Augmenting Monte Carlo Dropout Classification Models with Unsupervised Learning Tasks for Detecting and Diagnosing Out-of-Distribution Faults
This work addresses fault detection and diagnosis in industrial or safety-critical systems, offering an incremental improvement over existing methods.
The paper tackles the problem of detecting and diagnosing out-of-distribution faults in classification models by augmenting Monte Carlo dropout with an unsupervised learning task, resulting in improved performance on incipient and unknown faults across three diverse datasets.
The Monte Carlo dropout method has proved to be a scalable and easy-to-use approach for estimating the uncertainty of deep neural network predictions. This approach was recently applied to Fault Detection and Di-agnosis (FDD) applications to improve the classification performance on incipient faults. In this paper, we propose a novel approach of augmenting the classification model with an additional unsupervised learning task. We justify our choice of algorithm design via an information-theoretical analysis. Our experimental results on three datasets from diverse application domains show that the proposed method leads to improved fault detection and diagnosis performance, especially on out-of-distribution examples including both incipient and unknown faults.