A data-driven approach to coal mine safety performance using swarm intelligence and ensemble learning

  • Yejiao Liu orcid

    School of Safety and Emergency Management, Inner Mongolia University of Science and Technology, Baotou 014010, China; School of Mining and Coal, Inner Mongolia University of Science and Technology, Baotou 014010, China; Key Laboratory of Mining Engineering of Inner Mongolia Autonomous Region, Inner Mongolia University of Science and Technology, Baotou 014010, China; Inner Mongolia Autonomous Region Coal Safety Mining and Utilization Engineering Technology Research Center, Inner Mongolia University of Science and Technology, Baotou 014010, China; Inner Mongolia Coal Green Mining and Green Utilization Collaborative Innovation Center, Inner Mongolia University of Science and Technology,Baotou 014010, China
  • Jinliang Li orcid

    School of Safety and Emergency Management, Inner Mongolia University of Science and Technology, Baotou 014010, China; School of Mining and Coal, Inner Mongolia University of Science and Technology, Baotou 014010, China
  • Ting Teng

    Xinmeiguang (Haining) Electronic Materials Co., Ltd., Jiaxing 314400, China
  • Wenjie Yan

    School of Safety and Emergency Management, Inner Mongolia University of Science and Technology, Baotou 014010, China; School of Mining and Coal, Inner Mongolia University of Science and Technology, Baotou 014010, China
  • Huixin Wang

    School of Safety and Emergency Management, Inner Mongolia University of Science and Technology, Baotou 014010, China; School of Mining and Coal, Inner Mongolia University of Science and Technology, Baotou 014010, China
  • Dongqiang Cao

    School of Safety and Emergency Management, Inner Mongolia University of Science and Technology, Baotou 014010, China; School of Mining and Coal, Inner Mongolia University of Science and Technology, Baotou 014010, China
  • Fu Gao

    School of Safety and Emergency Management, Inner Mongolia University of Science and Technology, Baotou 014010, China; School of Mining and Coal, Inner Mongolia University of Science and Technology, Baotou 014010, China
  • Fengyi Jiang

    School of Safety and Emergency Management, Inner Mongolia University of Science and Technology, Baotou 014010, China; School of Mining and Coal, Inner Mongolia University of Science and Technology, Baotou 014010, China
Article ID: 4235
DOI: https://doi.org/10.59400/adecp4235
Keywords: coal mine safety performance; random forest; ANP-TOPSIS; particle swarm optimization; assessment

Abstract

At present, there are some shortcomings in the dynamic adaptability and subjectivity of coal mine safety performance evaluation, and it is difficult to realize the short-term safety performance evaluation with full staff participation. In this study, based on the Analytic Network Process-Technique for Order Preference by Similarity to an Ideal Solution (ANP-TOPSIS), a coal mine safety performance evaluation index system was constructed, and the evaluation index was optimized by a particle swarm optimization algorithm to improve the accuracy of dynamic index weight allocation. Emotional processing analysis technology is introduced, and the survey evaluation form is designed to quantify the subjective emotional tendency. Statistical methods such as the intra-group correlation coefficient, consistency test and regression model are used to improve the reliability of expert scoring data and quantitatively analyze individual subjective differences. Using the random forest classification method, combined with the term frequency-inverse document frequency (TF-IDF) to vectorize the text data, a bottom-up dynamic evaluation method of employee safety performance based on machine learning is established. The random forest model achieved an average F1-score of 0.929, with all six safety dimensions scoring above 0.8. The example shows that the short-process long-period safety performance evaluation based on ANP-TOPSIS-PSO, and a random forest model can accurately describe the coal mine safety appearance and provide scientific decision support for improving the coal mine safety performance level.

Article Status
In press
How to Cite
Liu, Y., Li, J., Teng, T., Yan, W., Wang, H., Cao, D., Gao, F., & Jiang, F. (2026). A data-driven approach to coal mine safety performance using swarm intelligence and ensemble learning. Advances in Differential Equations and Control Processes, 33(2). https://doi.org/10.59400/adecp4235
Issue
Vol. 33 No. 2 (2026): In Progress
Section
Articles

Copyright (c) 2026 Yejiao Liu, Jinliang Li, Ting Teng, Wenjie Yan, Huixin Wang, Dongqiang Cao, Fu Gao, Fengyi Jiang

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

References

[1]Jiang L, Zhang Y, Li F. A multilevel model of autonomous safety motivation and safety performance. Advances in Psychological Science. 2019; 27(7): 1141–1152. doi: 10.3724/SP.J.1042.2019.01141

[2]Ghahramani A, Ebrahimi M, Hajaghazadeh M. Development and psychometric evaluation of an occupational health and safety performance tool for manufacturing companies. Heliyon. 2023; 9(6): e17343. doi: 10.1016/j.heliyon.2023.e17343

