURASIP Journal on Wireless Communications and Networking, 2018(1):101-111.

[42]Xia Xuewen, Xing Ying, Wei Bo,et al. A fitness-based multi-role particle swarm optimization[J]. Swarm & Evolutionary Computation, 2018,44:349-364.

[43]Reddy A S, Vaisakh K. Environmental Constrained Economic Dispatch by Modified Shuffled Frog Leaping Algorithm[J]. Journal of Bioinformatics & Intelligent Control, 2013, 2(3):216-222.

[44]马原响.智能优化算法简述[J].科学技术创新,2021(03):123-124.

[45]Xu Ping. Research on optimized model of travel route selection based on intelligent image information and ant Colony algorithm[J]. Multimedia Tools and Applications, 2019(4):1-17.

[46]Neshat M, Sepidnam G, Sargolzaei M, et al. Artificial fish swarm algorithm: a survey of the state-of-the-art, hybridization, combinatorial and indicative applications[J]. Artificial Intelligence Review, 2014, 42(4):965-997.

[47]Luan Xinyuan, Li Zhanpei, Liu Tingzhang. A Novel Attribute Reduction Algorithm Based on Rough Set and Improved Artificial Fish Swarm Algorithm[J]. Neurocomputing, 2015, 174:522-529.

[48]Chen S M，Sarosh A，Dong Y F．Simulated annealing based artificial bee colony algorithm for global mumerical optimization[J].Applied Mathematics and Computations,2012, 219:3575-3589.

[49]Zhang R L , Shan M Y , Liu X H , et al. A novel fuzzy hybrid quantum artificial immune clustering algorithm based on cloud model[J]. Engineering Applications of Artificial Intelligence, 2014, 35:1-13.

[50]Tan Y, Tan G, Deng S. Hybrid particle swarm optimization with chaotic search for solving integer and mixed integer programming problems[J].Journal of Central South University,2014, 21(7):2731-2742.

[51]Niknam T,Narimani M R,Azizipanah-Abarghooee R.A. new hybrid algorithm for optimal power flow considering prohibited zones and valve point effect[J].Energy conversion and management,2012,58:197-206.

[52]Dorigo M, Bonabeau E, Theraulaz G.Ant algorithm and stigmery[J].Future Generation Computer Systems,2000,16(8):851-871.

[53]Diaz D, Molina A, Hahn D W. Laser-Induced Breakdown Spectroscopy and Principal Component Analysis for the Classification of Spectra from Gold-Bearing Ores[J].Applied spectroscopy,2020,74(1):42-54.

[54]胡迪,聂飞平,李学龙.基于深度线性判别分析的哈希技术[J].中国科学:信息科学, 2021,51(02):279-293.

[55]Lu Guifu, Wang Yong, Zou Jian, et al. Matrix exponential based discriminant locality preserving projections for feature extraction.[J]. Neural networks : the official journal of the International Neural Network Society,2018,97:127-136.

[56]杜杰,王骁,胡良剑.非线性降维技术与可视化应用[J].东华大学学报(自然科学版), 2020,46(04):675-680.

[57]黄虹,徐庆根,张奕倩,等.基于KPCA降维的Weight-LSSVM财务危机预警模型[J].统计与决策,2020,36(20):180-184.

[58]李鑫,续婷,胡红萍,等.局部流形学习在SAR目标分类中的应用[J].现代雷达,2020, 42(04):33-36+40.

[59]张晓东,韦程东,岑泰林,等.基于等距特征映射算法在人脸识别问题中的数学建模[J].广西师范学院学报(自然科学版),2018,35(04):42-48.

[60]高亮,李学杰,潘吉成.布尔台矿回采工作面瓦斯涌出主控因素及治理措施[J].中国安全生产科学技术,2019,15(05):130-135.

[61]陈建强.开采急倾斜特厚煤层瓦斯涌出影响因素分析[J].矿业安全与环保,2015,42(05):92-95.

[62]尹灿伟,余同勇,李新建.掘进工作面瓦斯涌出影响因素分析及预测模型[J].中州煤炭,2014(02):43-45+48.

[63]原德胜,陈跟马,李子文,等.大佛寺煤矿40108综采工作面瓦斯涌出规律及影响因素分析[J].煤矿安全,2014,45(05):155-158.

