Risk Chain Mining of Hazard Sources in Metro Operation System Safety: A New Method to Mine and Control Risk for Safety Management

Abstract

With the promotion of the major strategy of national transportation power, the super-large-scale metro operation network has become an inevitable trend, and operation safety has become increasingly prominent. Metro operation dispatch logs and accident reports were taken as the research object, the hazard sources were efficiently and accurately identified, the risk chains of hazard sources were mined, and the risk evolution mechanism was revealed. Firstly, the transportation lexicon was constructed to improve the accuracy of word segmentation, the text features were extracted based on the term frequency-inverse document frequency (TF-IDF) algorithm, and the key eigenvalues were mined to identify the key hazard sources. Secondly, pattern matching was used to extract explicit causality, and the Self-Attention BiLSTM extracted implicit causality and integrated event trigger word position identification to enhance the effectiveness of implicit causality extraction. Finally, an example was given to verify the efficiency and accuracy of the model, the experiments showed that the F value of extraction effect was increased by nearly 10%, the extraction accuracy was 87.53%, the identification of operational hazard sources was more accurate, and the visualization of risk evolution law was realized.

Keywords

Urban rail transit / Operational hazards / Risk chain / Text mining / Causality extraction

References

[1] He L. Application of hazard identification and assessment grading optimization method for metro lines. Safety, 2018, 39(8): 8-11.

[2] Yang NH, Ye M, Wu AM (2017) Hazard identification and risk assessment for safe operation of modern tram. Modern Transp Technol 14(2):75–80

[3] Yang QM (2018) Research on safety risk identification and analysis of large railway passenger station system [D]. Beijing Jiaotong University, Beijing

[4] Wang J. Research on building construction safety prediction based on RS-GA-BP. J Eng Manag, 2010, 24(6): 647-651.

[5] Jia RY, Pan WW (2012) Partner selection of virtual enterprise based on rough set and genetic algorithm. J Harbin Eng Univ. 33(6):730–734

[6] Ding X, Yang X, Hu H The safety management of urban rail transit based on operation fault log. Saf Sci, 2017, 94: 10-16

[7] Zhou Z, Li C, Mi C. Exploring the potential use of near-miss information to improve construction safety performance. Sustainability, 2019, 11(5): 1264

[8] Zhang G, Thai VV, Law AWK Quantitative risk assessment of seafarers’ nonfatal injuries due to occupational accidents based on Bayesian network modeling. Risk Anal, 2020, 40(1): 8-23

[9] Hei YJ. Research on hidden danger analysis and visualization of subway construction based on text mining, 2019, Wuhan, Hubei: Huazhong University of science and technology

[10] Xu N, Ling MA, Liu Q An improved text mining approach to extract safety risk factors from construction accident reports. Saf Sci, 2021, 138(8): 105216

[11] Bugalia N, Tarani V, Kedia J, Gadekar H. Machine learning-based automated classification of worker-reported safety reports in construction. J Inf Technol Constr, 2022, 27: 926-950.

[12] Chapman CB, Cooper DF (1987) Risk analysis for large project: models method and cases. Wiley, Hoboken, pp 544–549

[13] Kangari R. Risk management perceptions and trends of US construction. J Constr Eng Manag, 1995, 121(4): 422-429

[14] Liu X Analysis of causes of major train derailment and their effect on accident rates. Transp Res Rec, 2012, 2289(1): 154-163

[15] Liu YS. Supply chain risk early warning mechanism, 2007, Beijing: China Materials Press

[16] Ma Y, Wang HL Research on project group risk chain management technology. Aerosp Manuf Technol, 2007, 6: 35-37.

[17] Wang HX, Tian YD, Yin H. Correlation analysis of external environment risk factors for high-speed railway derailment based on unstructured data. J Adv Transp, 2021, 2021(Pt.6): 6980617.1-6980617.11.

[18] Moradi R, Moradi R Integration of deep learning and Bayesian networks for condition and operation risk monitoring of complex engineering systems. Reliab Eng Syst Saf, 2022, 222: 108433

[19] Li CB, Lu GS. System dynamics model of risk element transmission in engineering projects. Syst Eng Theory Pract, 2012, 32(12): 2731-2739.

[20] Cao JM, Shen LF. Progress risk assessment of construction projects from the perspective of risk chain. J Tongji Univ, 2015, 43(03): 468-474.

[21] Li JY, Gou JQ, Mu WX Research on railway potential risk correlation reasoning based on accident chain situation. J Railw, 2017, 39(11): 8-14.

[22] Qiu GF, Wang J. Research on knowledge discovery of construction safety accidents based on concept lattice. J Saf Environ, 2019, 19(05): 1625-1630.

[23] Fu L, Wang X, Zhao H Interactions among safety risks in metro deep foundation pit projects: an association rule mining-based modeling framework. Reliab Eng Syst Saf, 2022, 221: 108381

[24] Jia X, Guo B. Reliability analysis for complex system with multi-source data integration and multi-level data transmission. Reliab Eng Syst Saf, 2022, 217: 108050

[25] Liu AH. Research on dynamic evolution model of urban disaster chain and risk assessment method of disaster chain, 2013, Changsha, Hunan: Central South University

[26] Ding X, Qin B. BUEES: a bottom-up event extraction system. Front Inf Technol Electron Eng, 2015, 16(7): 541-552

[27] Liu ZT, Huang ML Research on event oriented ontology. Comput Sci, 2009, 36(11): 189-192.

[28] Che W, Feng Y, Qin L, et al. N-LTP (2021) An Open-source neural language technology platform for Chinese[C]. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. pp 42-49

[29] Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. Adv Neural Inf Process Syst 2017(12):5998–6008

[30] Chen HS, Chen JJ. Construction and optimization of Internet of things intrusion detection classification model based on RESNET and bidirectional LSTM fusion. J Hunan Univ, 2020, 47(8): 1-8.

Funding

The Shanghai Philosophy and Social Science Planning Project(2022BGL001)