|本期目录/Table of Contents|

[1]孟向学,邹平,陈璐,等.基于ETO-RF的尾矿库溃坝强度评估*[J].中国安全生产科学技术,2025,21(8):71-76.[doi:10.11731/j.issn.1673-193x.2025.08.009]
　MENG Xiangxue,ZOU Ping,CHEN Lu,et al.Assessment of tailings dam failure intensity based on ETO-RF[J].Journal of Safety Science and Technology,2025,21(8):71-76.[doi:10.11731/j.issn.1673-193x.2025.08.009]
点击复制

基于ETO-RF的尾矿库溃坝强度评估*

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
21
期数:
2025年8期
页码:
71-76
栏目:
职业安全卫生管理与技术
出版日期:
2025-08-30

文章信息/Info

Title:
Assessment of tailings dam failure intensity based on ETO-RF
文章编号:
1673-193X(2025)-08-0071-06
作者:
孟向学; 邹平; 陈璐; 丁文龙; 戴勇; 黄帅
（1.穆索诺伊矿业简易股份有限公司，卢阿拉巴 科卢韦齐 1004131，刚果(金)；
2.紫金（长沙）工程技术有限公司，湖南 长沙 410000；
3.中南大学 资源与安全工程学院，湖南 长沙 410000）
Author(s):
MENG Xiangxue;  ZOU Ping;  CHEN Lu;  DING Wenlong;  DAI Yong;  HUANG Shuai
（1.La Compagnie Miniere De Musonoie Global Societe Paractions Simplifiee (COMMUS SAS),Kolwezi Lualaba 1004131,Democratic Republic of Congo;
2.Zijin (Changsha) Engineering Technology Co.,Ltd.,Changsha Hunan 410000,China;
3.School of Resources and Safety Engineering,Central South University,Changsha Hunan 410000,China）
关键词:
尾矿库溃坝; 尾砂下泄量; 指数三角优化算法; 随机森林; 预测系统
Keywords:
tailings dam failure;  tailings discharge volume;  exponential-trigonometric optimization;  random forest;  prediction system
分类号:
TV122+.4;X936
DOI:
10.11731/j.issn.1673-193x.2025.08.009
文献标志码:
A
摘要:
为准确评估尾矿库溃坝强度，提出1种基于指数三角优化算法（exponential trigonometric optimization,ETO）和随机森林（random forest，RF）的ETO-RF模型，通过优化RF模型的超参数，并结合美国公众参与科学中心（Centre for Science in Public Participation,CSP2）提供的全球尾矿库溃坝数据库，构建ETO-RF模型及可视化评估系统。研究结果表明：与前人提出的经验公式相比，ETO-RF模型在均方根误差（RMSE）、均方误差（MSE）和平均绝对误差（MAE）上分别降低0.320，0.564和0.223，显著提升预测精度；开发的可视化系统为用户提供便捷的操作界面，增强模型的工程实用性。研究结果可为尾矿库安全管理提供科学根据，并为类似工程风险评估提供参考。
Abstract:
In order to accurately assess tailings dam failure intensity,this study proposes an ETO-RF model based on the exponential-trigonometric optimization (ETO) algorithm and random forest (RF).By optimizing hyperparameters of the RF model and utilizing the global tailings dam failure database provided by the Centre for Science in Public Participation (CSP2),this study developed an ETO-RF model and implemented a visual assessment system.The results demonstrate that compared with existing empirical formulas,the ETO-RF model reduces the root mean square error (RMSE),mean square error (MSE),and mean absolute error (MAE) by 0.320,0.564,and 0.223 respectively,significantly improving prediction accuracy.Additionally,the developed visualization system provides a user-friendly interface,enhancing the model’s engineering applicability.These findings offer a scientific basis for tailings dam safety management and provide a valuable reference for risk assessment in similar engineering projects.

参考文献/References:

