基于数据重构增强的采空区遗煤自燃预测模型
Natural prediction model of goaf residual coal based on data reconstruction and enhancement
-
摘要: 目前采空区遗煤自燃预测模型的外推泛化能力不强，主要原因是模型训练数据集数量较少以及监测过程和方法等造成的数据分布特征不明显；采用WGAN-GP模型生成虚拟样本，对实测数据集特征分布进行重构增强；通过参数相关性计算，生成虚拟数据集各参数间相关性系数变化均未超过15%；采用1倍实测数据集数量的扩容虚拟样本，进行模型的学习训练。结果表明：各模型的预测性能均有提高，其中R2指标GA-BPNN模型提高12%，GA-SVM模型提高4%，RF模型提高3%；MAE指标均降低，GA-BPNN模型降低0.67 ℃，GA-SVM模型降低了0.54 ℃，RF模型降低0.33 ℃； RMSE指标均降低，GA-BPNN模型降低0.41 ℃，GA-SVM模型降低0.46 ℃，RF模型降低0.39 ℃；增强扩容的数据集对3种预测模型的性能都有提高，其中GA-BPNN模型预测性能提高幅度最大。Abstract: The prediction model of residual coal spontaneous combustion temperature in goaf is weak of extrapolation and generalization at present. The main reason is that the number of model training data sets is small and the data distribution characteristics are not obvious due to the monitoring process and methods. In this paper, the WGAN-GP model is used to generate virtual samples and reconstruct and enhance the measured data sets. Through parameter correlation calculation, the variation of correlation coefficient among parameters of the generated virtual data set is not more than 15%. The results show that the prediction performance of each model is improved, among which the R2 index GA-BPNN model is improved by 12%, GA-SVM model is improved by 4%, RF model is improved by 3%. MAE index was decreased by 0.67 ℃ for GA-BPNN model, 0.54 ℃ for GA-SVM model and 0.33 ℃ for RF model. The RMSE index was decreased by 0.41 ℃ in GA-BPNN model, 0.46 ℃ in GA-SVM model and 0.39 ℃ in RF model. The enhanced and expanded data sets can improve the performance of the three prediction models, among which GA-BPNN model has the greatest improvement.
-
-
[1] 邓军，白祖锦，肖旸，等.煤自燃灾害防治技术现状与挑战[J].煤矿安全，2020，51（10）：118-125. DENG Jun, BAI Zujin, XIAO Yang, et al. Present situation and challenge of coal spontaneous combustion disasters prevention and control technology[J]. Safety in Coal Mines, 2020, 51（10）: 118-125.
[2] 方新秋，梁敏富，李爽，等.智能工作面多参量精准感知与安全决策关键技术[J].煤炭学报，2020，45（1）：493-508. FANG Xinqiu, LIANG Minfu, LI Shuang, et al. Key technologies of multi-parameter accurate perception and security decision in intelligent working face[J]. Journal of China Coal Society, 2020, 45（1）: 493-508.
[3] 王德明，王俊.基于无导师神经网络的煤炭自燃危险性聚类分析[J].煤炭学报，1999（2）：37-40. WANG Deming, WANG Jun. The cluster analysis based on non-teacher artificial neural network for the danger prediction of coal spontaneous fire[J]. Journal of China Coal Society, 1999（2）: 37-40.
[4] 徐精彩，赵敏，孙红丽，等.人工神经网络在煤氧化性预测方面的应用[J].辽宁工程技术大学学报，2004，23（2）：149-151. XU Jingcai, ZHAO Min, SUN Hongli, et al. Application of artificial neural network in predicting coal oxidation property[J]. Journal of Liaoning Technical University, 2004, 23（2）: 149-151.
[5] 周福宝，李金海.煤矿火区启封后复燃预测的BP神经网络模型[J].采矿与安全工程学报，2010，27（4）：494-498. ZHOU Fubao, LI Jinhai. Prediction model for reignition of fire zone after unsealing based on bp neural networks[J]. Journal of Mining & Safety Engineering, 2010, 27（4）: 494-498.
[6] 桂祥友，郁钟铭，孟絮屹.基于神经网络的自然发火危险性评价与预测[J].采矿与安全工程学报，2008，25（4）：453-457. GUI Xiangyou, YU Zhongming, MENG Xuyi. Evaluation and prediction of coal spontaneous combustion hazards risk based on neural network[J]. Journal of Mining & Safety Engineering, 2008, 25（4）: 453-457.
