Temperature effect modeling in structural health monitoring of concrete dams using kernel extreme learning machines

Kang, Fei; Liu, Xi; Li, Junjie

doi:10.1177/1475921719872939

Cited by 62 publications

(40 citation statements)

References 38 publications

(100 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ranković, Grujović, Divac, and Milivojević (2014) integrated previously measured displacements into a set of factors to form an SVR-based nonlinear autoregressive model with exogenous inputs. Kang, Li, and Dai (2019) and Kang, Liu, and Li (2019b) simulated the temperature effect by analyzing long-term actual ambient air temperature. It was found that, by explicitly modeling air temperature effect, the prediction error was significantly reduced.…”

Section: Background and Literature Reviewmentioning

confidence: 99%

A robust prediction model for displacement of concrete dams subjected to irregular water‐level fluctuations

Ren

et al. 2021

Computer aided Civil Eng

View full text Add to dashboard Cite

Monitoring and predicting the displacement of concrete dams is one of the most crucial considerations for ensuring their long-term safe operation. Most existing models are designed for dams subjected to common structural and environmental conditions, with little attention paid to atypical operational conditions, such as structural strengthening or sudden changes in the external environment. The motivation for this work is to develop a reliable prediction model for displacement behavior of concrete dams subjected to irregular upstream water-level fluctuations. In our study, a reconstruction method for unevenly sampled time series is presented to analyze such data. Then, an improved model, factor weighted support vector regression (FWSVR), which differentiates various factors and their effects through a weighting matrix, is theoretically derived. The weights are determined by the RReliefF algorithm, and together with FWSVR form the final RReliefF-based FWSVR (RFWSVR) model. In particular, the hyperparameters involved in the above modeling strategy are optimized by the Grey Wolf Optimizer. Eventually, the prediction robustness of the developed model was verified on the data from four representative monitoring points of a real-world dam, where its accuracy was compared to classical dam behavior modeling methods, FWSVR models using other weighting methods, and an ensemble learning algorithm. Comparative evaluation of the performance of the different methods was conducted with the help of recognized statistical indices. The evaluation results show that the overall performance of the proposed RFWSVR model is optimal for the displacement prediction at the selected points when the dam case is subjected to irregular water-level changes. This novel modeling approach may be generalized for modeling the evolution behavior of other civil or hydraulic structures.

show abstract

Section: Background and Literature Reviewmentioning

confidence: 99%

A robust prediction model for displacement of concrete dams subjected to irregular water‐level fluctuations

Ren

et al. 2021

Computer aided Civil Eng

View full text Add to dashboard Cite

show abstract

“…where a 0 , …, a 11 are fitting coefficients, h is the upstream water depth [34,35] or water level [24], s = 2πd/365.25, 2π/365.25 is a constant related to annual frequency, d is the number of days observed in a year, and t is the number of days since the beginning of the analysis.…”

Section: Displacement Prediction Modelmentioning

confidence: 99%

“…To better interpret the nonlinear thermal displacement in statistical models, many advanced HST and HTT models for thermal effect simulation have been proposed [9,17,18,[20][21][22][23]. In our recent study [24], a mathematical model based on kernel-extreme learning machines (KELM) algorithm [25,26] with long-term daily air temperature monitoring data series was proposed for displacement prediction modeling of concrete gravity dams. Compared to the traditional HST model based on the MLR method, the performance of the prediction model has been significantly improved.…”

Section: Introductionmentioning

confidence: 99%

Concrete arch dam behavior prediction using kernel-extreme learning machines considering thermal effect

Kang

Ma³

et al. 2021

J Civil Struct Health Monit

Self Cite

View full text Add to dashboard Cite

Behavior prediction of concrete arch dams requires the interpretation of monitoring data from instrument measurement. Mathematical models based on artificial intelligence algorithms provide an effective approach to interpret the dam behavior from the monitoring data, which can be utilized to model dam displacement as a function of water level, irreversible time effect, and thermal. In our recent study, an improved mathematical model base on kernel-extreme learning machines (KELM) algorithm with long-term daily air temperature monitoring data series has been successfully applied to the displacement prediction modeling of concrete gravity dams. Considering the important contribution of thermal effect on concrete arch dam deformation, the present paper concerns the applicability of the proposed method in the behavior prediction of concrete arch dams. For the sake of improving the efficiency of the mathematical model, the parameters which are crucial to the performance of KELM are selected by the Jaya optimization algorithm. The performance of the proposed automatic parameter optimization-based Jaya-KELM model was compared with the traditional statistical model and other intelligent algorithms. Results demonstrate that the proposed method is a promising and powerful approach for the behavior prediction modeling of concrete arch dams.

show abstract

“…The kernel extreme learning has shown speed in accuracy and performance. The simulation was also undertaken in real dam concrete gravity and the results are feasible to application [9].…”

Section: Machine Learning Applications In Recent Dam Water Researchmentioning

confidence: 99%

Machine Learning in Dam Water Research: An Overview of Applications and Approaches

Yahya¹,

Fazli²,

Sallehudin³

et al. 2020

IJATCSE

View full text Add to dashboard Cite

Dam plays a crucial role in water security. A sustainable dam intends to balance a range of resources involves within a dam operation. Among the factors to maintain sustainability is to maintain and manage the water assets in dams. Water asset management in dams includes a process to ensure the planned maintenance can be conducted and assets such as pipes, pumps and motors can be mended, substituted, or upgraded when needed within the allocated budgetary. Nowadays, most water asset management systems collect and process data for data analysis and decision-making. Machine learning (ML) is an emerging concept applied to fulfill the requirement in engineering applications such as dam water researches. ML can analyze vast volumes of data and through an ML model built from algorithms, ML can learn, recognize and produce accurate results and analysis. The result brings meaningful insights for water asset management specifically to strategize the optimal solution based on the forecast or prediction. For example, a preventive maintenance for replacing water assets according to the prediction from the ML model. We will discuss the approaches of machine learning in recent dam water research and review the emerging issues to manage water assets in dams in this paper.

show abstract

Temperature effect modeling in structural health monitoring of concrete dams using kernel extreme learning machines

Cited by 62 publications

References 38 publications

A robust prediction model for displacement of concrete dams subjected to irregular water‐level fluctuations

A robust prediction model for displacement of concrete dams subjected to irregular water‐level fluctuations

Concrete arch dam behavior prediction using kernel-extreme learning machines considering thermal effect

Machine Learning in Dam Water Research: An Overview of Applications and Approaches

Contact Info

Product

Resources

About