[64]裴建,白岳松.王家岭煤矿18101工作面瓦斯涌出量影响因素分析[J].能源技术与管理, 2016,41(04):38-40.

[65]夏海斌,郭林生,林建成,等.小庄矿40309工作面瓦斯涌出规律及影响因素分析[J].中国矿业,2020,29(10):134-138.

[66]解明垒,马尚权.基于多元线性回归理论的煤矿瓦斯涌出量预测[J].陕西煤炭,2021, 40(01):26-29+52.

[67]于健浩,毛德兵.我国煤矿顶板管理现状及防治对策[J].煤炭科学技术,2017,45(05):65-70.

[68]朱红青,常文杰,张彬.回采工作面瓦斯涌出BP神经网络分源预测模型及应用[J].煤炭学报,2007(05):504-508.

[69]齐德明.煤矿瓦斯涌出量影响因素分析与预测研究[J].山东煤炭科技,2018(01):99-101.

[70]柏树森.矿井瓦斯涌出量影响因素分析[J].企业技术开发,2014,33(14):179-180.

[71]朱士飞,秦云虎,徐田高.矿井瓦斯涌出量影响因素分析[J].地质学刊, 2011,35(1):86-89.

[72]陈波,郑文涛,梁汉东,等.地震活动与煤矿瓦斯溢出事故之间的影响关系[J].煤炭学报,2005(04):447-450.

[73]Ashok K J, Abirami S. Aspect-based opinion ranking framework for product reviews using a Spearman's rank correlation coefficient method[J].Information Sciences, 2018,460-461:23-41.

[74]陈迪,廖柯熹,何国玺,等.基于EWM-GRA的腐蚀主控因素分析与腐蚀模型建立[J].表面技术,2019,48(06):268-273.

[75]吴天昊,刘韬,施海宁,等.基于核主元分析法的核电厂设备状态监测技术研究[J].核动力工程,2020,41(05):132-137.

[76]Sun Haotong, Lv Guodong, Mo Jiaqing, et al. Application of KPCA combined with SVM in Raman spectral discrimination[J].Optik-International Journal for Light and Electron Optics,2019,184:214-219.

[77]赵秀红. 基于主成分分析的特征提取的研究[D].西安电子科技大学,2016.

[78]王红莲. 基于KPCA的生态效率评价与预测模型研究[D].华北理工大学,2017.

[79]张成,李娜,李元,等.核参数判别选择方法在核主元分析中的应用[J].计算机应用,2014,34(10):2895-2898.

[80]刘海,张广秀,陈勇,等.运用核主成分分析提取内燃机声品质客观特征[J].内燃机学报,2019,37(05):441-445.

[81]王莹,王亚慧,安允.基于PSO-KPCA-LVQ的燃气调压器故障诊断[J].现代电子技术, 2020,43(24):67-71.

[82]赵林,吕健.基于因子分析的虚拟现实环境评价方法[J].计算机应用,2019,39(S1):159-163.

[83]赵慧琴,朱建平.如何用SPSS软件计算因子分析应用结果[J].统计与决策,2019,35(20):72-77.

[84]李晓磊.一种新型的智能优化方法-人工鱼群算法[D].浙江大学,2003.

[85]朱旭辉,倪志伟,程美英.变步长自适应的改进人工鱼群算法[J].计算机科学,2015,42(02):210-216+246.

[86]王丽,宫建平.基于递减反馈视野的人工鱼群算法改进与应用[J].计算机应用与软件,2016,33(11):226-229+248.

[87]张毅,杨光辉,花远红.基于改进人工鱼群算法的机器人路径规划[J].控制工程,2020,27(07):1157-1163.

[88]刘东林,李乐乐.一种新颖的改进人工鱼群算法[J].计算机科学,2017,44(04):281-287.

[89]Zhang Z , Wang K , Zhu L , et al. A Pareto improved artificial fish swarm algorithm for solving a multi-objective fuzzy disassembly line balancing problem[J]. Expert Systems with Applications, 2017,86:165-176.

[90]黄柏儒,樊晓光,禚真福,等.引入贪心鱼群的改进人工鱼群算法[J].传感器与微系统,2015,34(05):119-122.

