Xuhui Huang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xuhui Huang has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Yiming Deng
Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI 48824, USA
5 shared publications Yiming Deng
Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, United States of America
3 shared publicationsCiaron Hamilton
Department of Electrical and Computer Engineering, Michigan State University, East Lansing, Michigan, USA
2 shared publicationsLalita Udpa
Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, United States of America
2 shared publications- Lalita Udpa
Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA
2 shared publications - Lei Peng
Michigan State University
2 shared publications
Latest Publications
- 15 July 2025
- Published by Elsevier in NDT & E International
- Vol. 156
Geometry complex structure inspection using stretchable eddy current array sensors
- 15 July 2025
- Published by Elsevier in NDT & E International
- Vol. 156
Geometry complex structure inspection using stretchable eddy current array sensors
- 20 November 2024
- Published by Elsevier in NDT & E International
- Vol. 150
A novel multi-fidelity Gaussian process regression approach for defect characterization in motion-induced eddy current testing
- 20 November 2024
- Published by Elsevier in NDT & E International
- Vol. 150
A novel multi-fidelity Gaussian process regression approach for defect characterization in motion-induced eddy current testing
- Open Access
- 30 September 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (19) , 8811
A Hybrid GAN-Inception Deep Learning Approach for Enhanced Coordinate-Based Acoustic Emission Source Localization
In this paper, we propose a novel approach to coordinate-based acoustic emission (AE) source localization to address the challenges of limited and imbalanced datasets from fiber-optic AE sensors used for structural health monitoring (SHM). We have developed a hybrid deep learning model combining four generative adversarial network (GAN) variants for data augmentation with an adapted inception neural network for regression-based prediction. The experimental setup features a single fiber-optic AE sensor based on a tightly coiled fiber-optic Fabry-Perot interferometer formed by two identical fiber Bragg gratings. AE signals were generated using the Hsu-Nielsen pencil lead break test on a grid-marked thin aluminum plate with 35 distinct locations, simulating real-world structural monitoring conditions in bounded isotropic plate-like structures. It is demonstrated that the single-sensor configuration can achieve precise localization, avoiding the need for a multiple sensor array. The GAN-based signal augmentation expanded the dataset from 900 to 4500 samples, with the Wasserstein distance between the original and synthetic datasets decreasing by 83% after 2000 training epochs, demonstrating the high fidelity of the synthetic data. Among the GAN variants, the standard GAN architecture proved the most effective, outperforming other variants in this specific application. The hybrid model exhibits superior performance compared to non-augmented deep learning approaches, with the median error distribution comparisons revealing a significant 50% reduction in prediction errors, accompanied by substantially improved consistency across various AE source locations. Overall, this developed hybrid approach offers a promising solution for enhancing AE-based SHM in complex infrastructures, improving damage detection accuracy and reliability for more efficient predictive maintenance strategies.
- 30 September 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (19) , 8811
Open AccessA Hybrid GAN-Inception Deep Learning Approach for Enhanced Coordinate-Based Acoustic Emission Source Localization
In this paper, we propose a novel approach to coordinate-based acoustic emission (AE) source localization to address the challenges of limited and imbalanced datasets from fiber-optic AE sensors used for structural health monitoring (SHM). We have developed a hybrid deep learning model combining four generative adversarial network (GAN) variants for data augmentation with an adapted inception neural network for regression-based prediction. The experimental setup features a single fiber-optic AE sensor based on a tightly coiled fiber-optic Fabry-Perot interferometer formed by two identical fiber Bragg gratings. AE signals were generated using the Hsu-Nielsen pencil lead break test on a grid-marked thin aluminum plate with 35 distinct locations, simulating real-world structural monitoring conditions in bounded isotropic plate-like structures. It is demonstrated that the single-sensor configuration can achieve precise localization, avoiding the need for a multiple sensor array. The GAN-based signal augmentation expanded the dataset from 900 to 4500 samples, with the Wasserstein distance between the original and synthetic datasets decreasing by 83% after 2000 training epochs, demonstrating the high fidelity of the synthetic data. Among the GAN variants, the standard GAN architecture proved the most effective, outperforming other variants in this specific application. The hybrid model exhibits superior performance compared to non-augmented deep learning approaches, with the median error distribution comparisons revealing a significant 50% reduction in prediction errors, accompanied by substantially improved consistency across various AE source locations. Overall, this developed hybrid approach offers a promising solution for enhancing AE-based SHM in complex infrastructures, improving damage detection accuracy and reliability for more efficient predictive maintenance strategies.
