A modelling approach based on Bayesian networks for dam risk analysis: Integration of machine learning algorithm and domain knowledge

Tang, Xianqi; Chen, Anyi; He, Jinrong

doi:10.1016/j.ijdrr.2022.102818

Cited by 17 publications

(5 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides and variables, each hazard contains a list of potentially affected DRS’ subsystems. This attribute is assessed using historical data if there are documented historical failures, and/or detailed numerical and theoretical analyses of the DRSs behavior (Rehamnia et al 2020 ; Chen et al 2021 ; Rakić et al 2022 ; Nafchi et al 2021a , b ; Tang et al 2022 ). It should be noted that the hazard database contains an event to describe normal conditions (no hazard), which has the highest occurrence probability.…”

Section: Methodsmentioning

confidence: 99%

Failure Conditions Assessment of Complex Water Systems Using Fuzzy Logic

Milašinović

Ivetić

Stojković³

et al. 2023

Water Resour Manage

View full text Add to dashboard Cite

Climate change, energy transition, population growth and other natural and anthropogenic impacts, combined with outdated (unfashionable) infrastructure, can force Dam and Reservoir Systems (DRS) operation outside of the design envelope (adverse operating conditions). Since there is no easy way to redesign or upgrade the existing DRSs to mitigate against all the potential failure situations, Digital Twins (DT) of DRSs are required to assess system’s performance under various what-if scenarios. The current state of practice in failure modelling is that failures (system’s not performing at the expected level or not at all) are randomly created and implemented in simulation models. That approach helps in identifying the riskiest parts (subsystems) of the DRS (risk-based approach), but does not consider hazards leading to failures, their occurrence probabilities or subsystem failure exposure. To overcome these drawbacks, this paper presents a more realistic failure scenario generator based on a causal approach. Here, the novel failure simulation approach utilizes fuzzy logic reasoning to create DRS failures based on hazard severity and subsystems’ reliability. Combined with the system dynamics (SD) model this general failure simulation tool is designed to be used with any DRS. The potential of the proposed method is demonstrated using the Pirot DRS case study in Serbia over a 10-year simulation period. Results show that even occasional hazards (as for more than 97% of the simulation there were no hazards), combined with outdated infrastructure can reduce DRS performance by 50%, which can help in identifying possible “hidden” failure risks and support system maintenance prioritization. Graphical Abstract

show abstract

Section: Methodsmentioning

confidence: 99%

Failure Conditions Assessment of Complex Water Systems Using Fuzzy Logic

Milašinović

Ivetić

Stojković³

et al. 2023

Water Resour Manage

View full text Add to dashboard Cite

show abstract

“…By collecting and analyzing real-time data, this approach can effectively prevent disasters and ensure dam safety (Rico et al, 2019). Tang et al (2022) proposes a Bayesian network model to analyze dam risk in their paper. The approach integrates ML models and domain knowledge.…”

Section: Research Backgroundmentioning

confidence: 99%

“…The study explores the potential of using such models in disaster risk reduction. The authors suggest that the proposed model can help policymakers make more informed decisions on dam safety (Tang et al, 2022).…”

Section: Research Backgroundmentioning

confidence: 99%

Maximizing hydropower station safety against earthquake through extreme learning machine-enabled shear waves velocity prediction

Song,

Guan,

Wang

et al. 2024

Front. Environ. Sci.

View full text Add to dashboard Cite

Hydropower stations are important infrastructures for generating clean energy. However, they are vulnerable to natural disasters such as earthquakes, which can cause severe damage and even lead to catastrophic failures. Therefore, it is essential to develop effective strategies for maximizing hydropower station safety against earthquakes. To evaluate the potential shear rate of surrounding rock layers, the shear wave velocity (Vs) parameter can be used as a useful tool. This parameter helps to determine the velocity at which shear waves travel through the rock layers, which can indicate their stability and susceptibility to earthquakes. This study will investigate the significance of the Vs parameter in evaluating the potential shear rate of rock layers surrounding hydropower stations and how it can be used to ensure their safety and efficiency in earthquake-prone regions. Furthermore, a novel approach is proposed in this research, which involves using extreme learning machine (ELM) technology to predict Vs and enhance the seismic safety of hydropower stations. The ELM model predicts the Vs of the soil layers around the hydropower station, a crucial factor in determining the structure’s seismic response. The predicted Vs is then used to assess seismic hazard and design appropriate safety measures. The ML-ELM model outperformed both the ELM and empirical models, with an RMSE of 0.0432 μs/ft and R2 of 0.9954, as well as fewer outlier data predictions. This approach shows promise for predicting Vs in similar environments, and future research could explore its effectiveness in other datasets and practical applications.

show abstract

“…To avoid creating an overly complicated diagram, only key indicators (piping, cracks, uneven settlement, etc.) were retained, and other risk factors with a low frequency of occurrence were removed, such as earthquakes [12]. To restore the integrity and maintain the balance of the system, we introduced balance variables (in blue), such as safety awareness level, monitoring and warning level, flood control and communication, and rescue efficiency.…”

Section: Nonlinear Causal Miningmentioning

confidence: 99%

“…But for dam failure risk analysis, most current studies are based on domain knowledge (DK) (e.g., published scientific evidence and expert opinion) because of the lack of historical data available for reference. Although there is rich domain knowledge on dam failure mechanisms and probability calculations, the DK-based BN model is unstable [12] due to the complexity limitation of the network and the lack of clarity in the basis for determining the probability parameters. From the results of the relevant published papers [13][14][15], BN models built on DK are susceptible to subjective influences.…”

Section: 、 Introductionmentioning

confidence: 99%

A Bayesian Method for Dam Failure Risk Analysis using Causal Loop Diagrams and Word Frequency Analysis

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

Earthen dams operate in complex environments where their safety is often affected by multiple uncertain risks. A Bayesian network (BN) is often used to analyze the dam failure risk, which is an effective tool for this issue as its excellent ability in representing uncertainty and reasoning. The validity of the BN model is strongly dependent on the quality of the sample data, making convincing modeling rationale a challenge, which limits its use. There has been a lack of systematic analysis of the dam failure data of China, which further leads to a lack of in-depth exploration of potential associations between risk factors. In this paper, we established a comprehensive database containing various dam failure cases in China. Herein, historical dam failure statistics are used to develop BN models for risk analysis of earthen dams in China. In order to unleash the value of the historical data, we established a Bayesian network through the Causal Loop Diagrams (CLD) based on the nonlinear causal analysis. We determined the conditional probabilities using Word Frequency Analysis (WFA). By comparing with the Bayesian learning results, the modeling method of BN proposed in our study has apparent advantages. According to the BN model established in this paper, the probabilities of dam failure with three damage modes of seepage damage, overtopping and structural instability are 22.1%, 58.1%, and 7.9%, respectively. In addition, we demonstrated how to perform the inference process of the dam failure path. This will provide helpful information for dam safety practitioners in their decision-making process.

show abstract

A modelling approach based on Bayesian networks for dam risk analysis: Integration of machine learning algorithm and domain knowledge

Cited by 17 publications

References 59 publications

Failure Conditions Assessment of Complex Water Systems Using Fuzzy Logic

Failure Conditions Assessment of Complex Water Systems Using Fuzzy Logic

Maximizing hydropower station safety against earthquake through extreme learning machine-enabled shear waves velocity prediction

A Bayesian Method for Dam Failure Risk Analysis using Causal Loop Diagrams and Word Frequency Analysis

Contact Info

Product

Resources

About