no code implementations • 12 Apr 2024 • Mina Montazeri, Chetan Kulkarni, Olga Fink
This paper addresses the joint problem of mission planning and health-aware real-time control of opera-tional parameters to prescriptively control the duration of one discharge cycle of the battery pack.
no code implementations • 11 Apr 2024 • Keivan Faghih Niresi, Hugo Bissig, Henri Baumann, Olga Fink
To address this limitation, we adopt Graph Neural Networks (GNNs), renowned for their ability to effectively capture the complex relationships between sensor measurements.
no code implementations • 4 Apr 2024 • Raffael Theiler, Olga Fink
PSH are complex, highly interconnected systems encompassing electrical and hydraulic subsystems, each characterized by their respective underlying networks that can individually be represented as graphs.
no code implementations • 2 Apr 2024 • Mengjie Zhao, Cees Taal, Stephan Baggerohr, Olga Fink
Since temperature and vibration signals exhibit vastly different dynamics, we propose Heterogeneous Temporal Graph Neural Networks (HTGNN), which explicitly models these signal types and their interactions for effective load prediction.
1 code implementation • 18 Mar 2024 • Mariam Hassan, Florent Forest, Olga Fink, Malcolm Mielle
Thermal scene reconstruction exhibit great potential for ap- plications across a broad spectrum of fields, including building energy consumption analysis and non-destructive testing.
1 code implementation • 7 Feb 2024 • Yuan Tian, Wenqi Zhou, Hao Dong, David S. Kammer, Olga Fink
Our results demonstrate that Sym-Q excels not only in recovering underlying mathematical structures but also uniquely learns to efficiently refine the output expression based on reward signals, thereby discovering underlying expressions.
no code implementations • 24 Jan 2024 • Ismail Nejjar, Gaetan Frusque, Florent Forest, Olga Fink
Our approach serves a dual purpose: providing a measure of confidence in predictions and acting as a regularization of the embedding space.
no code implementations • 5 Dec 2023 • Gaëtan Frusque, Ismail Nejjar, Majid Nabavi, Olga Fink
The Health Index (HI) is crucial for evaluating system health, aiding tasks like anomaly detection and predicting remaining useful life for systems demanding high safety and reliability.
Semi-supervised Anomaly Detection Supervised Anomaly Detection
no code implementations • 5 Dec 2023 • Florent Forest, Olga Fink
However, deep learning models usually only perform well on the data distribution they have been trained on.
1 code implementation • 20 Nov 2023 • Hao Dong, Gaëtan Frusque, Yue Zhao, Eleni Chatzi, Olga Fink
While AD is typically treated as an unsupervised learning task due to the high cost of label annotation, it is more practical to assume access to a small set of labeled anomaly samples from domain experts, as is the case for semi-supervised anomaly detection.
1 code implementation • NeurIPS 2023 • Hao Dong, Ismail Nejjar, Han Sun, Eleni Chatzi, Olga Fink
In real-world scenarios, achieving domain generalization (DG) presents significant challenges as models are required to generalize to unknown target distributions.
no code implementations • 20 Sep 2023 • Florent Forest, Hugo Porta, Devis Tuia, Olga Fink
This paper proposes applying this methodology to segment and monitor surface cracks.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +1
no code implementations • 19 Sep 2023 • Vinay Sharma, Jens Ravesloot, Cees Taal, Olga Fink
Through this approach, we demonstrate the effectiveness of the GNN-based method in accurately predicting the dynamics of rolling element bearings, highlighting its potential for real-time health monitoring of rotating machinery.
no code implementations • 8 Sep 2023 • Keivan Faghih Niresi, Mengjie Zhao, Hugo Bissig, Henri Baumann, Olga Fink
The use of Internet of Things (IoT) sensors for air pollution monitoring has significantly increased, resulting in the deployment of low-cost sensors.
no code implementations • 5 Sep 2023 • Chi-Ching Hsu, Gaetan Frusque, Olga Fink
Fault detection is achieved by applying a threshold that is determined based on the healthy condition.
no code implementations • 3 Aug 2023 • Sergei Garmaev, Olga Fink
In this work, we demonstrate the successful extension of the previously proposed Deep Koopman Operator approach to learn the dynamics of industrial systems by transforming them into linearized coordinate systems, resulting in a latent representation that provides sufficient information for estimating the system's remaining useful life.
no code implementations • 20 Jul 2023 • Tianfu Li, Chuang Suna, Ruqiang Yan, Xuefeng Chen, Olga Fink
To overcome these limitations, we propose two graph neural network models: the graph wavelet autoencoder (GWAE), and the graph wavelet variational autoencoder (GWVAE).
1 code implementation • 7 Jul 2023 • Mengjie Zhao, Olga Fink
We rigorously evaluated DyEdgeGAT using both a synthetic dataset, simulating varying levels of fault severity, and a real-world industrial-scale multiphase flow facility benchmark with diverse fault types under varying operating conditions and detection complexities.
Ranked #1 on Unsupervised Anomaly Detection on PRONTO
no code implementations • 4 Jul 2023 • Baorui Dai, Gaëtan Frusque, Tianfu Li, Qi Li, Olga Fink
We validate the effectiveness of the proposed SFDANN method based on two fault diagnosis cases: one involving fault diagnosis of bearings in noisy environments and another involving fault diagnosis of slab tracks in a train-track-bridge coupling vibration system, where the transfer task involves transferring from numerical simulations to field measurements.
no code implementations • 19 Jun 2023 • Gaëtan Frusque, Daniel Mitchell, Jamie Blanche, David Flynn, Olga Fink
In this paper, we enhance the quality assurance of manufacturing utilizing FMCW radar as a non-destructive sensing modality.
no code implementations • 31 May 2023 • Jong Moon Ha, Olga Fink
CutPaste and FaultPaste are then applied to generate faulty samples based on the healthy data in the target domain, using domain knowledge and fault signatures extracted from the source domain, respectively.
no code implementations • 31 May 2023 • Tommaso Bendinelli, Luca Biggio, Daniel Nyfeler, Abhigyan Ghosh, Peter Tollan, Moritz Alexander Kirschmann, Olga Fink
The value of luxury goods, particularly investment-grade gemstones, is greatly influenced by their origin and authenticity, sometimes resulting in differences worth millions of dollars.
1 code implementation • 7 May 2023 • Venkat Nemani, Luca Biggio, Xun Huan, Zhen Hu, Olga Fink, Anh Tran, Yan Wang, Xiaoge Zhang, Chao Hu
In this tutorial, we aim to provide a holistic lens on emerging UQ methods for ML models with a particular focus on neural networks and the applications of these UQ methods in tackling engineering design as well as prognostics and health management problems.
no code implementations • 30 Apr 2023 • Zhichao Han, Olga Fink, David S. Kammer
First, it infers the interaction types of different edges collectively by explicitly encoding the correlation among incoming interactions with a joint distribution, and second, it allows handling systems with variable topological structure over time.
1 code implementation • 26 Apr 2023 • Hao Lu, Adam Thelen, Olga Fink, Chao Hu, Simon Laflamme
To quantify dataset similarity between clients without explicitly sharing data, each client sets aside a local test dataset and evaluates the other clients' model prediction accuracy and uncertainty on this test dataset.
no code implementations • 23 Apr 2023 • Jiawei Xiong, Olga Fink, Jian Zhou, Yizhong Ma
In this study, a novel hybrid framework combining the controlled physics-informed data generation approach with a deep learning-based prediction model for prognostics is proposed.
no code implementations • 27 Mar 2023 • Tianfu Li, Chuang Sun, Olga Fink, Yuangui Yang, Xuefeng Chen, Ruqiang Yan
Intelligent fault diagnosis has been increasingly improved with the evolution of deep learning (DL) approaches.
1 code implementation • 23 Mar 2023 • Ismail Nejjar, Qin Wang, Olga Fink
Unsupervised Domain Adaptation Regression (DAR) aims to bridge the domain gap between a labeled source dataset and an unlabelled target dataset for regression problems.
no code implementations • 3 Feb 2023 • Ismail Nejjar, Fabian Geissmann, Mengjie Zhao, Cees Taal, Olga Fink
Domain adaptation (DA) methods aim to address the domain shift problem by extracting domain invariant features.
