Next Article in Journal
Real-Time Cooperative Path Planning and Collision Avoidance for Autonomous Logistics Vehicles Using Reinforcement Learning and Distributed Model Predictive Control
Previous Article in Journal
Quality Management for AI-Generated Self-Adaptive Resource Controllers
Previous Article in Special Issue
Encoding Multivariate Time Series of Gas Turbine Data as Images to Improve Fault Detection Reliability
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Machines
Volume 14
Issue 1
10.3390/machines14010026
machines-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

An AI Digital Platform for Fault Diagnosis and RUL Estimation in Drivetrain Systems Under Varying Operating Conditions

by
Dimitrios M. Bourdalos
1,
Xenofon D. Konstantinou
1,
Josef Koutsoupakis
2,
Ilias A. Iliopoulos
1,
Kyriakos Kritikakos
1,
George Karyofyllas
2,
Panayotis E. Spiliotopoulos
1,
Ioannis E. Saramantas
1,
John S. Sakellariou
1,
Dimitrios Giagopoulos
2,*,
Spilios D. Fassois
1,
Panagiotis Seventekidis
2 and
Sotirios Natsiavas
2
1
Stochastic Mechanical Systems & Automation (SMSA) Laboratory, Department of Mechanical Engineering and Aeronautics, University of Patras, 26504 Patras, Greece
2
Machine Dynamics Laboratory (MDL), Department of Mechanical Engineering, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
*
Author to whom correspondence should be addressed.
Machines 2026, 14(1), 26; https://doi.org/10.3390/machines14010026
Submission received: 17 November 2025 / Revised: 5 December 2025 / Accepted: 22 December 2025 / Published: 24 December 2025
(This article belongs to the Special Issue Advanced Techniques for Fault Detection, Diagnosis, and Prognostics in Machinery)
Versions Notes

Abstract

Drivetrain systems operate under varying operating conditions (OCs), which often obscure early-stage fault signatures and hinder robust condition monitoring (CM). This work introduces an AI digital platform developed during the EEDRIVEN project, featuring a holistic CM framework that integrates statistical time series methods—using Generalized AutoRegressive (GAR) models in a multiple model fault diagnosis scheme—with deep learning approaches, including autoencoders and convolutional neural networks, enhanced through a dedicated decision fusion methodology. The platform addresses all key CM tasks, including fault detection, fault type identification, fault severity characterization, and remaining useful life (RUL) estimation, which is performed using a dynamics-informed health indicator derived from GAR parameters and a simple linear Wiener process model. Training for the platform relies on a limited set of experimental vibration signals from the physical drivetrain, augmented with high-fidelity multibody dynamics simulations and surrogate-model realizations to ensure coverage of the full space of OCs and fault scenarios. Its performance is validated on hundreds of inspection experiments using confusion matrices, ROC curves, and metric-based plots, while the decision fusion scheme significantly strengthens diagnostic reliability across the CM stages. The results demonstrate near-perfect fault detection (99.8%), 97.8% accuracy in fault type identification, and over 96% in severity characterization. Moreover, the method yields reliable early-stage RUL estimates for the outer gear of the drivetrain, with normalized errors < 20% and consistently narrow confidence bounds, which confirms the platform’s robustness and practicality for real-world drivetrain systems monitoring.
Keywords: fault diagnosis; remaining useful life estimation; varying operating conditions; drivetrain systems; prognostics; condition monitoring; gearbox; rotating machinery fault diagnosis; remaining useful life estimation; varying operating conditions; drivetrain systems; prognostics; condition monitoring; gearbox; rotating machinery

Share and Cite

MDPI and ACS Style

Bourdalos, D.M.; Konstantinou, X.D.; Koutsoupakis, J.; Iliopoulos, I.A.; Kritikakos, K.; Karyofyllas, G.; Spiliotopoulos, P.E.; Saramantas, I.E.; Sakellariou, J.S.; Giagopoulos, D.; et al. An AI Digital Platform for Fault Diagnosis and RUL Estimation in Drivetrain Systems Under Varying Operating Conditions. Machines 2026, 14, 26. https://doi.org/10.3390/machines14010026

AMA Style

Bourdalos DM, Konstantinou XD, Koutsoupakis J, Iliopoulos IA, Kritikakos K, Karyofyllas G, Spiliotopoulos PE, Saramantas IE, Sakellariou JS, Giagopoulos D, et al. An AI Digital Platform for Fault Diagnosis and RUL Estimation in Drivetrain Systems Under Varying Operating Conditions. Machines. 2026; 14(1):26. https://doi.org/10.3390/machines14010026

Chicago/Turabian Style

Bourdalos, Dimitrios M., Xenofon D. Konstantinou, Josef Koutsoupakis, Ilias A. Iliopoulos, Kyriakos Kritikakos, George Karyofyllas, Panayotis E. Spiliotopoulos, Ioannis E. Saramantas, John S. Sakellariou, Dimitrios Giagopoulos, and et al. 2026. "An AI Digital Platform for Fault Diagnosis and RUL Estimation in Drivetrain Systems Under Varying Operating Conditions" Machines 14, no. 1: 26. https://doi.org/10.3390/machines14010026

APA Style

Bourdalos, D. M., Konstantinou, X. D., Koutsoupakis, J., Iliopoulos, I. A., Kritikakos, K., Karyofyllas, G., Spiliotopoulos, P. E., Saramantas, I. E., Sakellariou, J. S., Giagopoulos, D., Fassois, S. D., Seventekidis, P., & Natsiavas, S. (2026). An AI Digital Platform for Fault Diagnosis and RUL Estimation in Drivetrain Systems Under Varying Operating Conditions. Machines, 14(1), 26. https://doi.org/10.3390/machines14010026

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop