Analysis and interpretation of observed dynamic behaviour of a large concrete dam aided by soft computing and machine learning techniques

Mata, Juan; Gomes, Jorge Pereira; Pereira, Sérgio; Magalhães, Filipe; Cunha, Álvaro

doi:10.1016/j.engstruct.2023.116940

Cited by 2 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of artificial intelligence (AI) models applied to dam safety has proliferated in recent times. Numerous scientific references related to the use of ML, DL, or hybrid models with other types of models such as statistical, time series, or physics-based numerical models can be found [6][7][8][9][10][11][12]. Machine Learning models have shown good performance in monitoring data prediction and are more accessible to interpretation than DL models.…”

Section: Introductionmentioning

confidence: 99%

Identification of Trends in Dam Monitoring Data Series Based on Machine Learning and Individual Conditional Expectation Curves

Fernández-Centeno,

Alocén,

Toledo

2024

Water

View full text Add to dashboard Cite

Dams are complex systems that involve both the structure itself and its foundation. Rheological phenomena, expansive reactions, or alterations in the geotechnical parameters of the foundation, among others, result in non-reversible and cumulative modifications in the dam response, leading to trends in the monitoring data series. The accurate identification and definition of these trends to study their evolution are key aspects of dam safety. This manuscript proposes a methodology to identify trends in dam behavioural data series by identifying the influence of the time variable on the predictions provided by the ML models. Initially, ICE curves and SHAP values are employed to extract temporal dependence, and the ICE curves are found to be more precise and efficient in terms of computational cost. The temporal dependencies found are adjusted using a GWO algorithm to different function characteristics of irreversible processes in dams. The function that provides the best fit is selected as the most plausible. The results obtained allow us to conclude that the proposed methodology is capable of obtaining estimates of the most common trends that affect movements in concrete dams with greater precision than the statistical models most commonly used to predict the behaviour of these types of variables. These results are promising for its general application to other types of dam monitoring data series, given the versatility demonstrated for the unsupervised identification of temporal dependencies.

show abstract

Section: Introductionmentioning

confidence: 99%

Identification of Trends in Dam Monitoring Data Series Based on Machine Learning and Individual Conditional Expectation Curves

Fernández-Centeno,

Alocén,

Toledo

2024

Water

View full text Add to dashboard Cite

show abstract

“…Concrete-face slab deflection increased by approximately 0.1% when the dam was built on a gravel foundation, and the calculated results were consistent with the monitoring data. These previous studies indicate that the stress and deformation characteristics of high concrete-face rockfill dams under complex conditions can be determined accurately using static and dynamic calculations, which are crucial for engineering construction and management [17][18][19].…”

Section: Introductionmentioning

confidence: 99%

Three-Dimensional Static and Dynamic Analyses of an Embedded Concrete-Face Rockfill Dam

Qu,

Chai,

2023

Water

View full text Add to dashboard Cite

Concrete-face rockfill dams have gradually become the preferred dam type in the engineering community. This study presents a hydropower station in China as a case study to introduce a new type of embedded concrete-face rockfill dam. The static and dynamic stress–strain characteristics of the proposed and conventional concrete-face rockfill dams were compared, and the optimal height of the embedded concrete body at the hydropower station was determined. The results indicate that, under static conditions, the embedded concrete body could reduce deformation upstream and downstream of the rockfill body, eliminate tensile stress along the concrete-face slab slope, reduce concrete-face slab deflection, and increase the maximum deflection area to 0.47 times the dam height. The inhibitory effect of the embedded concrete body on the stress and strain of the dam body became more evident as the size of the embedded body increased. Although the embedded concrete body did not enhance the dynamic and superposed static–dynamic stress states of the embedded concrete body and rockfill, the stress and strain increase in the dynamic state were within a controllable range. Through a sensitivity analysis and considering the terrain conditions and engineering cost of the hydropower station, the height of the embedded concrete body is recommended to be 0.4 times the dam height.

show abstract

Analysis and interpretation of observed dynamic behaviour of a large concrete dam aided by soft computing and machine learning techniques

Cited by 2 publications

References 38 publications

Identification of Trends in Dam Monitoring Data Series Based on Machine Learning and Individual Conditional Expectation Curves

Identification of Trends in Dam Monitoring Data Series Based on Machine Learning and Individual Conditional Expectation Curves

Three-Dimensional Static and Dynamic Analyses of an Embedded Concrete-Face Rockfill Dam

Contact Info

Product

Resources

About