Version 1
: Received: 1 September 2021 / Approved: 2 September 2021 / Online: 2 September 2021 (11:36:48 CEST)
Version 2
: Received: 15 September 2021 / Approved: 16 September 2021 / Online: 16 September 2021 (11:47:31 CEST)
Version 3
: Received: 11 January 2022 / Approved: 12 January 2022 / Online: 12 January 2022 (10:22:47 CET)
How to cite:
Nor, A.K.M.; Pedapati, S.R.; Muhammad, M.; Leiva, V. Abnormality Detection and Failure Prediction Using Explainable Bayesian Deep Learning: Methodology and Case Study of Real-World Gas Turbine Anomalies. Preprints2021, 2021090034. https://doi.org/10.20944/preprints202109.0034.v3
Nor, A.K.M.; Pedapati, S.R.; Muhammad, M.; Leiva, V. Abnormality Detection and Failure Prediction Using Explainable Bayesian Deep Learning: Methodology and Case Study of Real-World Gas Turbine Anomalies. Preprints 2021, 2021090034. https://doi.org/10.20944/preprints202109.0034.v3
Nor, A.K.M.; Pedapati, S.R.; Muhammad, M.; Leiva, V. Abnormality Detection and Failure Prediction Using Explainable Bayesian Deep Learning: Methodology and Case Study of Real-World Gas Turbine Anomalies. Preprints2021, 2021090034. https://doi.org/10.20944/preprints202109.0034.v3
APA Style
Nor, A.K.M., Pedapati, S.R., Muhammad, M., & Leiva, V. (2022). Abnormality Detection and Failure Prediction Using Explainable Bayesian Deep Learning: Methodology and Case Study of Real-World Gas Turbine Anomalies. Preprints. https://doi.org/10.20944/preprints202109.0034.v3
Chicago/Turabian Style
Nor, A.K.M., Masdi Muhammad and Víctor Leiva. 2022 "Abnormality Detection and Failure Prediction Using Explainable Bayesian Deep Learning: Methodology and Case Study of Real-World Gas Turbine Anomalies" Preprints. https://doi.org/10.20944/preprints202109.0034.v3
Abstract
: Mistrust, amplified by numerous artificial intelligence (AI) related incidents, has caused the energy and industrial sectors to be amongst the slowest adopter of AI methods. Central to this issue is the black-box problem of AI, which impedes investments and fast becoming a legal hazard for users. Explainable AI (XAI) is a recent paradigm to tackle this challenge. Being the backbone of the industry, the prognostic and health management (PHM) domain has recently been introduced to XAI. However, many deficiencies, particularly lack of explanation assessment methods and uncertainty quantification, plague this young field. In this paper, we elaborate a framework on explainable anomaly detection and failure prognostic employing a Bayesian deep learning model to generate local and global explanations from the PHM tasks. An uncertainty measure of the Bayesian model is utilized as marker for anomalies expanding the prognostic explanation scope to include model’s confidence. Also, the global explanation is used to improve prognostic performance, an aspect neglected from the handful of PHM-XAI publications. The quality of the explanation is finally examined employing local accuracy and consistency properties. The method is tested on real-world gas turbine anomalies and synthetic turbofan data failure prediction. Seven out of eight of the tested anomalies were successfully identified. Additionally, the prognostic outcome showed 19% improvement in statistical terms and achieved the highest prognostic score amongst best published results on the topic.
Keywords
Artificial intelligence; CMAPSS; consistency and local accuracy; CUSUM chart; deep learning; prognostic and health management; RMSE; sensing and data extraction; SHAP; Uncertainty; XAI
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Received:
12 January 2022
Commenter:
Victor Leiva
Commenter's Conflict of Interests:
Author
Comment:
We have updated our preprint after publishing a review paper in Sensors recently. We have submitted the new version of the preprint to Mathematics. This paper is: Nor AKM, Pedapati SR, Muhammad M, Leiva V (2021) Overview of explainable artificial intelligence for prognostic and health management of industrial assets based on preferred reporting items for systematic reviews and meta-analyses. Sensors 21(23):8020.
Commenter: Victor Leiva
Commenter's Conflict of Interests: Author
Nor AKM, Pedapati SR, Muhammad M, Leiva V (2021) Overview of explainable artificial intelligence for prognostic and health management of industrial assets based on preferred reporting items for systematic reviews and meta-analyses. Sensors 21(23):8020.