Data Requirements and Prediction Scaling for Long-Term Failure Forecasts in Wind Turbines

2024/07/31 by Viktor Begun, Begun, Viktor, Ulrich Schlickewei +1
Engineering · #Engineering Diagnostics and Reliability #FOS: Electrical engineering #Machine Fault Diagnosis Techniques #Mechanical Failure Analysis and Simulation #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2407.21533

openalex publication_date 2024/07/31 · openalex created_date 2024/08/04 · openalex updated_date 2026/07/28

Abstract

We investigate the key factors that enable early failure forecasting in wind turbines. For this purpose, we analyze studies with long-term forecasts and compare their main features: prediction time, methods, targeted components, dataset size, and check the effect of using additional sensors. We found that the size of the dataset is the main factor and that an approximate linear scaling holds: the number of forecast days is twice the size of the dataset, measured in turbine years. We also observe that the data allow us to quantify the meaning of "big" and "long" in the terms "big data" and "long-term" forecasts, which are found to be ten turbine years and two weeks.

Related

• Fine-Tuning Pre-trained Large Time Series Models for Prediction of Wind Turbine SCADA Data
• Digital Twin Framework for Time to Failure Forecasting of Wind Turbine Gearbox: A Concept
• Equipment Health Assessment: Time Series Analysis for Wind Turbine Performance
• Condition Monitoring with Machine Learning: A Data-Driven Framework for Quantifying Wind Turbine Energy Loss
• A Deep Learning Approach Towards Prediction of Faults in Wind Turbines