Probabilistic Machine Learning for Uncertainty-Aware Diagnosis of Industrial Systems

Deep neural networks has been increasingly applied in fault diagnostics, where it uses historical datato capture systems behavior, bypassing the need for high-fidelity physical models.However, despite their competence in prediction tasks, these models often struggle withthe evaluation of their confidence. This matter is particularlyimportant in consistency-based diagnosis where decision logic is highly sensitive to false alarms.To address this challenge, this work presents a diagnostic framework that usesensemble probabilistic machine learning toimprove diagnostic characteristics of data driven consistency based diagnosisby quantifying and automating the prediction uncertainty.The proposed method is evaluated across several case studies using both ablationand comparative analyses, showing consistent improvements across a range of diagnostic metrics.