Thi Phuong Khanh Nguyen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Thi Phuong Khanh Nguyen has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Kamal Medjaher
Production Engineering Laboratory, Toulouse University INPT-ENIT, Tarbes, France
16 shared publications - Ferhat Tamssaouet
LGP – ENIT
6 shared publications Kamal Medjaher
Univ. Toulouse, UTTOP, LGP, 47 Av. d’Azereix, 65000 Tarbes, France
6 shared publications- Marcos E. Orchard
University of Chile
5 shared publications - Moncef Soualhi
SUPMICROTECH, CNRS, Institut FEMTO-ST, Université de Franche-Comté, 25000 Besançon, France
4 shared publications - Bruno Castanier
LARIS - Laboratoire Angevin de Recherche en Ingénierie des Systèmes (Université d'Angers, LARIS | Polytech Angers, 62 Avenue Notre Dame du Lac - 49000 Angers - France)
3 shared publications
Latest Publications
- Open Access
- 3 July 2026
- Published by PHM Society in Phm Society European Conference
- Vol. 9 (1) , 1-9
Comparative Evaluation of Prognostic Models for Medium-Term Pressure Prediction in Gas Transmission Units
Gas pressure reduction and delivery stations are critical components of gas transmission networks, where pressure drifts may signal early degradation or control malfunction. Despite the availability of measurements supporting data-driven Prognostics and Health Management (PHM), medium-term forecasting remains difficult due to non-stationarities, operator adjustments, and heterogeneous setpoints. This study investigates 5-day-ahead pressure forecasting for maintenance planning and early detection of evolutions preceding threshold exceedances. A robust preprocessing pipeline addresses irregular sampling, missing data, and level shifts under real operating conditions. Two interpretable models are evaluated: SARIMAX, for seasonal and exogenous effects, and LightGBM, for nonlinear dynamics with feature-importance analysis. Performance is assessed on a homogeneous subset of gas pressure measurement recorders using standard regression metrics. The results emphasize not only predictive capability but also interpretability, positioning transparent forecasting models as scalable and auditable building blocks for PHM in gas transmission networks.
- 3 July 2026
- Published by PHM Society in Phm Society European Conference
- Vol. 9 (1) , 1-9
Open AccessComparative Evaluation of Prognostic Models for Medium-Term Pressure Prediction in Gas Transmission Units
Gas pressure reduction and delivery stations are critical components of gas transmission networks, where pressure drifts may signal early degradation or control malfunction. Despite the availability of measurements supporting data-driven Prognostics and Health Management (PHM), medium-term forecasting remains difficult due to non-stationarities, operator adjustments, and heterogeneous setpoints. This study investigates 5-day-ahead pressure forecasting for maintenance planning and early detection of evolutions preceding threshold exceedances. A robust preprocessing pipeline addresses irregular sampling, missing data, and level shifts under real operating conditions. Two interpretable models are evaluated: SARIMAX, for seasonal and exogenous effects, and LightGBM, for nonlinear dynamics with feature-importance analysis. Performance is assessed on a homogeneous subset of gas pressure measurement recorders using standard regression metrics. The results emphasize not only predictive capability but also interpretability, positioning transparent forecasting models as scalable and auditable building blocks for PHM in gas transmission networks.
- 2 December 2025
- Published by Elsevier in Neurocomputing
- Vol. 666
A modular deep learning methodology for multi-fault machine health diagnostics from sparse and imbalanced multimodal data
- 2 December 2025
- Published by Elsevier in Neurocomputing
- Vol. 666
A modular deep learning methodology for multi-fault machine health diagnostics from sparse and imbalanced multimodal data
- 29 September 2024
- Published by Springer Nature
- p. 101-136
Enhancing Trustworthiness in AI-Based Prognostics: A Comprehensive Review of Explainable AI for PHM
- 29 September 2024
- Published by Springer Nature
- p. 101-136
Enhancing Trustworthiness in AI-Based Prognostics: A Comprehensive Review of Explainable AI for PHM
- Top Cited Papers
- 9 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 255
Advancing multimodal diagnostics: Integrating industrial textual data and domain knowledge with large language models
- 9 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 255
Top Cited PapersAdvancing multimodal diagnostics: Integrating industrial textual data and domain knowledge with large language models
- Open Access
- 4 September 2023
- Published by PHM Society in PHM Society Asia-Pacific Conference
- Vol. 4 (1)
Explainable multimodal learning for predictive maintenance of steam generators
Prognostics and Health Management (PHM) is identified as an important lever for enhancing the development of predictive maintenance to ensure the reliability, availability, and safety of industrial systems. However, the efficiency of data- driven PHM approaches is dependent on the quality and quantity of data. Therefore, exploiting multiple data sources can provide additional, useful information than single-modal data. For instance, by incorporating multiple data sources, including condition monitoring data, images from cameras, and texts from maintenance technicians’ reports, multi-modal learning can provide a more comprehensive and accurate understanding of the system’s health. However, multi-modal deep learning is complex to understand. To address this complexity, it is crucial to incorporate explainable artificial intelligent techniques to provide clear and interpretable insights into how the model makes decisions. In this light, this paper proposes the application of the model-agnostic-explanation approach, i.e., SHAP, to explain the working mechanism of multimodal learning for the prediction of industrial steam generator degradation. Particularly, we determine the important features of each data modality and investigate how multimodal learning can overcome the issues of low-quality data from a single modality due to the additional information from other data modalities.