[3]Khalid U, Sagoo A, Benachir M. Safety Management System (SMS) framework development – Mitigating the critical safety factors affecting Health and Safety performance in construction projects. Safety Science. 2021; 143: 105402. doi: 10.1016/j.ssci.2021.105402

[4]Hadjimanolis A, Boustras G, Economides A, et al. Work attitudes and safety performance in micro-firms – Results from a nationwide survey: (the opinion of the employees). Safety Science. 2015; 80: 135–143. doi: 10.1016/j.ssci.2015.07.026

[5]Cheng D, Hun B, Wang Y. Coal mine safety performance management based on the Objective and Key Results method. Safety in Coal Mines. 2019; (7): 285–288. (in Chinese)

[6]Li Q. Study on the construction of coal mine safety production management system based on the concept of risk pre-control. Inner Mongolia Coal Economy. 2025; (16): 85–87. doi: 10.13487/j.cnki.imce.027117 (in Chinese)

[7]Xiao Z, Liu W, Yang J, et al. Influence of psychological states on train drivers' safety performance. China Safety Science Journal. 2022; 32(2): 13–18. doi: 10.16265/j.cnki.issn1003-3033.2022.S2.0202 (in Chinese)

[8]Sang L, Li J. A cross-level study on influence of team relationship conflict on safety performance of miners. China Safety Science Journal. 2022; 32(2): 51–58. doi: 10.16265/j.cnki.issn1003-3033.2022.02.008 (in Chinese)

[9]Liu YJ, Tian ZC, Huang DM. Application of BP Neural Network in Coalmine Safety Management Performance Evaluation. Advanced Materials Research. 2013; 734–737: 2925–2929. doi: 10.4028/www.scientific.net/AMR.734-737.2925

[10]Meng Q, Ma X, Zhou Y. Application of the PSO-SVM model for coal mine safety assessment. In: Proceedings of the 2012 8th International Conference on Natural Computation; 29–31 May 2012; Chongqing, China. pp. 393–397. doi: 10.1109/ICNC.2012.6234669

[11]Wang Y, Shi Y, Hao J. Safety Evaluation and Simulation Research of Filling Mining Mine—A Case Study of Jisuo Coal Mine. Sustainability. 2023; 15(13): 10156. doi: 10.3390/su151310156

[12]Di Gravio G, Patriarca R, Mancini M, et al. Overall safety performance of the Air Traffic Management system: The Italian ANSP’s experience on APF. Research in Transportation Business & Management. 2016; 20: 3–12. doi: 10.1016/j.rtbm.2016.03.001

[13]Singh A, Misra SC. Safety performance & evaluation framework in Indian construction industry. Safety Science. 2021; 134: 105023. doi: 10.1016/j.ssci.2020.105023

[14]So J, Hoffmann S, Lee J, et al. A Prediction Accuracy-Practicality Tradeoff Analysis of the State-of-the-art Safety Performance Assessment Methods. Transportation Research Procedia. 2016; 15: 794–805. doi: 10.1016/j.trpro.2016.06.066

[15]Li S, You M, Li D, et al. Identifying coal mine safety production risk factors by employing text mining and Bayesian network techniques. Process Safety and Environmental Protection. 2022; 162: 1067–1081. doi: 10.1016/j.psep.2022.04.054

[16]Liu Y, Yan W, Gao F, et al. Empirical study on safety performance evaluation of non-coal underground mines. Journal of Physics: Conference Series. 2025; 2969(1): 012013. doi: 10.1088/1742-6596/2969/1/012013

[17]Liu Y, Teng T, Duan Z, et al. Research on the Construction Method of Double Prevention Mechanism in Chinese Heating Enterprises Based on Bidirectional Dynamic Risk-Hidden Danger Transmission. Sustainability. 2023; 15(3): 2849. doi: 10.3390/su15032849

[18]Yao Y, Kou J, Zhang M. Risk assessment of "one-ventilation and three-prevention" in coal mine based on game theory combination weighting-TOPSIS. Mining Safety & Environmental Protection. 2024; 51(6): 71–78. doi: 10.19835/j.issn.1008-4495.20230694 (in Chinese)

[19]Liu X, Liu H, Wan Z, et al. The comprehensive evaluation of coordinated coal-water development based on analytic hierarchy process fuzzy. Earth Science Informatics. 2021; 14(1): 311–320. doi: 10.1007/s12145-020-00523-z

[20]Diao Z, Qi J, Huang J. Distribution characteristics of bacterial survival rate in bioaerosols near the coast of Qingdao and random forest regression analysis of its influencing factors. Periodical of Ocean University of China (Natural Science Edition). 2025; 55(8): 116–127. doi: 10.16441/j.cnki.hdxb.20240191 (in Chinese)