1 code implementation • CVPR 2023 • Ismail Nejjar, Qin Wang, Olga Fink
Unsupervised Domain Adaptation Regression (DAR) aims to bridge the domain gap between a labeled source dataset and an unlabelled target dataset for regression problems.
no code implementations • 28 Aug 2022 • Katharina Rombach, Gabriel Michau, Wilfried Bürzle, Stefan Koller, Olga Fink
Our results demonstrate that the proposed approach is able to learn the ground truth health evolution of milling machines and the learned health indicator is suited for fault detection of railway wheels operated under various operating conditions by outperforming state-of-the-art methods.
no code implementations • 27 Aug 2022 • Adam Thelen, Xiaoge Zhang, Olga Fink, Yan Lu, Sayan Ghosh, Byeng D. Youn, Michael D. Todd, Sankaran Mahadevan, Chao Hu, Zhen Hu
This second paper presents a literature review of key enabling technologies of digital twins, with an emphasis on uncertainty quantification, optimization methods, open source datasets and tools, major findings, challenges, and future directions.
no code implementations • 26 Aug 2022 • Adam Thelen, Xiaoge Zhang, Olga Fink, Yan Lu, Sayan Ghosh, Byeng D. Youn, Michael D. Todd, Sankaran Mahadevan, Chao Hu, Zhen Hu
In part two of this review, the role of uncertainty quantification and optimization are discussed, a battery digital twin is demonstrated, and more perspectives on the future of digital twin are shared.
no code implementations • 16 Aug 2022 • Chi-Ching Hsu, Gaetan Frusque, Mahir Muratovic, Christian M. Franck, Olga Fink
A key to ensure a reliable operation of CBs is to monitor their condition.
no code implementations • 11 Aug 2022 • Pegah Rokhforoz, Olga Fink
This information on the system topology helps the agents to improve their bidding strategies and increase the profit.
Distributed Optimization Multi-agent Reinforcement Learning +2
no code implementations • 13 Jun 2022 • Gaetan Frusque, Olga Fink
We show that the learnable wavelet packet transform has the learning capabilities of deep learning methods while maintaining the robustness of standard signal processing approaches.
1 code implementation • 1 Jun 2022 • Luca Biggio, Tommaso Bendinelli, Chetan Kulkarni, Olga Fink
Electrochemical batteries are ubiquitous devices in our society.
no code implementations • 11 May 2022 • Baorui Dai, Gaëtan Frusque, Qi Li, Olga Fink
Therefore, only acoustic sensors (non-intrusive) need to be installed during the application phase, which is convenient and crucial for the condition monitoring of safety-critical infrastructure.
no code implementations • 12 Apr 2022 • Yuan Tian, Klaus-Rudolf Kladny, Qin Wang, Zhiwu Huang, Olga Fink
In this paper, we propose to exploit the fact that the agents seek to improve their expected cumulative reward and introduce a novel \textit{Time Dynamical Opponent Model} (TDOM) to encode the knowledge that the opponent policies tend to improve over time.
2 code implementations • CVPR 2022 • Qin Wang, Olga Fink, Luc van Gool, Dengxin Dai
However, real-world machine perception systems are running in non-stationary and continually changing environments where the target domain distribution can change over time.
no code implementations • 1 Feb 2022 • Zhichao Han, David S. Kammer, Olga Fink
Access to the governing particle interaction law is fundamental for a complete understanding of such systems.
no code implementations • 20 Jan 2022 • Yuan Tian, Minghao Han, Chetan Kulkarni, Olga Fink
Moreover, we demonstrate the applicability of the proposed algorithm on a prescriptive operation case, where we propose the Dirichlet power allocation policy and evaluate the performance on a case study of a set of multiple lithium-ion (Li-I) battery systems.
no code implementations • 20 Dec 2021 • Pegah Rokhforoz, Olga Fink
This paper proposes a safe reinforcement learning algorithm for generation bidding decisions and unit maintenance scheduling in a competitive electricity market environment.
1 code implementation • 5 Jul 2021 • Qin Wang, Cees Taal, Olga Fink
In this paper, we aim to overcome this limitation by integrating expert knowledge with domain adaptation in a synthetic-to-real framework for unsupervised fault diagnosis.
no code implementations • 3 May 2021 • Gabriel Michau, Gaetan Frusque, Olga Fink
In this paper, we propose a fully unsupervised deep learning framework that is able to extract a meaningful and sparse representation of raw HF signals.
1 code implementation • ICCV 2021 • Qin Wang, Dengxin Dai, Lukas Hoyer, Luc van Gool, Olga Fink
However, such a supervision is not always available.