- 4 September 2023
- Published by PHM Society in PHM Society Asia-Pacific Conference
- Vol. 4 (1)
Open AccessExplainable multimodal learning for predictive maintenance of steam generators
Prognostics and Health Management (PHM) is identified as an important lever for enhancing the development of predictive maintenance to ensure the reliability, availability, and safety of industrial systems. However, the efficiency of data- driven PHM approaches is dependent on the quality and quantity of data. Therefore, exploiting multiple data sources can provide additional, useful information than single-modal data. For instance, by incorporating multiple data sources, including condition monitoring data, images from cameras, and texts from maintenance technicians’ reports, multi-modal learning can provide a more comprehensive and accurate understanding of the system’s health. However, multi-modal deep learning is complex to understand. To address this complexity, it is crucial to incorporate explainable artificial intelligent techniques to provide clear and interpretable insights into how the model makes decisions. In this light, this paper proposes the application of the model-agnostic-explanation approach, i.e., SHAP, to explain the working mechanism of multimodal learning for the prediction of industrial steam generator degradation. Particularly, we determine the important features of each data modality and investigate how multimodal learning can overcome the issues of low-quality data from a single modality due to the additional information from other data modalities.
- Open Access
- 21 July 2023
- Published by PHM Society in International Journal of Prognostics and Health Management
- Vol. 14 (2)
Open Heterogeneous Data for Condition Monitoring of Multi Faults in Rotating Machines Used in Different Operating Conditions
Rotating machines are widely used in several fields such as railways, renewable energies, robotics, etc. This diversity of application implies a large variety of faults of critical components susceptible to fail. For this purpose, prognostics and health management (PHM) is deployed to effectively monitor these components through the detection, diagnostics as well as prognostics of faults. In the literature, there exist numerous methods to ensure the above monitoring activities. However, few of them consider different failure types using heterogeneous data and various operating conditions. Also, there are no dominant methods that can be generalized for monitoring. For this reason, the genericity of these methods and their applicability in several systems is a crucial issue. To help researchers to achieve the above challenges, this paper presents a detailed description of data sources from experimental test benches. These data-sets correspond to different case studies that monitor the health states of multiple critical components in various operating conditions using numerous sensors.
- 21 July 2023
- Published by PHM Society in International Journal of Prognostics and Health Management
- Vol. 14 (2)
Open AccessOpen Heterogeneous Data for Condition Monitoring of Multi Faults in Rotating Machines Used in Different Operating Conditions
Rotating machines are widely used in several fields such as railways, renewable energies, robotics, etc. This diversity of application implies a large variety of faults of critical components susceptible to fail. For this purpose, prognostics and health management (PHM) is deployed to effectively monitor these components through the detection, diagnostics as well as prognostics of faults. In the literature, there exist numerous methods to ensure the above monitoring activities. However, few of them consider different failure types using heterogeneous data and various operating conditions. Also, there are no dominant methods that can be generalized for monitoring. For this reason, the genericity of these methods and their applicability in several systems is a crucial issue. To help researchers to achieve the above challenges, this paper presents a detailed description of data sources from experimental test benches. These data-sets correspond to different case studies that monitor the health states of multiple critical components in various operating conditions using numerous sensors.
- 2 June 2023
- Published by Springer Nature
- p. 167-197
Multimodal Machine Learning in Prognostics and Health Management of Manufacturing Systems
- 2 June 2023
- Published by Springer Nature
- p. 167-197
Multimodal Machine Learning in Prognostics and Health Management of Manufacturing Systems
- 12 September 2022
- Published by Elsevier in Computers in Industry
- Vol. 144
Dealing with prognostics uncertainties: Combination of direct and recursive remaining useful life estimations
- 12 September 2022
- Published by Elsevier in Computers in Industry
- Vol. 144
Dealing with prognostics uncertainties: Combination of direct and recursive remaining useful life estimations
- 9 September 2022
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 56 (4) , 3659-3709
A review of artificial intelligence methods for engineering prognostics and health management with implementation guidelines
- 9 September 2022
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 56 (4) , 3659-3709
A review of artificial intelligence methods for engineering prognostics and health management with implementation guidelines
- Top Cited Papers
- 26 February 2022
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 222
Probabilistic deep learning methodology for uncertainty quantification of remaining useful lifetime of multi-component systems
- 26 February 2022
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 222
Top Cited PapersProbabilistic deep learning methodology for uncertainty quantification of remaining useful lifetime of multi-component systems