Generalizable Temperature Nowcasting with Physics-Constrained RNNs for Predictive Maintenance of Wind Turbine Components
This work addresses predictive maintenance for wind turbine operators to reduce downtimes and costs, but it is incremental as it builds on existing physics-constrained methods with partial system knowledge.
The paper tackles temperature nowcasting for predictive maintenance of wind turbine gearbox bearings by integrating physics constraints into neural networks, resulting in improved generalization to unseen environments compared to a baseline neural network.
Machine learning plays an important role in the operation of current wind energy production systems. One central application is predictive maintenance to increase efficiency and lower electricity costs by reducing downtimes. Integrating physics-based knowledge in neural networks to enforce their physical plausibilty is a promising method to improve current approaches, but incomplete system information often impedes their application in real world scenarios. We describe a simple and efficient way for physics-constrained deep learning-based predictive maintenance for wind turbine gearbox bearings with partial system knowledge. The approach is based on temperature nowcasting constrained by physics, where unknown system coefficients are treated as learnable neural network parameters. Results show improved generalization performance to unseen environments compared to a baseline neural network, which is especially important in low data scenarios often encountered in real-world applications.