| 241 | 0 | 193 |
| 下载次数 | 被引频次 | 阅读次数 |
尾矿库失稳可能引发严重的安全事故，及时掌握坝体位移变化趋势并设定科学预警阈值，对风险防控具有重要意义。研究提出一种结合灰色关联分析、带外生变量的神经基扩展分析模型(Neural Basis Expansion Analysis with Exogenous Variables, N-BEATSx)深度学习预测和云模型预警的尾矿坝位移预警方法，通过分析辽宁省某尾矿库的数据，发现时间和库水压力与坝体位移的灰色关联度最高，反映了现实物理环境是坝体位移的最大影响因素。基于N-BEATSx 7 d位移预测结果，发现水平位移和沉降量分别平均提升约28.5%和9.6%,综合指标提升约19.0%。此外，基于云模型的3E原则划定蓝-黄-橙-红四级预警阈值，实现了预测结果向风险等级的量化转化。研究结果表明，该方法不仅提高了尾矿坝位移预测精度，也建立了可量化的风险预警分级阈值，为尾矿坝安全监测与预警提供了有效的技术支撑。
Abstract：This paper proposes a displacement early warning method for tailings dams that integrates grey relational analysis, the Neural Basis Expansion Analysis for Time Series with Exogenous Variables(N-BEATSx) deep learning model, and a cloud model-based risk classification framework. Grey relational analysis is employed as a preliminary step to identify the dominant factors affecting dam deformation. The results indicate that time and ponding water pressure have the strongest influences, with correlation coefficients of 0.799 and 0.703, respectively. These reflect the combined effects of material creep, consolidation, and hydrostatic loading. Building on this, the N-BEATSx model is utilized to predict seven-day-ahead displacements using monitoring data from a tailings dam in Liaoning Province, with separate evaluations for horizontal displacement and settlement. The predictive performance shows that N-BEATSx significantly outperforms the baseline N-BEATS model, as the Root Mean Square Error(RMSE) and Mean Absolute Error(MAE) for horizontal displacement forecasts reach 0.423 and 0.361, respectively, while settlement forecasts achieve RMSE and MAE values of 0.398 and 0.318. Compared to Neural Basis Expansion Analysis for Time Series(N-BEATS), the N-BEATSx model improves prediction accuracy by an average of approximately 19%, demonstrating its superior ability to capture nonlinear temporal dependencies and short-term fluctuation patterns in dam deformation. To translate numerical forecasts into actionable early warning signals, a cloud model is introduced to establish quantitative thresholds and classify displacement predictions into four hierarchical risk levels. Following the 3E principle, blue, yellow, orange, and red warning grades are defined, enabling a direct mapping of predicted values to discrete safety states and transforming model outputs into operational risk indicators. This proposed method achieves both high-precision forecasting and risk quantification, providing an effective technical pathway for linking predictive modeling with engineering decision-making. The results confirm that this integrated approach not only enhances the reliability of displacement forecasting but also delivers a transparent and structured framework for risk-based early warning, offering valuable support for the safe operation and management of tailings dams.
[1] Islam K,Murakami S.Global-scale impact analysis of mine tailings dam failures:1915-2020[J].Global Environmental Change,2021,70:102361.
[2] Tian Sen,Dai Xuanyan,Wang Guangjin,et al.Formation and evolution characteristics of dam breach and tailings flow from dam failure:an experimental study[J].Natural Hazards,2021,107(2):1621-1638.
[3] Ma Guotao.Quantitative assessment method study based on weakness theory of dam failure risks in tailings dam[J].Procedia Engineering,2011,26:1827-1834.
[4] Buch A C,Sims D B,De Ramos L M,et al.Assessment of environmental pollution and human health risks of mine tailings in soil:after dam failure of the Córrego do Feijão Mine (in Brumadinho,Brazil)[J].Environmental Geochemistry and Health,2024,46(3):72.
[5] 王昆，杨鹏，Karen H E,等.尾矿库溃坝灾害防控现状及发展[J].工程科学学报，2018,40(5):526-539.Wang Kun,Yang Peng,Karen H E,et al.Status and development of tailings dam failure prevention and control[J].Journal of Engineering Science,2018,40(5):526-539.
[6] 袁利伟，张舒寒，李延林，等.结合SBAS-InSAR与IPSO-CNN-LSTM优化模型的尾矿库监测与预测研究[J/OL].安全与环境学报：1-12[2026-01-26].https://doi.org/10.13637/j.issn.1009-6094.2025.0619.Yuan Liwei,Zhang Shuhan,Li Yanlin,et al.Research on monitoring and prediction of tailings pond combining SBAS-InSAR and IPSO-CNN-LSTM optimized model[J/OL].Journal of Safety and Environment:1-12[2026-01-26].https://doi.org/10.13637/j.issn.1009-6094.2025.0619.
[7] 唐宇峰，何俚秋，胡光忠.尾矿坝位移实时预测在线深度学习方法研究[J/OL].安全与环境学报：1-7[2026-01-26].https://doi.org/10.13637/j.issn.1009-6094.2025.0560.Tang Yufeng,He Liqiu,Hu Guangzhong.Research on online deep learning method for real-time prediction of tailings dam displacement[J/OL].Journal of Safety and Environment:1-7[2026-01-26].https://doi.org/10.13637/j.issn.1009-6094.2025.0560.
[8] Ribeiro M T,Singh S,Guestrin C.“Why should I trust you?” Explaining the predictions of any classifier[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,August 13-17,2016,San Francisco,California,USA.New York:ACM,2016:1135-1144.
