The Impact of Feature Causality on Normal Behaviour Models for SCADA-based Wind Turbine Fault Detection
This work addresses feature selection inconsistencies in SCADA-based fault detection for wind turbines, which could reduce maintenance costs, but it appears incremental as it builds on existing normal behavior models.
The authors tackled the problem of inconsistent feature selection in normal behavior models for wind turbine fault detection by introducing a taxonomy based on causal relations between input features and targets, and they evaluated its impact on modeling and fault detection performance, though no concrete numbers were provided.
The cost of wind energy can be reduced by using SCADA data to detect faults in wind turbine components. Normal behavior models are one of the main fault detection approaches, but there is a lack of consensus in how different input features affect the results. In this work, a new taxonomy based on the causal relations between the input features and the target is presented. Based on this taxonomy, the impact of different input feature configurations on the modelling and fault detection performance is evaluated. To this end, a framework that formulates the detection of faults as a classification problem is also presented.