中国安全科学学报 ›› 2025, Vol. 35 ›› Issue (2): 137-143.doi: 10.16265/j.cnki.issn1003-3033.2025.02.0552

• 安全工程技术 • 上一篇    下一篇

改进SSA优化BPNN的煤体瓦斯渗透率预测模型

汪伟1,2,3(), 崔欣超4,**(), 祁云1,2,5, 李绪萍1,2,5, 王璜瑞4, 齐庆杰6   

  1. 1 内蒙古科技大学 矿业与煤炭学院,内蒙古 包头 014010
    2 内蒙古自治区矿业工程重点实验室,内蒙古 包头 014010
    3 内蒙古自治区煤炭安全开采与利用工程技术研究中心,内蒙古 包头 014010
    4 山西大同大学 煤炭工程学院,山西 大同 037000
    5 内蒙古煤炭绿色开采与绿色利用协同创新中心,内蒙古 包头 014010
    6 辽宁理工学院,辽宁 锦州 121000
  • 收稿日期:2024-09-25 修回日期:2024-11-26 出版日期:2025-02-28
  • 通信作者:
    **崔欣超(1999—),男,山西晋城人,硕士研究生,主要研究方向为矿井灾害防治。E-mail:
  • 作者简介:

    汪伟 (1991—),男,河北玉田人,博士,副教授,硕士生导师,主要从事矿井灾害防治、应急技术与管理等方面的研究。E-mail:

    祁云 副教授

    李绪萍 教授

    齐庆杰 教授

  • 基金资助:
    国家自然科学基金面上项目资助(51974149); 国家自然科学基金地区基金资助(52464020); 山西省基础研究计划资助项目(202203021222300); 内蒙古自然科学基金资助(2024LHMS05012)

Improving SSA and optimizing BPNN for coal gas permeability prediction model

WANG Wei1,2,3(), CUI Xinchao4,**(), QI Yun1,2,5, LI Xuping1,2,5, WANG Huangrui4, QI Qingjie6   

  1. 1 School of Mining and Coal, Inner Mongolia University of Science and Technology, Baotou Inner Mongolia 014010, China
    2 Inner Mongolia Key Laboratory of Mining Engineering, Baotou Inner Mongolia 014010, China
    3 Inner Mongolia Research Center for Coal Safety Mining and Utilization Engineering and Technology, Baotou Inner Mongolia 014010, China
    4 School of Coal Engineering, Shanxi Datong University, Datong Shanxi 037000, China
    5 Inner Mongolia Cooperative Innovation Center for Coal Green Mining and Green Utilization, Baotou Inner Mongolia 014010, China
    6 Liaoning Institute of Science and Engineering, Jinzhou Liaoning 121000, China
  • Received:2024-09-25 Revised:2024-11-26 Published:2025-02-28

摘要:

为更加精确地预测煤体瓦斯渗透率,进而保障煤矿安全生产,构建基于改进麻雀搜索算法(ISSA)优化反向传播神经网络(BPNN)的煤体瓦斯渗透率预测模型。首先,通过引入Sine混沌映射和高斯变异改进麻雀搜索算法(SSA),以增强其全局搜索能力和局部寻优精度,从而优化BPNN的权值和阈值配置;然后,通过皮尔逊相关系数矩阵和核主成分分析(KPCA)处理瓦斯渗透率影响因素的数据,以提高模型的计算效率和准确性,并以累积方差达88.59%的3个主成分提取为模型输入,渗透率作为输出进行试验;最后,将该模型应用于山西某煤矿进行实例验证。结果表明:ISSA-BPNN在平均绝对误差(MAE)、平均绝对百分比误差(MAPE)、均方根误差(RMSE)和决定系数R2等4个指标上优于粒子群算法(PSO)优化BPNN、PSO优化支持向量机(PSO-SVM)、PSO优化最小二乘支持向量机(LSSVM)及SSA优化BPNN(SSA-BPNN)模型,且相较于其他模型在测试样本中的平均绝对误差(MAE)分别降低0.032 7、0.022、0.017 9、0.018 2;MAPE分别降低5.15%、3.14%、2.76%、2.36%;RMSE分别降低0.031 6、0.027 9、0.018 8、0.022 2;R2分别提高0.077 5、0.065 8、0.040 1、0.049 3;实例验证表明模型可靠性和稳定性较高。

关键词: 改进麻雀搜索算法(ISSA), 反向传播神经网络(BPNN), 煤体瓦斯, 渗透率, 预测模型

Abstract:

In order to predict coal gas permeability more accurately and ensure coal mine safety production, a prediction model of coal gas permeability based on ISSA-optimized BPNN was constructed. Firstly, the sparrow search algorithm (SSA) was improved by introducing Sine chaotic mapping and Gaussian mutation to enhance its global search capability and local optimization accuracy, thereby optimizing the weight and threshold configuration of BPNN. Secondly, the data on the factors affecting gas permeability were processed using Pearson correlation coefficient matrix and kernel principal component analysis (KPCA) to improve the computational efficiency and accuracy of the model. Three principal components with a cumulative variance of 88.59% were extracted as model inputs, and permeability was used as the output for the experiment. Finally, the model was applied to a coal mine in Shanxi for case verification. The experimental results show that ISSA-BPNN outperforms PSO-BPNN, PSO-SVM, PSO-LSSVM, and SSA-BPNN models in four indicators: mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), root mean square error (RMSE), and coefficient of determination (R2). Compared with other models, ISSA-BPNN has reduced MAE by 0.032 7, 0.022, 0.017 9, and 0.018 2 in the test samples, respectively. MAPE decreases by 5.15%, 3.14%, 2.76%, and 2.36% respectively. RMSE decreases by 0.031 6, 0.027 9, 0.018 8, and 0.022 2 respectively. R2 increases by 0.077 5, 0.065 8, 0.040 1, and 0.049 3, respectively. Finally, the case verification shows that its reliability and stability are high in practical applications.

Key words: improved sparrow search algorithm (ISSA), back propagation neural network (BPNN), coal gas, permeability, prediction model

中图分类号: