Bayesian network-based approach for dam safety diagnosis

Abstract

Certain frontline dam safety management personnel lack the ability to diagnose dam hazard issues and often find it difficult to identify potential risks in practice. Existing causal analysis methods for dam safety diagnosis struggle to provide specific reasoning paths and quantify risk probabilities. To address this gap, this study proposes a dam safety diagnostic method based on Bayesian networks (BNs). First, historical cases of dam safety hazards were collected and classified to extract various types of hazard issues, abnormal manifestations, and underlying causes, which were used as nodes within the BN. Correlation analysis was then performed to identify relationships among the nodes, enabling the construction of directed edges that form the BN structure. The degree centrality algorithm was employed to analyze the prior probabilities of parent nodes, while Bayes’ theorem was applied to calculate the conditional probabilities of the child nodes, generating conditional probability tables for all nodes within the network. Using the BN’s posterior probability inference method, the probabilities of hidden hazards in a target dam were calculated, facilitating accurate diagnosis and root cause tracing of potential risks. Finally, a case study involving a hidden hazard in a domestic earth-rock dam was used to validate the proposed method. The results demonstrate that the method efficiently utilizes a large number of scattered dam hazard cases, is less affected by subjective factors, provides clear reasoning links and risk probabilities, and can accurately identify dam hazard issues and trace their root causes, offering technical support for dam operation and safety management personnel.

Keywords

Dam safety / Bayesian network / Hidden hazards / Probabilistic diagnosis / Risk assessment

Funding

This research was funded by the China Postdoctoral Science Foundation (grant number: 2023M733315) and the National Key Research and Development Program of China (grant number: 2021YFC3090101). This article is also based on a research project supported by the Huanghe Company, titled “Research and Application of Key Technologies for Intelligent Online Monitoring of Dam Operation Safety in Hydropower Stations of Huanghe Company” (grant number: HGS-KJ/CX-2024-10).

Conflict of interest

The authors declare that they have no competing interests.

References

[1] Jiang, ZX, He, JP. Method of fusion diagnosis for dam service status based on joint distribution function of multiple points. Math Probl Eng. 2016;S2016:9049260. doi: 10.1155/2016/9049260

[2] Su, HZ, Wen, ZP, Sun, XR, Yan, X. Multisource information fusion-based approach diagnosing structural behavior of dam engineering. Struct Control Health Monit. 2018; 25(2):e2073. doi: 10.1002/stc.2073

[3] Xu, Y, Zhang, LM, Jia, JS. Diagnosis of embankment dam distresses using Bayesian networks. Part II. Diagnosis of a specific distressed dam. Canad Geotech J. 2011; 48(11):1645-1657. doi: 10.1139/T11-070.

[4] Dong, K, Mi, ZK, Yang, DW. Comprehensive diagnosis method of the health of tailings dams based on dynamic weight and quantitative index. Sustainability. 2022; 14(5):3068. doi: 10.3390/su14053068

[5] Jiang, ZX, Wu, B, Chen, H. Dam health diagnosis model based on cumulative distribution function. Water Resour Manag. 2023; 37(11):4293-4308. doi: 10.1007/s11269-023-03553-6

[6] Zhang, LM, Xu, Y, Jia, JS, Zhao, C. Diagnosis of embankment dam distresses using Bayesian networks. Part I. Global-level characteristics based on a dam distress database. Canad Geotechn J. 2011; 48(11):1630-1644. doi: 10.1139/T11-069

[7] Garg, A, Kaur, A, Dangi, H. Outsourcing of fire inspection services: An analytical approach. Asian J Water Environ Pollut. 2024; 21(6):189-194. doi: 10.3233/ajw240086

[8] Wen, LF, Yang, Y, Li, YL, et al. Comprehensive evaluation method for the concrete-face rockfill dams behavior based on the fuzzy recognition model. J Perform Constructed Facil. 2022; 36(3):04022021. doi: 10.1061/(ASCE)CF.1943-5509.0001734

[9] Sonsare, PM, Khedgaonkar, R, Singh, K, et al. Environmental applications of molecular graph learning: Graph neural network based prediction of partition coefficients. Asian J Water Environ Pollut. 2025; 22(3):88-103. doi: 10.36922/ajwep025070041

[10] Wang, F, Zhong, DH, Yan, YL, Ren, B, Wu, BP. Rockfill dam compaction quality evaluation based on cloud-fuzzy model. J Zhejiang Univ Sci A. 2018; 19(4):289-303. doi: 10.1631/jzus.a1600753

[11] Abu-Afifeh, Q, Rahbeh, M, Al-Afeshat, A, et al. Dam sustainability’s interdependency with climate change and dam failure drivers. Sustainability. 2023; 15(23):16239. doi: 10.3390/su152316239

[12] Lv, ZJ, Li, JJ, He, GJ. Hazard assessment of concrete dam cracks based on variable fuzzy sets and the modified analytic hierarchy process. Arab J Sci Eng. 2023; 48(10):13165-13178. doi: 10.1007/s13369-023-07668-1

[13] Alrazgan, M, Ghoneim, A, Albesher, L, et al. Automated hybrid methodology for software architecture style selection using analytic hierarchy process and fuzzy analytic hierarchy process. IET Softw. 2025; 2025(1): 9943825.doi: 10.1049/sfw2/9943825

[14] Hassan, DS, Zaki, AH, Hawash, MK. Estimation of hazard rate function for building second order mixed model using fuzzy techniques. Asian J Water Environ Pollut. 2022; 19(2):109-116. doi: 10.3233/ajw220030

[15] Hu, YJ, Wu, LZ, Pan, XQ, et al. Comprehensive evaluation of cloud manufacturing service based on fuzzy theory. Int J Fuzzy Syst. 2021; 23(6):1755-1764. doi: 10.1007/s40815-021-01071-4