- Open Access
- 31 May 2024
- Published by IOP Publishing in Engineering Research Express
- Vol. 6 (2) , 025222
Deep learning-assisted structural health monitoring: acoustic emission analysis and domain adaptation with intelligent fiber optic signal processing
Structural health monitoring aims to detect damage progression in materials. This study focuses on categorizing crack stages, a critical aspect of monitoring structural integrity. By leveraging acoustic emission (AE) monitoring, cracks can be analyzed in a data-driven manner. However, applying AE analysis poses several challenges, including discrepancies between simulated AE data from models and experimental data from the field, as well as class imbalance in crack progression data, with a scarcity of late-stage data. To bridge the gap between theory and experiments, our approach employs domain adaptation to synchronize simulated and actual AE data. The model learns robust domain-invariant features through meticulous experimentation across training epochs. Quantitative analysis of the model’s performance provides key insights. F1 scores vary with feature counts, and domain adaptation outperforms by 20% on highly imbalanced datasets. This emphasizes the model’s adaptability for precise crack classification, even with underrepresented damage classes. In summary, this study advances structural health monitoring by offering a solid AE analysis approach. Core contributions include reconciling simulated and experimental data discrepancies, tackling class imbalance, optimizing feature extraction, and demonstrating robust crack stage categorization. The insights gained highlight the merits of domain adaptation and data-driven AE analysis for predicting crack progression.
- 31 May 2024
- Published by IOP Publishing in Engineering Research Express
- Vol. 6 (2) , 025222
Open AccessDeep learning-assisted structural health monitoring: acoustic emission analysis and domain adaptation with intelligent fiber optic signal processing
Structural health monitoring aims to detect damage progression in materials. This study focuses on categorizing crack stages, a critical aspect of monitoring structural integrity. By leveraging acoustic emission (AE) monitoring, cracks can be analyzed in a data-driven manner. However, applying AE analysis poses several challenges, including discrepancies between simulated AE data from models and experimental data from the field, as well as class imbalance in crack progression data, with a scarcity of late-stage data. To bridge the gap between theory and experiments, our approach employs domain adaptation to synchronize simulated and actual AE data. The model learns robust domain-invariant features through meticulous experimentation across training epochs. Quantitative analysis of the model’s performance provides key insights. F1 scores vary with feature counts, and domain adaptation outperforms by 20% on highly imbalanced datasets. This emphasizes the model’s adaptability for precise crack classification, even with underrepresented damage classes. In summary, this study advances structural health monitoring by offering a solid AE analysis approach. Core contributions include reconciling simulated and experimental data discrepancies, tackling class imbalance, optimizing feature extraction, and demonstrating robust crack stage categorization. The insights gained highlight the merits of domain adaptation and data-driven AE analysis for predicting crack progression.
- 20 February 2024
- Published by Taylor & Francis in Research in Nondestructive Evaluation
- Vol. 35 (2) , 102-118
Fast VGG: An Advanced Pre-Trained Deep Learning Framework for Multi-Layered Composite NDE via Multifrequency Near-Field Microwave Imaging
- 20 February 2024
- Published by Taylor & Francis in Research in Nondestructive Evaluation
- Vol. 35 (2) , 102-118
Fast VGG: An Advanced Pre-Trained Deep Learning Framework for Multi-Layered Composite NDE via Multifrequency Near-Field Microwave Imaging
- Open Access
- 16 July 2021
- Published by ASME International
A Kriging Based Fast and Efficient Method for Defect Detection in Massive Pipelines Using Magnetic Flux Leakages
Pipeline systems in service continue to degrade with passage of time. For public safety it is of utmost importance to monitor pipelines and detect new defects within the pipelines. Magnetic flux leakage (MFL) testing is a widely used non-destructive evaluation (NDE) technique for defect detections within the pipelines, particularly those composed of ferromagnetic materials.
- 16 July 2021
- Published by ASME International
Open AccessA Kriging Based Fast and Efficient Method for Defect Detection in Massive Pipelines Using Magnetic Flux Leakages
Pipeline systems in service continue to degrade with passage of time. For public safety it is of utmost importance to monitor pipelines and detect new defects within the pipelines. Magnetic flux leakage (MFL) testing is a widely used non-destructive evaluation (NDE) technique for defect detections within the pipelines, particularly those composed of ferromagnetic materials.
