Are Ensemble Classifiers Powerful Enough for the Detection and Diagnosis of Intermediate-Severity Faults?

\ac{IS} faults present milder symptoms compared to severe faults, and are more difficult to detect and diagnose due to their close resemblance to normal operating conditions. The lack of \ac{IS} fault examples in the training data can pose severe risks to \ac{FDD} methods that are built upon \ac{ML} techniques, because these faults can be easily mistaken as normal operating conditions. Ensemble models are widely applied in \ac{ML} and are considered promising methods for detecting \ac{OOD} data. We identify common pitfalls in these models through extensive experiments with several popular ensemble models on two real-world datasets. Then, we discuss how to design more effective ensemble models for detecting and diagnosing \ac{IS} faults.