Abstract

La Baells arch dam has a height above the foundations of 102 m. It entered service in 1976 and since then it had correct performance, which has been controlled with a very complete monitoring system and conventional interpretation techniques. This communication presents the results of a pilot study in which machine learning techniques have been applied to analyze their monitoring data. These techniques offer greater flexibility than conventional procedures for generating dam response prediction models, as well as for identifying relationships between devices of a different nature. This allows a better understanding of the behavior of the structure and greater safety control.

Abstract

Large plants in the process industry are monitored and maintained at regular intervals and repeatedly maintenance is either too early or too late. This causes unnecessary costs due to technicians, spare parts procurement as well as delivery issues and to high downtime costs due to unexpected shutdowns. In this context, the Remaining Useful Life (RUL) plays a major role, as it is an indicator of how long a machine or component can run without breakdown, repair or replacement. By predicting RUL using predictive maintenance, maintenance can be better planned, operational efficiency optimized, and unplanned downtime avoided. Optimizing the prediction accuracy should therefore always be in the foreground and is therefore the topic of this paper.

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