Publications by Gaëtan Michel Frusque

Classifier-free diffusion-based weakly-supervised approach for health indicator derivation in rotating machines: Advancing early fault detection and condition monitoring

Deriving health indicators of rotating machines is crucial for their maintenance. However, this process is challenging for the prevalent adopted intelligent methods since they may take the whole data distributions, not only introducing noise interference b ...

2025

Explainable AI guided unsupervised fault diagnostics for high-voltage circuit breakers

Olga Fink, Florent Evariste Forest, Gaëtan Michel Frusque

Commercial high-voltage circuit breaker (CB) condition monitoring systems rely on directly observable physical parameters such as gas filling pressure with pre-defined thresholds. While these parameters are crucial, they only cover a small subset of malfun ...

2025

Continuous Health State Monitoring of High Voltage Circuit Breakers

Olga Fink, Gaëtan Michel Frusque

Circuit breakers (CBs) are renowned for their high reliability and long lifespan. As a result, many CBs installed decades ago are now approaching their predefined end of service life. However, this predefined service life does not always reflect the actual ...

Institute of Electrical and Electronics Engineers (IEEE)2025

Robust time series denoising with learnable wavelet packet transform

Olga Fink, Gaëtan Michel Frusque

Noise in the data is one of the main cause of model performance drop. Denoising is therefore a critical step in most data pipelines. In this paper we propose to fuse the learning abilities of Neural Network with the well-proven efficiency of the wavelet pa ...

2024

Semisupervised Health Index Monitoring With Feature Generation and Fusion

Olga Fink, Ismail Nejjar, Gaëtan Michel Frusque

—The health index (HI) is crucial for evaluating system health, important for tasks, such as anomaly detection and remaining useful life prediction of safety-critical systems. Real-time, meticulous monitoring of system conditions is essential, especially i ...

2024

Informed Graph Learning By Domain Knowledge Injection and Smooth Graph Signal Representation

Lukas Kühn, Olga Fink, Keivan Faghih Niresi, Gaëtan Michel Frusque

Graph signal processing represents an important advancement in the field of data analysis, extending conventional signal processing methodologies to complex networks and thereby facilitating the exploration of informative patterns and structures across var ...

IEEE2024

NNG-Mix: Improving Semi-Supervised Anomaly Detection with Pseudo-Anomaly Generation

Olga Fink, Gaëtan Michel Frusque

Anomaly detection (AD) is essential in identifying rare and often critical events in complex systems, finding applications in fields such as network intrusion detection, financial fraud detection, and fault detection in infrastructure and industrial system ...

2024

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

Olga Fink, Gaëtan Michel Frusque

The occurrence of manufacturing defects in wind turbine blade (WTB) production can result in significant increases in operation and maintenance costs of WTBs, reduce capacity factors of wind farms, and occasionally lead to severe and disastrous consequence ...

2024

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

Olga Fink, Gaëtan Michel Frusque, Tianfu Li, Qi Li, Baorui Dai

The application of unsupervised domain adaptation (UDA)-based fault diagnosis methods has shown significant efficacy in industrial settings, facilitating the transfer of operational experience and fault signatures between different operating conditions, di ...

2023

A Comparison of Residual-based Methods on Fault Detection

Olga Fink, Gaëtan Michel Frusque

An important initial step in fault detection for complex industrial systems is gaining an understanding of their health condition. Subsequently, continuous monitoring of this health condition becomes crucial to observe its evolution, track changes over tim ...

PHM Society2023