[91]Jia Shiyu, Zhou Kang, Zhou Sisi,et al. An artificial fish swarm algorithm for a multi-objective grain transportation problem[J]. Evolutionary Intelligence,2020,13(1):9-19.

[92]许恒迎,孙伟斌,张霞,等.自适应视野和步长的局部邻域人工鱼群算法[J].计算机工程与设计,2012,33(07):2815-2821.

[93]龚波,曾飞艳.基于自适应动态邻域结构的人工鱼群算法[J].计算机工程与应用,2015,51(13):52-55+110.

[94]梁毓明,裴兴环.粒子群优化人工鱼群算法[J].计算机仿真,2016,33(06):213-217+281.

[95]袁光辉,樊重俊,张惠珍,等.一种新的粒子群算法与人工鱼群算法的混合算法[J].上海理工大学学报,2014,36(03):223-226+238.

[96]梁雪慧,赵嘉祺.人工鱼群与遗传混合算法在无人艇路径规划中的应用[J].计算机工程与科学,2019,41(05):942-947.

[97]姜慧楠,张向锋.一种人工鱼群-蛙跳混合优化算法[J].上海电机学院学报,2019,22(06):330-336+344.

[98]Zhang Xialin, Lian Lingkun, Zhu Fukang. Parameter fitting of variogram based on hybrid algorithm of particle swarm and artificial fish swarm[J].Future Generation Computer Systems,2020,116:265-274.

[99]Keerthana G, Anandan P, Nachimuthu N. Robust Hybrid Artificial Fish Swarm Simulated Annealing Optimization Algorithm for Secured Free Scale Networks against Malicious Attacks[J]. Computers, Materials & Continua, 2021,66(1):903-917.

[100]魏星,李志远,陈艳.基于蚁群和鱼群的混合优化光网络动态RWA算法[J].光通信技术,2015,39(03):47-49.

[101]Li Jianpo, Dong Pengwei. Global maximum power point tracking for solar power systems using the hybrid artificial fish swarm algorithm[J].Global Energy Interconnection, 2019,2(04):351-360.

[102]Hu X.T., Zhang H.Q.,Li Z.C, et al. A Novel Self-Adaptation Hybrid Artificial Fish-Swarm Algorithm[J]. IFAC Proceedings Volumes,2013,46(05):583-588.

[103]Fang Na, Zhou Jianzhong, Zhang Rui,et al. A hybrid of real coded genetic algorithm and artificial fish swarm algorithm for short-term optimal hydrothermal scheduling[J]. International Journal of Electrical Power & Energy Systems,2014,62:617-629.

[104]Xian Sidong, Zhang Jianfeng, Xiao Yue, et al. A novel fuzzy time series forecasting method based on the improved artificial fish swarm optimization algorithm[J].Soft Computing, 2018,22(12):3907-3917.

[105]王李进,尹义龙,钟一文.逐维改进的布谷鸟搜索算法[J].软件学报,2013,24(11):2687-2698.

[106]Huang, G.B., Zhu, Q.Y., Siew, C. K. Extreme learning machine: theory and applications. Neurocomputing, 2006,70(01):489-501.

[107]徐睿,梁循,齐金山,等.极限学习机前沿进展与趋势[J].计算机学报,2019,42(07):1640-1670.

[108]Zhu Xuhui, Ni Zhiwei, Cheng Meiying, et al. Selective ensemble based on extreme learning machine and improved discrete artificial fish swarm algorithm for haze forecast[J]. Applied Intelligence,2018,48(7):1757-1775.

[109]Dokeroglu T, Sevinc E. Evolutionary parallel extreme learning machines for the data classification problem[J].Computers & Industrial Engineering,2019,130:237-249.

[110]周云飞,李芳,安政,等.基于C#与MATLAB混合编程在瓦斯预测系统中的应用[J].山西能源学院学报,2020,33(06):96-98+102.

[111]Li Runqiu, Shi Shiliang, Wu Aiyou, et al. Research on Prediction of Gas Emission based on Self-organizing Data Mining in Coal Mines[J]. Procedia Engineering,2014, 84:779-785.

[112]董晓雷,贾进章,白洋,等.基于SVM耦合遗传算法的回采工作面瓦斯涌出量预测[J].安全与环境学报,2016,16(02):114-118.