［1］ROTTAL H S,ALCNTARAE,PARK E,et al.The 2019 Brumadinho tailings dam collapse:possible cause and impacts of the worst human and environmental disaster in Brazil［J］.International Journal of Applied Earth Observation and Geoinformation,2020,90:102119.
［2］LUMBROSO D,DAVISON M,BODY R,et al.Modelling the Brumadinho tailings dam failure,the subsequent loss of life and how it could have been reduced［J］.Natural Hazards and Earth System Sciences,2021,21(1):21-37.
［3］CLARKSON L,WILLIAMS D.Critical review of tailings dam monitoring best practice［J］.International Journal of Mining,Reclamation and Environment,2020,34(2):119-148.
［4］柯丽华,张莹,李全明,等.基于Spearman-EAHP变权灰云聚类模型的尾矿库安全评价 ［J］.矿冶工程,2022,42(1):5-9. KE Lihua,ZHANG Ying,LI Quanming,et al.Safety evaluation of tailings pond with grey cloud clustering model based on Spearman-EAHP variable weight ［J］.Mining and Metallurgical Engineering,2022,42(1):5-9.
［5］沈鸿杰,徐力群,刘子茜.改进DB-IWHR模型及其在尾矿库溃坝影响分析中的应用 ［J］.水利水电科技进展,2022,42(5):64-70. SHEN Hongjie,XU Liqun,LIU Ziqian.Improved DB-IWHR model and its application in influence analysis of tailings dam break ［J］.Advances inScience and Technology of Water Resources,2022,42(5):64-70.
［6］毛翼飞,徐力群,史亚旋,等.基于分段模型法的尾矿库溃坝影响预测分析 ［J］.水电能源科学,2019,37(11):100-103,14. MA Yifei,XU Liqun,SHI Yaxuan,et al.Influence predictive analysis of tailings dam-break based on segmentation model method ［J］.Water Resources and Power,2019,37(11):100-103,14.
［7］付搏涛,李钢,张红,等.基于GDEM-PDyna的尾矿库溃坝三维数值模拟分析研究 ［J］.中国安全生产科学技术,2023,19(2):71-77. FU Botao,LI Gang,ZHANG Hong,et al.Three-dimensional numerical simulation analysis of tailings dam break based on GDEM-PDyna［J］.Journal of Safety Science and Technology,2023,19(2):71-77.
［8］杨春和,张超,马昌坤,等.高应力条件下尾矿破碎特性及坝体稳定性研究 ［J］.中国安全生产科学技术,2022,18(2):20-26,2. YANG Chunhe,ZHANG Chao,MA Changkun,et al.Study on tailings breakage characteristics and dam stability under high stress conditions［J］.Journal of Safety Science and Technology,2022,18(2):20-26,2.
［9］CONCHA LARRAURI P,LALL U.Tailings dams failures:updated statistical model for discharge volume and runout［J］.Environments,2018,5(2):28.
［10］RICO M,BENITO G,DIEZ-HERRERO A.Floods from tailings dam failures［J］.Journal of Hazardous Materials,2008,154(1-3):79-87.
［11］PICIULLO L,STORRSTEN E B,LIU Z,et al.A new look at the statistics of tailings dam failures［J］.Engineering Geology,2022,303:106657.
［12］BREIMAN L.Random forests［J］.Machine Learning,2001,45:5-32.
［13］LUAN T M,KHATIR S,TRAN M T,et al.Exponential-trigonometric optimization algorithm for solving complicated engineering problems［J］.Computer Methods in Applied Mechanics and Engineering,2024,432:117411.
［14］邹平,王亮,戴勇,等.基于SSA-XGBoost的爆破振动预测系统的构建与应用 ［J］.爆破,2023,40(3):199-205. ZOU Ping,WANG Liang,DAI Yong,et al.Establishment and application of blasting vibration prediction system based on ssa-xgboost ［J］.Blasting,2023,40(3):199-205.
［15］马斌,张晨晨,赵怡晴,等.基于EEMD-LSTM模型的尾矿库风险预测模型研究 ［J］.中国安全生产科学技术,2022,18(12):116-121. MA Bin,ZHANG Chenchen,ZHAO Yiqing,et al.Rsearch on risk prediction model of tailings pond based on EEMD-LSTM model ［J］.Journal of Safety Science and Technology,2022,18(12):116-121.

相似文献/References:

[1]梁玉霞,覃璇,李振涛.“头顶库”风险量化分析模型研究及实例应用[J].中国安全生产科学技术,2019,15(6):120.[doi:10.11731/j.issn.1673-193x.2019.06.019]
　LIANG Yuxia,QIN Xuan,LI Zhentao.Research on risk quantitative analysis model of “overhead tailings pond” and its application[J].Journal of Safety Science and Technology,2019,15(8):120.[doi:10.11731/j.issn.1673-193x.2019.06.019]

备注/Memo

备注/Memo:
收稿日期： 2025-05-31
* 基金项目： 国家重点研发计划项目(2022YFC2903904)
作者简介： 孟向学，本科，工程师，主要研究方向为露天矿山采矿技术与安全。
通信作者： 邹平，博士，正高级工程师，主要研究方向为矿山开采技术与安全。
更新日期/Last Update: 2025-09-01