[16] Bonet, E, Yubero, MT, Sanmiquel, L, et al. Neural network approaches for leakage flow quantification in masonry dam. Innov Infrastruct Solut. 2024; 9(11):426. doi: 10.1007/s41062-024-01744-7

[17] Bakary, K, Mouhamadou, D, Seydou, T. Contribution based on neurons networks for the prediction of greenhouse gas emissions in a handling port. Asian J Water Environ Pollut. 2024; 21(6):261-269. doi: 10.3233/ajw240094

[18] Wang, GY, Xu, CL, Li, DY.Generic normal cloud model. Inf Sci. 2014; 280:1-15. doi: 10.1016/j.ins.2014.04.051

[19] Mandal, S, Khan, DA. Cloud-CoCoSo: Cloud model-based combined compromised solution model for trusted cloud service provider selection. Arab J Sci Eng. 2022; 47(8):10307-10332. doi: 10.1007/s13369-021-06512-8

[20] Cai, RC, Wu, YJ, Huang, XK, Chen, W, Fu, TZ, Hao, Z. Granger causal representation learning for groups of time series. Sci China Inf Sci. 2024; 67(5):56-68. doi: 10.1007/s11432-021-3724-0

[21] Zhao, JC, Huang, LA, Wu, XQ, Xiao, L. The impact of trade war on Shanghai stock exchange industry based on Granger causality network. Acta Phys Sin. 2021; 70(7):325-333. doi: 10.7498/aps.70.20201516

[22] Man, J, Dong, HH, Jia, LM, Qin, Y. GGC: Gray-Granger causality method for sensor correlation network structure mining on high-speed train. Tsinghua Sci Technol. 2022; 27(1):207-222. doi: 10.26599/tst.2021.9010034

[23] Heckerman, D, Geiger, D, Chickering, DM. Learning bayesian networks: The combination of knowledge and statistical data. Mach Learn. 1995; 20:197-243. doi: 10.1023/a:1022623210503

[24] Briganti, G, Scutari, M, McNally, RJ. A tutorial on Bayesian networks for psychopathology researchers. Psychol Methods. 2022; 28(4):947-961. doi: 10.1037/met0000479

[25] Zhong, L, Xue, FZ. A lung cancer risk prediction model based on Bayesian network uncertainty inference. J Shandong Univ Health Sci. 2023; 61(4):89-94.

[26] Wu, XG, Zhao, HY, Xu, WT, Pan, W, Ji, Q, Hua, X. Fault diagnosis of the distribution network based on the D-S evidence theory Bayesian network. Front Energy Res. 2024; 12:1422639. doi: 10.3389/fenrg.2024.1422639

[27] Wu, YF, Wei, YM, Yang, B, et al. An improved fault diagnosis method for solid-liquid rocket engine. Chin Space Sci Technol. 2023; 43(1):88-99. doi: 10.16708/j.cnki.1000-758x.2023.0009

[28] Li, ZK, Wang, T, Ge, W, Wei, D, Li, H. Risk analysis of earth-rock dam breach based on dynamic Bayesian network. Water. 2019; 11(11):2305. doi: 10.3390/w11112305

[29] Li, ZK, Wang, T, Ge, W, et al. Risk analysis of concrete dam breach based on dynamic Bayesian network. J Changjiang River Sci Res Inst. 2021; 38(5):137-143.

[30] Chen, Y, Lin, PZ. Bayesian network of risk assessment for a super-large dam exposed to multiple natural risk sources. Stoch Environ Res Risk Assess. 2019; 33(2):581-592. doi: 10.1007/s00477-018-1631-0

[31] Yue, ZY, Wei, Z, Wang, KQ, et al. Reliability evaluation of integrated energy system based on Bayesian network time series simulation. Acta Energiae Solaris Sin. 2024; 45(10):220-230. doi: 10.19912/j.0254-0096.tynxb.2023-0958

[32] Cai, SL. Research on Routing Algorithms of Vehicular Delay Tolerant Networks Based on Bayesian Network. China: Nanjing University of Posts and Telecommunications; 2023.

[33] Gemela, J. Learning Bayesian networks using various datasources and applications to financial analysis. Soft Comput. 2003; 7(5):297-303. doi: 10.1007/s00500-002-0216-4

[34] Drton, M, Maathuis, MH.Structure learning in graphical modeling. Ann Rev Stat Appl. 2017; 4:365-393.

[35] Vomlel, J, Kratochvíl, V, Kratochvíl, F. Structural learning of mixed noisy-OR Bayesian networks. Int J Approx Reason. 2023; 161:108990. doi: 10.1016/j.ijar.2023.108990

[36] Gao, WL, Zeng, ZM, Ma, ML, Ke, Y, Zhi, M. An improved hybrid structure learning strategy for Bayesian networks based on ensemble learning. Intell Data Anal. 2023; 27(4):1103-1120. doi: 10.3233/ida-226818

[37] Laskey, KB, Sun, W, Hanson, R, Twardy, C, Matsumoto, S, Goldfedder, B. Graphical model market maker for combinatorial prediction markets. J Artif Intell Res. 2018; 63:421-460. doi: 10.1613/jair.1.11249

[38] Kessler, S, Cobb, A, Rudner, TGJ, Zohren, S, Roberts, SJ. On sequential Bayesian inference for continual learning. Entropy. 2023; 25(6):884. doi: 10.48550/arXiv.2301.01828

[39] Dutta, R, Mira, A, Onnela, JP. Bayesian inference of spreading processes on networks. Proc Math Phys Eng Sci. 2018; 474( 2215):20180129. doi: 10.1098/rspa.2018.0129