[7] 程结园，张涛，杨艳.基于多传感器小波神经网络的煤自燃监测研究[J].煤矿机械，2015，36（1）：230-232. CHENG Jieyuan, ZHANG Tao, YANG Yan. Research on coal combustion based on wavelet neural network for multi-sensor fusion technique[J]. Coal Mine Machinery, 2015, 36（1）: 230-232.
[8] 赵伟，任凤国.基于模糊C均值聚类算法的矿井煤炭自燃预测[J].煤矿安全，2015，46（11）：183-185. ZHAO Wei, REN Fengguo. Prediction of coal spontaneous combustion in mine based on fuzzy C means clustering algorithm[J]. Safety in Coal Mines, 2015, 46（11）: 183-185.
[9] 边冰，刘奇，何浩.基于LVQ神经网络的煤自然发火预测系统[J].华北理工大学学报（自然科学版），2017， 39（1）：12-16. BIAN Bing, LIU Qi, HE Hao. Forecasting system of spontaneous combustion of coal based on LVQ neural network[J]. Journal of North China University of Science and Technology（Natural Science Edition）, 2017, 39（1）: 12-16.
[10] 温廷新，于凤娥.基于KPCA-Fisher判别分析的煤炭自燃预测研究[J].矿业安全与环保，2018，45（2）：49-53. WEN Tingxin, YU Feng’e. Research on prediction of coal spontaneous combustion based on KPCA-Fisher discriminant analysis[J]. Mining Safety & Environmental Protection, 2018, 45（2）: 49-53.
[11] 邢媛媛，张飞飞.基于AEM-TOPSIS的煤炭自燃风险评价研究[J].煤炭工程，2021，53（11）：131-134. XING Yuanyuan, ZHANG Feifei. Risk evaluation of coal spontaneous combustion based on AEM-TOPSIS[J]. Coal Engineering, 2021, 53（11）: 131-134.
[12] 孟倩.基于计算智能的煤矿自然发火预警研究[D].徐州：中国矿业大学，2015. [13] 邓军，杨一帆，翟小伟.基于层次分析法的矿井煤自燃危险性模糊评价[J].中国安全生产科学技术，2014，10（4）：120-125. DENG Jun, YANG Yifan, ZHAI Xiaowei. Fuzzy evaluation on risk of coal spontaneous combustion based on AHP[J]. Journal of Safety Science and Technology, 2014, 10（4）: 120-125.
[14] 邓军，周少柳，马砺，等.基于PCA-PSOSVM的煤自燃程度预测研究[J].矿业安全与环保，2016，43（5）：27-31. DENG Jun, ZHOU Shaoliu, MA Li, et al. Research on prediction method of coal spontaneous combustion degree based on PCA－PSOSVM[J]. Mining Safety & Environmental Protection, 2016, 43（5）: 27-31.
[15] 邓军，雷昌奎，曹凯，等.采空区煤自燃预测的随机森林方法[J].煤炭学报，2018，43（10）：2800-2808. DENG Jun, LEI Changkui, CAO Kai, et al. Random forest method for predicting coal spontaneous combustion in gob[J]. Journal of China Coal Society, 2018, 43（10）: 2800-2808.
[16] 仲晓星，王建涛，周昆.矿井煤自燃监测预警技术研究现状及智能化发展趋势[J].工矿自动化，2021，47（9）：7-17. ZHONG Xiaoxing, WANG Jiantao, ZHOU Kun. Monitoring and early warning technology of coal spontaneous combustion in coal mines: research status and intelligent development trends[J]. Industry and Mine Automation, 2021, 47（9）: 7-17.
[17] 向家伟.机械故障数值模拟驱动的生成式对抗网络及智能诊断原理[J].中国科学（技术科学），2021，51（3）：341-355. XIANG Jiawei. Numerical simulation driving generative adversarial networks in association with the artificial intelligence diagnostic principle to detect mechanical faults[J]. Scientia Sinica（Technologica）, 2021, 51（3）: 341-355.
[18] 刘建伟，谢浩杰，罗雄麟.生成对抗网络在各领域应用研究进展[J].自动化学报，2020，46（12）：2500. LIU Jianwei, XIE Haojie, LUO Xionglin. Research progress on application of generative adversarial networks in various fields[J]. Acta Automatica Sinica, 2020, 46（12）: 2500.