[21]Chen C, Tang J, Li J, et al. A systematic review of safety risk assessment research in China. Journal of Safety Science and Resilience. 2025; 6(1): 58–69. doi: 10.1016/j.jnlssr.2024.06.012

[22]Liu R, Liu HC, Shi H, et al. Occupational health and safety risk assessment: A systematic literature review of models, methods, and applications. Safety Science. 2023; 160: 106050. doi: 10.1016/j.ssci.2022.106050

[23]Chellappa V, Ginda G. Application of multiple-criteria decision making methods for construction safety research. Proceedings of the Institution of Civil Engineers - Management, Procurement and Law. 2024; 177(3): 127–136. doi: 10.1680/jmapl.23.00006

[24]Krasuski A, Zimny M, Hostikka S, et al. Risk-aware decision making in the safety investments - Application of stochastic simulations and judgment value method. Fire Safety Journal. 2022; 127: 103491. doi: 10.1016/j.firesaf.2021.103491

[25]Asad MM, Hassan RB, Sherwani F, et al. Design and development of a novel knowledge-based decision support system for industrial safety management at drilling process: HAZFO Expert 1.0. Journal of Engineering, Design and Technology. 2019; 17(4): 705–718. doi: 10.1108/JEDT-09-2018-0167

[26]Simanaviciene R, Liaudanskiene R, Ustinovichius L. Assessing reliability of design, construction, and safety related decisions. Automation in Construction. 2014; 39: 47–58. doi: 10.1016/j.autcon.2013.11.008

[27]Han Y, Shen J, Zhu X, et al. Two-stage propagation analysis of safety risks in complex underground engineering: An integrated modeling framework. Reliability Engineering & System Safety. 2025; 261: 111081. doi: 10.1016/j.ress.2025.111081

[28]Jiskani IM, Han S, Rehman AU, et al. An Integrated Entropy Weight and Grey Clustering Method–Based Evaluation to Improve Safety in Mines. Mining, Metallurgy & Exploration, 2021, 38: 1773–1787. doi: https://doi.org/10.1007/s42461-021-00444-5

[29]Liu H, Zhang Z, Dong J, et al. A review of positioning technologies for personnel and equipment in underground mines. International Journal of Digital Earth. 2025; 18(1). doi: https://doi.org/10.1080/17538947.2025.2506493

[30]Miao D, Lv Y, Yu K, et al. Research on coal mine hidden danger analysis and risk early warning technology based on data mining in China. Process Safety and Environmental Protection. 2023; 171: 1–17. doi: https://doi.org/10.1016/j.psep.2022.12.077

[31]Zhu Y, Li C, Li L, et al. Dynamic assessment and system dynamics simulation of safety risk in whole life cycle of coal mine. Environmental Science and Pollution Research. 2023; 30: 64154–64167. doi: https://doi.org/10.1007/s11356-023-26958-7

[32]Darko A, Chan APC, Ameyaw EE, et al. Review of application of analytic hierarchy process (AHP) in construction. International Journal of Construction Management. 2019; 19(5): 436–452. doi: https://doi.org/10.1080/15623599.2018.1452098

[33]Liu S, Chan FTS, Chung SH. A study of distribution center location based on the rough sets and interactive multi-objective fuzzy decision theory. Robotics and Computer-Integrated Manufacturing. 2011; 27(2): 426–433. doi: 10.1016/j.rcim.2010.09.003

[34]Guo YQ, Zhang Y, Xu ZD, et al. Single-Frequency GNSS Integer Ambiguity Solving Based on Adaptive Genetic Particle Swarm Optimization Algorithm. Sensors. 2023; 23(23): 9353. doi: 10.3390/s23239353

[35]Chen L, Ma M, Sun L. Heuristic swarm intelligent optimization algorithm for path planning of agricultural product logistics distribution. Journal of Intelligent & Fuzzy Systems. 2019; 37(4): 4697–4703. doi: 10.3233/JIFS-179304

[36]Salman HA, Kalakech A, Steiti A. Random Forest Algorithm Overview. Babylonian Journal of Machine Learning. 2024; 2024: 69–79. doi: https://doi.org/10.58496/BJML/2024/007

[37]Ramalingam S, Baskaran K. An efficient data prediction model using hybrid Harris Hawk Optimization with random forest algorithm in wireless sensor network. Journal of Intelligent & Fuzzy Systems. 2021; 40(3): 5171–5195. doi: 10.3233/JIFS-201921

[38]Harbin Institute of Technology. Harbin Institute of Technology Stop Word List. Harbin Institute of Technology; 2024. Available online: https://gitcode.com/open-source-toolkit/63e0e

[39]Aizawa A. An information-theoretic perspective of tf–idf measures. Information Processing & Management. 2003; 39(1): 45–65. doi: 10.1016/S0306-4573(02)00021-3