[9] Olivares K G,Challu C,Marcjasz G,et al.Neural basis expansion analysis with exogenous variables:forecasting electricity prices with NBEATSx[J].International Journal of Forecasting,2023,39(2):884-900.
[10] Wang Guoyin,Xu Changlin,Li Deyi.Generic normal cloud model[J].Information Sciences,2014,280:1-15.
[11] 李德毅，孟海军，史雪梅.隶属云和隶属云发生器[J].计算机研究与发展，1995,32(6):15-20.Li Deyi,Meng Haijun,Shi Xuemei.Membership cloud and membership cloud generator[J].Journal of Computer Research and Development,1995,32(6):15-20.
[12] Oreshkin B N,Carpov D,Chapados N,et al.N-BEATS:Neural basis expansion analysis for interpretable time series forecasting[C]//Proceedings of the 8th International Conference on Learning Representations,April 26-May 1,2020,Addis Ababa,Ethiopia.Ethiopia:OpenReview.net,2020:1-15.
[13] 范茜茜，王国强，罗贺，等.基于N-BEATS与辅助编码器的短期电力负荷预测[J].电网技术，2024,48(4):1612-1621.Fan Qianqian,Wang Guoqiang,Luo He,et al.Short-term power load forecasting based on N-BEATS and auxiliary encoder[J].Power System Technology,2024,48(4):1612-1621.
[14] 吴雷，杜文研，林超然.基于专利数据应用LDA和N-BEATS组合方法的技术主题预测研究[J].数字图书馆论坛，2023,19(11):62-73.Wu Lei,Du Wenyan,Lin Chaoran.Research on technology topic prediction using LDA and N-BEATS combined method based on patent data[J].Digital Library Forum,2023,19(11):62-73.
[15] 李荟，朱万成，徐晓冬，等.露天矿山地表变形智能预测与灾害风险评价研究现状与展望[J].矿业科学学报，2024,9(6):837-848.Li Hui,Zhu Wancheng,Xu Xiaodong,et al.Research status and prospect of intelligent prediction of surface deformation and disaster risk assessment in open-pit mines[J].Journal of Mining Science,2024,9(6):837-848.
[16] Morgenstern N R.Geotechnical risk,regulation and public policy[J].Soils and Rocks,2018,41(2):115-127.
[17] 王仪心，米占宽.尾矿坝溃坝安全风险分析评价方法[J].金属矿山，2019,48(6):184-188.Wang Yixin,Mi Zhankuan.Safety risk analysis and evaluation method for tailings dam failure[J].Metal Mine,2019,48(6):184-188.
[18] Chandola V,Banerjee A,Kumar V.Anomaly detection:a survey[J].ACM Computing Surveys,2009,41(3):1-58.
[19] Savitzky A,Golay M J E.Smoothing and differentiation of data by simplified least squares procedures[J].Analytical Chemistry,1964,36(8):1627-1639.
[20] Deng Julong.Control problems of grey systems[J].Systems & Control Letters,1982,1(5):288-294.
[21] Wang Xuanzheng,Li Changwang,Yi Chengqi,et al.EcoForecast:an interpretable data-driven approach for short-term macroeconomic forecasting using N-BEATS neural network[J].Engineering Applications of Artificial Intelligence,2022,114:105072.
[22] Kasprzyk M,Pełka P,Oreshkin B N,et al.Enhanced N-BEATS for mid-term electricity demand forecasting[J].Applied Soft Computing,2025,182:113575.
[23] Apte M,Haribhakta Y V.Advancing financial forecasting:a comparative analysis of neural forecasting models N-HITS[C]//Information Systems for Intelligent Systems:Proceedings of ISBM 2024,Volume 5,May 23-25,2024,Bangkok,Thailand.Singapore:Springer,2025:199-210.
[24] Souto H G,Moradi A.Introducing NBEATSx to realized volatility forecasting[J].Expert Systems with Applications,2024,242:122802.
[25] Hu Shaohua,Qu Meixian,Yuan Youcui,et al.Coupling cloud theory and concept hierarchy construction early warning thresholds for deformation safety of tailings dam[J].Natural Hazards,2024,120(9):8827-8849.
[26] Yang Guang,Sun Jin,Zhang Jianwei,et al.Research on temperature control index for high concrete dams based on information entropy and cloud model from the view of spatial field[J].Water,2023,15(22):4023.
[27] Liang Xiaobin,Liang Wei,Zhang Laibin,et al.Risk assessment for long-distance gas pipelines in coal mine gobs based on structure entropy weight method and multi-step backward cloud transformation algorithm based on sampling with replacement[J].Journal of Cleaner Production,2019,227:218-228.
[28] GB 51108—2015 尾矿库在线安全监测系统工程技术规范[S].GB 51108—2015 Technical code for tailings pond on-line safety monitoring system engineering[S].
基本信息:
DOI：10.13637/j.issn.1009-6094.2025.1215
中图分类号:TP18;TD926.4
引用信息:
[1]杨斌,秦树豪,杨玉好,等.基于深度学习与云模型的尾矿坝位移预警模型构建[J].安全与环境学报,2026,26(07):2573-2585.DOI:10.13637/j.issn.1009-6094.2025.1215.
基金信息:
辽宁省教育厅高校基本科研项目(LJ212410146040,LJ222410146057); 辽宁省科技计划联合计划(2025-MSLH-350)
2026-02-03
2026-02-03
2026-02-03