[19] Gulrajani I, Ahmed F, Arjovsky M, et al. Improved training of Wasserstein GANs[C]// Proceedings of the 2017 Advances in Neural Information Processing Systems. LongBeach, 2017: 5767-5777. [20] 丁珮宽.基于GANs数据增强的复杂工业过程建模方法[D].徐州：中国矿业大学，2021. [21] 何强，唐向红，李传江，等.负载不平衡下小样本数据的轴承故障诊断[J].中国机械工程，2021，32（10）：1164-1171. HE Qiang, TANG Xianghong, LI Chuanjiang,et al. Bearing fault diagnosis method based on small sample data under unbalanced loads[J]. China Mechanical Engineering, 2021, 32（10）: 1164-1171.
[22] 罗新新.基于深度生成模型的零样本学习方法研究[D].南京：南京邮电大学，2021. [23] Wei N, Wang L, Chen G, et al. Mixed-type data generation method based on generative adversarial networks[J]. EURASIP Journal on Wireless Communications and Networking, 2022, 2022（1）: 1-11. [24] 马丹.生成对抗网络的关键技术研究与应用[D].成都：电子科技大学，2020. [25] 彭志江.面向小样本数据的特征分析技术研究[D]. 成都：电子科技大学，2021. [26] 杨懿男，齐林海，王红.基于生成对抗网络的小样本数据生成技术研究[J].电力建设，2019，40（5）：71. YANG Yinan, QI Linhai, WANG Hong. Research on generation technology of small sample data based on generative adversarial network[J]. Electric Power Construction, 2019, 40（5）: 71-77.
[27] 尤鸣宇，韩煊.基于样本扩充的小样本车牌识别[J].南京师大学报（自然科学版），2019，42（3）：1-10. YOU Mingyu, HAN Xuan. Small sample license platerecognition based on sample expansion[J]. Journal of Nanjing Normal University（Natural Science Edition）, 2019, 42（3）: 1-10.
[28] 郭清杨.基于生成对抗网络的对抗样本生成[J].现代计算机，2020（7）：24-28. GUO Qingyang. Adversarial examples generating algorithm based on generative adversarial networks[J]. Modern Computer, 2020（7）: 24-28.
[29] 郑学召，李梦涵，张嬿妮.基于随机森林算法的煤自燃温度预测模型研究[J].工矿自动化，2021，47（5）：58-64. ZHENG Xuezhao, LI Menghan, ZHANG Yanni, et al. Research on the prediction model of coal spontaneous combustion temperature based on random forest algorithm[J]. Industry and Mine Automation, 2021, 47（5）: 58-64.
-
期刊类型引用(7)
1. 崔忠麒，徐娅煊，苏皓. 基于Stacking-SHAP的煤自燃倾向性影响因素研究. 煤炭技术. 2025(01): 150-155 . 
百度学术
2. 孙吉平. 基于SF_6质量浓度变化特征的煤矿火灾状态识别分析. 山西煤炭. 2025(01): 42-49 . 百度学术
3. 曹富荣，吴学松，李军，付天予，刘佳伟，李志辉，杨小彬. 基于机器学习的多气体指标煤自燃温度预测. 煤矿安全. 2024(04): 106-113 . 本站查看
4. 樊永勇，王新瑞，张春雷. 急倾斜特厚煤层分段采空区低温氮气防灭火技术研究与实践. 能源与环保. 2024(11): 254-262 . 百度学术
5. 武泽伟，汪伟，祁云，梁然. 采空区遗煤自燃影响因素分析及风险评价. 山西大同大学学报(自然科学版). 2023(04): 116-122 . 百度学术
6. 孔彪，朱思想，胡相明，杨涛，赵旭帅，斐达特，万姝含. 基于改进鲸鱼算法优化BP神经网络的煤自燃预测研究. 矿业安全与环保. 2023(05): 30-36 . 百度学术
7. 陈鹏燕，周春山，程熙宇，田雅琪. 全物理交联Al~(3+)-CMC/MMT-PAM双网络凝胶的制备及性能. 矿业研究与开发. 2023(11): 143-149 . 百度学术
其他类型引用(2)
计量
- 文章访问数: 54
- HTML全文浏览量: 0
- PDF下载量: 16
- 被引次数: 9
下载:
