Publications

Learning Informative Health Indicators Through Unsupervised Contrastive Learning

K. Rombach; G. Michau; W. Burzle; S. Koller; O. Fink 

Ieee Transactions On Reliability. 2024-05-16. DOI : 10.1109/TR.2024.3397394.

Collective relational inference for learning heterogeneous interactions

Z. Han; O. Fink; D. S. Kammer 

Nature Communications. 2024-04-12. Vol. 15, num. 1, p. 3191. DOI : 10.1038/s41467-024-47098-7.

Domain adaptation via alignment of operation profile for Remaining Useful Lifetime prediction

I. Nejjar; F. Geissmann; M. Zhao; C. Taal; O. Fink 

Reliability Engineering & System Safety. 2024. Vol. 242, p. 109718. DOI : 10.1016/j.ress.2023.109718.

Federated learning with uncertainty-based client clustering for fleet-wide fault diagnosis

H. Lu; A. Thelen; O. Fink; C. Hu; S. Laflamme 

Mechanical Systems and Signal Processing. 2024. Vol. 210, p. 111068. DOI : 10.1016/j.ymssp.2023.111068.

Non-contact sensing for anomaly detection in wind turbine blades: A focus-SVDD with complex-valued auto-encoder approach

G. M. Frusque; D. Mitchell; J. Blanche; D. Flynn; O. Fink 

Mechanical Systems and Signal Processing. 2024. Vol. 208, p. 111022. DOI : 10.1016/j.ymssp.2023.111022.

A Study on Gradient-based Meta-learning for Robust Deep Digital Twins

R. P. Theiler; M. Viscione; O. Fink 

2023-09-01. The 33rd European Safety and Reliability Conference (ESREL 2023), Southampton, UK, September 3-7,2023. p. 2419-2420. DOI : 10.3850/978-981-18-8071-1.

Learning Dynamics of Spring-Mass Models with Physics-Informed Graph Neural Networks

V. Sharma; M. Manav; L. De Lorenzis; O. Fink 

2023. 33rd European Safety and Reliability Conference (ESREL 2023), Southampton, UK, 3–8 September 2023. p. 2421-2422. DOI : 10.3850/978-981-18-8071-1_P508-cd.

Controlled physics-informed data generation for deep learning-based remaining useful life prediction under unseen operation conditions

J. Xiong; O. Fink; J. Zhou; Y. Ma 

Mechanical Systems and Signal Processing. 2023. Vol. 197, p. 110359. DOI : 10.1016/j.ymssp.2023.110359.

Uncertainty quantification in machine learning for engineering design and health prognostics: A tutorial

V. Nemani; L. Biggio; X. Huan; Z. Hu; O. Fink et al. 

Mechanical Systems and Signal Processing. 2023. Vol. 205, p. 110796. DOI : 10.1016/j.ymssp.2023.110796.

Smart filter aided domain adversarial neural network for fault diagnosis in noisy industrial scenarios

B. Dai; G. M. Frusque; T. Li; Q. Li; O. Fink 

Engineering Applications of Artificial Intelligence. 2023. Vol. 126, p. 107202. DOI : 10.1016/j.engappai.2023.107202.

Vibrational NDT with Under-sampled Data through Physics-informed Neural Networks

S. Hedayatrasa; O. Fink; M. Kersemans 

2023-08-01. 13th European Conference on Non-Destructive Testing (ECNDT) 2023, Lisbon, July 3-7, 2023.

Generating Controlled Physics-Informed Time-to-failure Trajectories for Prognostics in Unseen Operational Conditions

J. Xiong; J. Zhou; Y. Ma; O. Fink 

2023. ESREL, Southampton, UK, September 3-8, 2023. p. 2417-2418. DOI : 10.3850/978-981-18-8071-1_P732-cd.

Segmenting Without Annotating: Crack Segmentation and Monitoring via Post-Hoc Classifier Explanations

F. E. Forest; H. L. P. Porta; D. Tuia; O. Fink 

2023. ESREL 2023, Southampton, UK, September 3-8, 2023. p. 1392-1393. DOI : 10.3850/978-981-18-8071-1_P290-cd.

Exploiting Explanations to Detect Misclassifications of Deep Learning Models in Power Grid Visual Inspection

G. Floreale; P. Baraldi; E. Zio; O. Fink 

2023. 33rd European Safety and Reliability Conference, Southampton, UK, September 3-8, 2023. p. 3123-3124. DOI : 10.3850/978-981-18-8071-1_P662-cd.

Calibrated Adaptive Teacher for Domain Adaptive Intelligent Fault Diagnosis

F. E. Forest; O. Fink 

2023. DOI : 10.48550/arxiv.2312.02826.

Learnable Wavelet Transform and Domain Adversarial Learning for Enhanced Bearing Fault Diagnosis

B. Dai; G. M. Frusque; Q. Li; O. Fink 

2023. 33rd European Safety and Reliability Conference, Southampton, UK, September 3-8, 2023. DOI : 10.3850/978-981-18-8071-1_P208-cd.

Complex-Valued-Autoencoder for Structural Health Monitoring with Frequency Modulated Continuous Wave Radar

G. M. Frusque; D. Mitchell; J. Blanche; D. Flynn; O. Fink 

2023. ESREL European Safety & Reliability Conference 2023, Southampton, UK, September 3-8, 2023. p. 3064-3065. DOI : 10.3850/978-981-18-8071-1_P600-cd.

Learning Linearized Degradation of Health Indicators using Deep Koopman Operator Approach

S. Garmaev; O. Fink 

2023. ESREL, Southampton, UK, September 3-8, 2023. p. 2423-2424. DOI : 10.3850/978-981-18-8071-1_P470-cd.

A Comparison of Residual-based Methods on Fault Detection

C-C. Hsu; G. M. Frusque; O. Fink 

2023. 15th Annual Conference of the Prognostics and Health Management Society (PHM 2023), Salt Lake City, Utah , October 28 – November 2, 2023. DOI : 10.36001/phmconf.2023.v15i1.3444.

Graph neural networks for dynamic modeling of roller bearings

V. Sharma; J. Ravesloot; C. Taal; O. Fink 

2023. Annual Conference of the Prognostics and Health Management Society. Proceedings, Salt Lake City, Utah , October 28 – November 2, 2023. DOI : 10.36001/phmconf.2023.v15i1.3467.

Spatial-Temporal Graph Attention Fuser for Calibration in IoT Air Pollution Monitoring Systems

K. Faghih Niresi; M. Zhao; H. Bissig; H. Baumann; O. Fink 

2023. IEEE SENSORS, Vienna, Austria, October 29-November 01, 2023. DOI : 10.1109/SENSORS56945.2023.10325090.

DARE-GRAM : Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices

I. Nejjar; Qin Wang; O. Fink 

2023. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, June 17-24, 2023. p. 11744-11754. DOI : 10.1109/CVPR52729.2023.01130.

SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization

H. Dong; I. Nejjar; H. Sun; E. Chatzi; O. Fink 

2023. Thirty-seventh Conference on Neural Information Processing Systems, New Orleans, Louisiana, USA, December 10-16, 2023.

Learning Physics-Consistent Particle Interactions

O. Fink; Z. Han; D. S. Kammer 

2023. International Conference on Particle-Based Methods. Fundamentals and Applications, Milan, Italy, October 9-11, 2023.

Domain knowledge-informed synthetic fault sample generation with health data map for cross-domain planetary gearbox fault diagnosis

J. M. Ha; O. Fink 

Mechanical Systems And Signal Processing. 2023-11-01. Vol. 202, p. 110680. DOI : 10.1016/j.ymssp.2023.110680.