Ranked #15 on Domain Adaptation on SYNTHIA-to-Cityscapes (using extra training data)
no code implementations • 8 Apr 2021 • Luca Biggio, Alexander Wieland, Manuel Arias Chao, Iason Kastanis, Olga Fink
Remaining Useful Life (RUL) estimation is the problem of inferring how long a certain industrial asset can be expected to operate within its defined specifications.
no code implementations • 7 Jan 2021 • Gabriel Rodriguez Garcia, Gabriel Michau, Herbert H. Einstein, Olga Fink
In tunnel construction projects, delays induce high costs.
no code implementations • 7 Dec 2020 • Ajaykumar Unagar, Yuan Tian, Manuel Arias-Chao, Olga Fink
In this paper, we implement a Reinforcement Learning-based framework for reliably and efficiently inferring calibration parameters of battery models.
no code implementations • 30 Sep 2020 • Katharina Rombach, Gabriel Michau, Olga Fink
In the first step, we identify outliers (including the mislabeled samples) based on the update in the hypothesis space.
no code implementations • 18 Aug 2020 • Gabriel Michau, Olga Fink
A solution to this problem is to perform unsupervised transfer learning (UTL), to transfer complementary data between different units.
no code implementations • 13 Aug 2020 • Gabriel Michau, Chi-Ching Hsu, Olga Fink
It provides interpretability of the results for the domain experts with the identification of the pulses that led to the detection of the PDs.
1 code implementation • ECCV 2020 • Yuan Tian, Qin Wang, Zhiwu Huang, Wen Li, Dengxin Dai, Minghao Yang, Jun Wang, Olga Fink
In this paper, we introduce a new reinforcement learning (RL) based neural architecture search (NAS) methodology for effective and efficient generative adversarial network (GAN) architecture search.
Ranked #13 on Image Generation on STL-10
no code implementations • 7 Jun 2020 • Yuan Tian, Manuel Arias Chao, Chetan Kulkarni, Kai Goebel, Olga Fink
The dynamic, real-time, and accurate inference of model parameters from empirical data is of great importance in many scientific and engineering disciplines that use computational models (such as a digital twin) for the analysis and prediction of complex physical processes.
no code implementations • 14 May 2020 • Oliver Ammann, Gabriel Michau, Olga Fink
We demonstrate that mixing kervolutional with convolutional layers in the encoder is more sensitive to variations in the input data and is able to detect anomalous time series in a better way.
no code implementations • 14 May 2020 • Gabriel Rodriguez Garcia, Gabriel Michau, Mélanie Ducoffe, Jayant Sen Gupta, Olga Fink
Essential characteristics of time series, situated outside the time domain, are often difficult to capture with state-of-the-art anomaly detection methods when no transformations have been applied to the time series.
no code implementations • 5 May 2020 • Olga Fink, Qin Wang, Markus Svensén, Pierre Dersin, Wan-Jui Lee, Melanie Ducoffe
Deep learning applications have been thriving over the last decade in many different domains, including computer vision and natural language understanding.
2 code implementations • 7 Jan 2020 • Qin Wang, Gabriel Michau, Olga Fink
We demonstrate in this paper that the performance of domain adversarial methods can be vulnerable to an incomplete target label space during training.
no code implementations • 28 Dec 2019 • Manuel Arias Chao, Bryan T. Adey, Olga Fink
With this work, we propose training a variational autoencoder (VAE) with labeled and unlabeled samples while inducing implicit supervision on the latent representation of the healthy conditions.
no code implementations • 22 Jul 2019 • Gabriel Michau, Olga Fink
In the early life of the system, the collected data is probably not representative of future operating conditions, making it challenging to train a robust model.
no code implementations • 15 Jul 2019 • Gabriel Michau, Olga Fink
Two approaches rely on the data from the unit to be monitored only: the baseline is trained on the early life of the unit.
no code implementations • 15 May 2019 • Qin Wang, Gabriel Michau, Olga Fink
Thanks to digitization of industrial assets in fleets, the ambitious goal of transferring fault diagnosis models fromone machine to the other has raised great interest.
1 code implementation • 12 Oct 2018 • Gabriel Michau, Yang Hu, Thomas Palmé, Olga Fink
The performance is first evaluated on a synthetic dataset that encompasses typical characteristics of condition monitoring data.