A5064722162- Machine Fault Diagnosis Techniques
- Gear and Bearing Dynamics Analysis
- Fault Detection and Control Systems
- Engineering Diagnostics and Reliability
- Structural Health Monitoring Techniques
- Non-Destructive Testing Techniques
- Advanced machining processes and optimization
- Tribology and Lubrication Engineering
- Mechanical Failure Analysis and Simulation
- Anomaly Detection Techniques and Applications
- Ultrasonics and Acoustic Wave Propagation
- Advanced Measurement and Detection Methods
- Speech and Audio Processing
- Vehicle Noise and Vibration Control
- Advanced Measurement and Metrology Techniques
- Optical measurement and interference techniques
- Magnetic Bearings and Levitation Dynamics
- Engineering Applied Research
- Control Systems in Engineering
- Blind Source Separation Techniques
- Electric Motor Design and Analysis
- Icing and De-icing Technologies
- Domain Adaptation and Few-Shot Learning
- Spectroscopy and Chemometric Analyses
- Advanced Neural Network Applications
KU Leuven
2016-2025
Flanders Make (Belgium)
2016-2025
Psychiatric Medicine Associates
2019
Sirris
2019
Laboratoire de Mécanique des Contacts et des Structures
2014-2016
Université de Lyon
2016
National Technical University of Athens
2009-2014
Université Claude Bernard Lyon 1
2013
Laboratoire de Mécanique et d’Acoustique
2012
Cranfield University
2010-2011
Deep neural networks present very competitive results in mechanical fault diagnosis. However, training deep models require high computing power while the performance of architectures extracting discriminative features for decision making often suffers from lack sufficient data. In this paper, a transferable convolutional network (CNN) is proposed to improve learning target tasks. First, one-dimensional CNN constructed and pretrained based on large source task datasets. Then transfer strategy...
Recently, deep learning-based intelligent fault diagnosis techniques have obtained good classification performance with amount of supervised training data. However, domain shift problem between the and testing data usually occurs due to variation in operating conditions interferences environment noise. Transfer learning provides a promising tool for handling cross-domain problems by leveraging knowledge from source help target domain. Most existing studies attempt learn both features common...
The KDamper is a novel passive vibration isolation and damping concept, based essentially on the optimal combination of appropriate stiffness elements, which include negative element. concept does not require any reduction in overall structural stiffness, thus overcoming corresponding inherent disadvantage “Quazi Zero Stiffness” (QZS) isolators, drastic structure load bearing capacity. Compared to traditional Tuned Mass damper (TMD), can achieve better characteristics, without need...
State-of-the-art deep learning models remain data-intensive, requiring large training datasets to ensure their generalization ability. However, in industry, it is quite expensive or impractical obtain massive samples for condition monitoring practitioners. This article proposes a simulation-driven domain adaptation method circumvent the data deficiency issue using physical-based simulations. A bearing phenomenological model developed generate simulated vibration signals. In frame of transfer...
Abstract As fixed-wing unmanned aerial vehicles (FW-UAVs) are used for diverse civil and scientific missions, failure incidents on the rise. Recent rapid developments in deep learning (DL) techniques offer advanced solutions fault diagnosis of vehicles. However, most existing DL-based diagnostic models only perform well when trained massive amounts labeled data, which challenging to collect due complexity FW-UAVs systems service environments. To address these issues, this paper presents a...
Early fault diagnosis of bearings is crucial for ensuring safe and reliable operations. Convolutional Neural Networks (CNNs) have achieved significant breakthroughs in machinery diagnosis. However, complex varying working conditions can lead to inter-class similarity intra-class variability datasets, making it more challenging CNNs learn discriminative features. Furthermore, are often considered "black boxes" lack sufficient interpretability the field. To address these issues, this paper...
Intelligent fault diagnosis method based on deep learning has achieved promising results in recent years. However, the performance of most models requires many labeled samples for training, which is usually impractical real industry situations. At same time, large amounts unlabeled operational data are easily available. It great significance to efficiently harness and leverage wealth information encapsulated within build a robust deep-learning model with limited samples. Thus, we propose...