A5026107149- Machine Fault Diagnosis Techniques
- Anomaly Detection Techniques and Applications
- Power System Reliability and Maintenance
- Power Systems and Technologies
- Fault Detection and Control Systems
- Energy Efficiency and Management
- Smart Grid Energy Management
- Oil and Gas Production Techniques
- Building Energy and Comfort Optimization
Fraunhofer Institute for Energy Economics and Energy System Technology
2021-2024
A popular method to detect anomalous behaviour or specific failures in wind turbine sensor data uses a type of neural network called an autoencoder. These models have proven be very successful detecting such deviations, yet cannot show the underlying cause failure directly. Such information is necessary for implementation these planning maintenance actions. In this paper we introduce novel method: ARCANA. We use ARCANA identify possible root causes anomalies detected by It describes process...
Anomaly detection in wind turbines typically involves using normal behaviour models to detect faults early. However, training autoencoder for each turbine is time-consuming and resource intensive. Thus, transfer learning becomes essential with limited data or applications computational resources. This study examines how cross-turbine can be applied autoencoder-based anomaly detection. Here, autoencoders are combined constant thresholds the reconstruction error determine if input contains an...
Anomaly detection plays a crucial role in the field of predictive maintenance for wind turbines, yet comparison different algorithms poses difficult task because domain specific public datasets are scarce. Many comparisons approaches either use benchmarks composed data from many domains, inaccessible or one few publicly available which lack detailed information about faults. Moreover, publications highlight couple case studies where fault was successful. With this paper we publish high...
Anomaly detection in wind turbines typically involves using normal behaviour models to detect faults early. Normal are often implemented through the use of neural networks, which autoencoders particularly popular this field. However, training autoencoder for each turbine is time-consuming and resource intensive. Thus, transfer learning becomes essential with limited data or applications computational resources. This study examines how cross-turbine can be applied autoencoder-based anomaly...
Early fault detection plays a crucial role in the field of predictive maintenance for wind turbines, yet comparison different algorithms poses difficult task because domain-specific public datasets are scarce. Many comparisons approaches either use benchmarks composed data from many domains, inaccessible data, or one few publicly available that lack detailed information about faults. Moreover, publications highlight couple case studies where was successful. With this paper, we publish high...
High energy and electricity prices, coupled with high price volatility, increase the value of demand response side management. Energy management systems that are predictive exchange-price oriented can help to leverage flexibility while lowering costs. In this paper, is assessed in two scenarios low prices. To end, a self-learning home system introduced takes into account new volatility stock market The proposed approach compared baseline system, which typical household self-consumption...