Ageing-aware battery discharge prediction with deep learning

L. Biggio; T. Bendinelli; C. Kulkarni; O. Fink 

Applied Energy. 2023-09-15. Vol. 346, p. 121229. DOI : 10.1016/j.apenergy.2023.121229.

Multi-agent reinforcement learning with graph convolutional neural networks for optimal bidding strategies of generation units in electricity markets

P. Rokhforoz; M. Montazeri; O. Fink 

Expert Systems With Applications. 2023-04-13. Vol. 225, p. 120010. DOI : 10.1016/j.eswa.2023.120010.

Incentive Mechanism in the Sponsored Content Market With Network Effects

M. Montazeri; P. Rokhforoz; H. Kebriaei; O. Fink 

Ieee Transactions On Computational Social Systems. 2023-03-27. DOI : 10.1109/TCSS.2023.3257233.

Filter-Informed Spectral Graph Wavelet Networks for Multiscale Feature Extraction and Intelligent Fault Diagnosis

T. Li; C. Sun; O. Fink; Y. Yang; X. Chen et al. 

Ieee Transactions On Cybernetics. 2023-03-23. DOI : 10.1109/TCYB.2023.3256080.

Fusing physics-based and deep learning models for prognostics

M. Arias Chao; C. kulkarni; K. Goebel; O. Fink 

Reliability Engineering & System Safety. 2023-01-22. Vol. 217, p. 107961. DOI : 10.1016/j.ress.2021.107961.

Fully learnable deep wavelet transform for unsupervised monitoring of high-frequency time series

G. Michau; G. M. Frusque; O. Fink 

Proceedings of the National Academy of Sciences. 2023-02-18. Vol. 119, num. 8, p. e2106598119. DOI : 10.1073/pnas.2106598119.

Controlled generation of unseen faults for Partial and Open-Partial domain adaptation

K. Rombach; G. Michau; O. Fink 

Reliability Engineering & System Safety. 2023-02-01. Vol. 230, p. 108857. DOI : 10.1016/j.ress.2022.108857.

A comprehensive review of digital twin-part 2: roles of uncertainty quantification and optimization, a battery digital twin, and perspectives (vol 66, 1, 2022)

A. Thelen; X. Zhang; O. Fink; Y. Lu; S. Ghosh et al. 

Structural And Multidisciplinary Optimization. 2023-01-01. Vol. 66, num. 1, p. 23. DOI : 10.1007/s00158-022-03476-7.

Safe multi-agent deep reinforcement learning for joint bidding and maintenance scheduling of generation units

P. Rokhforoz; M. Montazeri; O. Fink 

Reliability Engineering & System Safety. 2023-01-10. Vol. 232, p. 109081. DOI : 10.1016/j.ress.2022.109081.

A comprehensive review of digital twin-part 2: roles of uncertainty quantification and optimization, a battery digital twin, and perspectives

A. Thelen; X. Zhang; O. Fink; Y. Lu; S. Ghosh et al. 

Structural And Multidisciplinary Optimization. 2023-01-01. Vol. 66, num. 1, p. 1. DOI : 10.1007/s00158-022-03410-x.

Multi-agent actor-critic with time dynamical opponent model

Y. Tian; K. -R. Kladny; Q. Wang; Z. Huang; O. Fink 

Neurocomputing. 2023-01-14. Vol. 517, p. 165-172. DOI : 10.1016/j.neucom.2022.10.045.

DG-Mix: Domain Generalization for Anomalous Sound Detection Based on Self-Supervised Learning

I. Nejjar; J. Meunier-Pion; G. M. Frusque; O. Fink 

2022. DCASE 2022 Workshop: Workshop on Detection and Classification of Acoustic Scenes and Events, Nancy, France, 3-4 November 2022.

Multi-agent maintenance scheduling of generation unit in electricity market using safe deep reinforcement learning algorithm

P. Rokhforoz; O. Fink 

2022-09-01. 32nd European Safety and Reliability Conference (ESREL 2022), Dublin, Ireland, August 28 – September 1, 2022.

