Abstract

Dam behaviour is difficult to predict with high accuracy. Numerical models for structural calculation solve the equations of continuum mechanics, but are subject to considerable uncertainty as to the characterisation of materials, especially with regard to the foundation. As a result, these models are often incapable to calculate dam behaviour with sufficient precision. Thus, it is difficult to determine whether a given deviation between model results and monitoring data represent a relevant anomaly or incipient failure.

By contrast, there is a tendency towards automatising dam monitoring devices, which allows for increasing the reading frequency and results in a greater amount and variety of data available, such as displacements, leakage, or interstitial pressure, among others.

This increasing volume of dam monitoring data makes it interesting to study the ability of advanced tools to extract useful information from observed variables.

In particular, in the field of Machine Learning (ML), powerful algorithms have been developed to face problems where the amount of data is much larger or the underlying phenomena is much less understood.

In this monograph, the possibilities of machine learning techniques are analysed for application to dam structural analysis based on monitoring data. The typical characteristics of the data sets available in dam safety are taking into account, as regards their nature, quality and size.

A critical literature review is performed, from which the key issues to consider for implementation of these algorithms in dam safety are identified.

A comparative study of the accuracy of a set of algorithms for predicting dam behaviour is carried out, considering radial and tangential displacements and leakage flow in a 100-m high dam. The results suggest that the algorithm called “Boosted Regression Trees” (BRT) is the most suitable, being more accurate in general, while flexible and relatively easy to implement.

The possibilities of interpretation of the mentioned algorithm are evaluated, to identify the shape and intensity of the association between external variables and the dam response, as well as the effect of time. The tools are applied to the same test case, and allow more accurate identification of the time effect than the traditional statistical method.

Finally, a methodology for the implementation of predictive models based on BRT for early detection of anomalies is presented, together with its implementation in an interactive tool that provides information on dam behaviour, through a set of selected devices. It allows the user to easily verify whether the actual data for each of these devices are within a pre-defined normal operation interval.

Abstract

The advances in information and communication technologies led to a general trend towards the availability of more detailed information on dam behaviour. This allows applying advanced data‐based algorithms in its analysis, which has been reflected in an increasing interest in the field. However, most of the related literature is limited to the evaluation of model prediction accuracy, whereas the ulterior objective of data analysis is dam safety assessment. In this work, a machine‐learning algorithm (boosted regression trees) is the core of a methodology for early detection of anomalies. It also includes a criterion to determine whether certain discrepancy between predictions and observations is normal, a procedure to compute a realistic estimate of the model accuracy, and an original approach to identify extraordinary load combinations. The performance of causal and noncausal models is assessed in terms of their ability to detect different types of anomalies, which were artificially introduced on reference time series generated with a numerical model of a 100‐m‐high arch dam. The final approach was implemented in an online application to visualise the results in an intuitive way to support decision making.

Abstract

Abstract

Dam safety assessment is typically made by comparison between the outcome of some predictive model and measured monitoring data. This is done separately for each response variable, and the results are later interpreted before decision making. In this work, three approaches based on machine learning classifiers are evaluated for the joint analysis of a set of monitoring variables: multiclass, two-class and one-class classification. Support vector machines are applied to all prediction tasks, and random forest is also used for multi-class and two-class. The results show high accuracy for multi-class classification, although the approach has limitations for practical use. The performance in two-class classification is strongly dependent on the features of the anomalies to detect and their similarity to those used for model fitting. The one-class classification model based on support vector machines showed high prediction accuracy, while avoiding the need for correctly selecting and modelling the potential anomalies. A criterion for anomaly detection based on model predictions is defined, which results in a decrease in the misclassification rate. The possibilities and limitations of all three approaches for practical use are discussed.

Abstract

Wind turbine reliability is essential for the renewable energy sector, as failures in key parts such as gearboxes and main bearings lead to more than $10 billion in downtime and maintenance costs each year. Supervisory control and data acquisition (SCADA) systems can monitor turbines using signals such as vibration, power output, and wind speed; however, applying machine learning to this data type is challenging due to the presence of unbalanced fault types and complex time patterns. Previous research has explored physics-informed deep learning, digital twins, and contrastive learning, achieving noteable fault detection accuracy. However, challenges remain in detecting rare faults, dealing with imbalanced data, combining data sources, and model generalization. This study presents StateSpaceNetWithGen (SS-Gen), a hybrid model integrating state-space modeling for temporal dynamics with generative augmentation for class imbalance. Tested on a 35,000-sample SCADA dataset (2018–2019), SS-Gen achieved high accuracy (≈1.00) and F1-score (≈1.00) on this specific dataset, improving by 33% over baselines. To further validate the strengths of the proposed method, the methodology is validated on a second dataset with different distribution. These results support more reliable and interpretable wind turbine health monitoring and move the field toward stronger physics-informed and federated machine learning solutions.OPEN ACCESS Received: 06/10/2025 Accepted: 19/11/2025

Abstract

Wind turbine reliability is essential for the renewable energy sector, as failures in key parts such as gearboxes and main bearings lead to more than $10 billion in downtime and maintenance costs each year. Supervisory control and data acquisition (SCADA) systems can monitor turbines using signals such as vibration, power output, and wind speed; however, applying machine learning to this data type is challenging due to the presence of unbalanced fault types and complex time patterns. Previous research has explored physics-informed deep learning, digital twins, and contrastive learning, achieving noteable fault detection accuracy. However, challenges remain in detecting rare faults, dealing with imbalanced data, combining data sources, and model generalization. This study presents StateSpaceNetWithGen (SS-Gen), a hybrid model integrating state-space modeling for temporal dynamics with generative augmentation for class imbalance. Tested on a 35,000-sample SCADA dataset (2018–2019), SS-Gen achieved high accuracy (≈1.00) and F1-score (≈1.00) on this specific dataset, improving by 33% over baselines. To further validate the strengths of the proposed method, the methodology is validated on a second dataset with different distribution. These results support more reliable and interpretable wind turbine health monitoring and move the field toward stronger physics-informed and federated machine learning solutions.OPEN ACCESS Received: 06/10/2025 Accepted: 19/11/2025 Published: 23/01/2026

Abstract

'''The improvements in monitoring devices result in databases of increasing size showing dam behaviour. Advanced tools are required to extract useful information from such large amounts of data. Machine learning is increasingly used for that purpose worldwide: data-based models are built to estimate the dam response in front of a given combination of loads. The results of the comparison between model predictions and actual measurements can be used for decision support in dam safety evaluations. However, most of the works to date consider each device separately. A different approach is used in this contribution: a set of displacement records are jointly considered to identify patterns using a classification model. First, potential anomaly scenarios are defined and the response of the dam for each of them is obtained with numerical models under a realistic load combination. Then, the resulting displacements are used to generate a machine learning classifier. This model is later used to predict the most probable class of dam behavior corresponding to a new set of records. The methodology is applied to a double-curvature arch dam, showing great potential for anomaly detection.