Contrastive Feature Learning for Railway Infrastructure Fault Diagnostic

O. Fink; K. Rombach; G. Michau; K. Ratnasabapathy; W. Bürzle et al. 

2022-08-22. 32nd European Safety and Reliability Conference (ESREL 2022), Dublin, Ireland, August 28 – September 1, 2022. p. 1875 – 1881. DOI : 10.3850/978-981-18-5183-4_S02-07-645-cd.

Vacuum Circuit Breaker Closing Time Key Moments Detection via Vibration Monitoring: A Run-to-Failure Study

C-C. Hsu; G. M. Frusque; M. Muratovic; C. M. Franck; O. Fink 

2022-08-16. IEEE International Conference on Systems, Man and Cybernetics, Prague, Czech Republic, October 9-12, 2022. p. 254-260. DOI : 10.1109/SMC53654.2022.9945354.

Learnable Wavelet Packet Transform for Data-Adapted Spectrograms

G. M. Frusque; O. Fink 

2022-04-27. ICASSP 2022 – IEEE International Conference on Acoustics, Speech and Signal Processing, Singapore, May 23-27, 2022. p. 3119-3123. DOI : 10.1109/ICASSP43922.2022.9747491.

Artificial intelligence across company borders

O. Fink; T. Netland; S. Feuerriegelc 

Communications of the ACM. 2022-01-03. Vol. 65, num. 1, p. 34-36. DOI : 10.1145/3470449.

Maintenance scheduling of manufacturing systems based on optimal price of the network

P. Rokhforoz; O. Fink 

Reliability Engineering & System Safety. 2022-01-03. Vol. 217, p. 108088. DOI : 10.1016/j.ress.2021.108088.

Real-time model calibration with deep reinforcement learning

Y. Tian; M. A. Chao; C. Kulkarni; K. Goebel; O. Fink 

Mechanical Systems and Signal Processing. 2022-02-15. Vol. 165, p. 108284. DOI : 10.1016/j.ymssp.2021.108284.

Learning physics-consistent particle interactions

Z. Han; D. S. Kammer; O. Fink 

PNAS Nexus. 2022-11-18. Vol. 1, num. 5, p. 264. DOI : 10.1093/pnasnexus/pgac264.

Acceleration-Guided Acoustic Signal Denoising Framework Based on Learnable Wavelet Transform Applied to Slab Track Condition Monitoring

B. Dai; G. Frusque; Q. Li; O. Fink 

Ieee Sensors Journal. 2022-12-15. Vol. 22, num. 24, p. 24140-24149. DOI : 10.1109/JSEN.2022.3218182.

Generalization of an Encoder-Decoder LSTM model for flood prediction in ungauged catchments

Y. Zhang; S. Ragettli; P. Molnar; O. Fink; N. Peleg 

Journal Of Hydrology. 2022-11-01. Vol. 614, p. 128577. DOI : 10.1016/j.jhydrol.2022.128577.

A comprehensive review of digital twin – part 1: modeling and twinning enabling technologies

A. Thelen; X. Zhang; O. Fink; Y. Lu; S. Ghosh et al. 

Structural And Multidisciplinary Optimization. 2022-12-01. Vol. 65, num. 12, p. 354. DOI : 10.1007/s00158-022-03425-4.

Continual Test-Time Domain Adaptation

Q. Wang; O. Fink; L. Van Gool; D. Dai 

2022-01-01. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, Jun 18-24, 2022. p. 7191-7201. DOI : 10.1109/CVPR52688.2022.00706.

A prescriptive Dirichlet power allocation policy with deep reinforcement learning

Y. Tian; M. Han; C. Kulkarni; O. Fink 

Reliability Engineering & System Safety. 2022-08-01. Vol. 224, p. 108529. DOI : 10.1016/j.ress.2022.108529.