- Open Access
- 7 June 2021
- Published by ASME International in Journal of Nondestructive Evaluation, Diagnostics and Prognostics of Engineering Systems
- Vol. 5 (1)
A Kriging-Based Magnetic Flux Leakage Method for Fast Defect Detection in Massive Pipelines
Systems in service continue to degrade with the passage of time. Pipelines are among the most common systems that wear away with usage. For public safety, it is of utmost importance to monitor pipelines. Magnetic flux leakage (MFL) testing is a widely used nondestructive evaluation (NDE) technique for defect detections within the pipelines, particularly those composed of ferromagnetic materials. Pipeline inspection gauge (PIG) procedure based on line scans can collect accurate MFL readings for defect detection. However, in real world, applications involving large pipe sectors such as extensive scanning techniques are extremely time consuming and costly. In this article, we develop a fast and cheap methodology that does not need MFL readings at all the points used in traditional PIG procedures but conducts defect detection with similar accuracy. We consider an under-sampling based scheme that collects MFL at uniformly chosen random scan points over large lattices instead of extensive PIG scans over all lattice points. On the basis of readings from the chosen random scan points, we use kriging to reconstruct MFL readings. Thereafter, we use thresholding-based segmentation on the reconstructed data for detecting defective areas. We demonstrate the applicability of our methodology on synthetic data generated using finite element models and on MFL data collected via laboratory experiments. In these experiments, spanning a wide range of defect types, our proposed novel MFL-based NDE methodology is witnessed to have operating characteristics within the acceptable threshold of PIG-based traditional methods and thus provide an extremely cost-effective, fast procedure with competing error rates.
- 7 June 2021
- Published by ASME International in Journal of Nondestructive Evaluation, Diagnostics and Prognostics of Engineering Systems
- Vol. 5 (1)
Open AccessA Kriging-Based Magnetic Flux Leakage Method for Fast Defect Detection in Massive Pipelines
Systems in service continue to degrade with the passage of time. Pipelines are among the most common systems that wear away with usage. For public safety, it is of utmost importance to monitor pipelines. Magnetic flux leakage (MFL) testing is a widely used nondestructive evaluation (NDE) technique for defect detections within the pipelines, particularly those composed of ferromagnetic materials. Pipeline inspection gauge (PIG) procedure based on line scans can collect accurate MFL readings for defect detection. However, in real world, applications involving large pipe sectors such as extensive scanning techniques are extremely time consuming and costly. In this article, we develop a fast and cheap methodology that does not need MFL readings at all the points used in traditional PIG procedures but conducts defect detection with similar accuracy. We consider an under-sampling based scheme that collects MFL at uniformly chosen random scan points over large lattices instead of extensive PIG scans over all lattice points. On the basis of readings from the chosen random scan points, we use kriging to reconstruct MFL readings. Thereafter, we use thresholding-based segmentation on the reconstructed data for detecting defective areas. We demonstrate the applicability of our methodology on synthetic data generated using finite element models and on MFL data collected via laboratory experiments. In these experiments, spanning a wide range of defect types, our proposed novel MFL-based NDE methodology is witnessed to have operating characteristics within the acceptable threshold of PIG-based traditional methods and thus provide an extremely cost-effective, fast procedure with competing error rates.
- 14 September 2020
- Published by The Royal Society in Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
- Vol. 378 (2182) , 20190590
Capacitive imaging for adhesive bonds and quality evaluation
Defective adhesive bonds pose significant threats towards structural integrity due to reduced joint strength. The nature of the adhesion of two solids remains poorly understood since the adhesion phenomenon is relevant to so many scientific and technological areas. A concept that has been gaining our attention from the perspective of non-destructive testing is the properties discontinuity of the adhesion. Discontinued properties depend significantly on the quality of the interface that is formed between adhesive and substrate. In this research, discontinued electrical properties at the interface are considered. The simplified model is free from multidisciplinary knowledge of chemistry, fracture mechanics, mechanics of materials, rheology and other subjects. From a practical standpoint, this emphasizes the need to establish a good relationship between electrical properties of adhesive bonds and corresponding measurements. Capacitive imaging (CI) is a technique where the dielectric property of an object is determined from external capacitance measurements. Thus, it is potentially promising since adhesive and substrate differ in terms of dielectric property. At the interface between adhesive and substrate, discontinuity of the dielectric properties causes abrupt changes in electric field spatial distribution and thus alters capacitance measurement by simulating defects in adhesive joints regarding permittivity uncertainties. Further understanding of the cause of degraded adhesion quality can be obtained. This article is part of the theme issue ‘Advanced electromagnetic non-destructive evaluation and smart monitoring’.
- 14 September 2020
- Published by The Royal Society in Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
- Vol. 378 (2182) , 20190590
Capacitive imaging for adhesive bonds and quality evaluation
Defective adhesive bonds pose significant threats towards structural integrity due to reduced joint strength. The nature of the adhesion of two solids remains poorly understood since the adhesion phenomenon is relevant to so many scientific and technological areas. A concept that has been gaining our attention from the perspective of non-destructive testing is the properties discontinuity of the adhesion. Discontinued properties depend significantly on the quality of the interface that is formed between adhesive and substrate. In this research, discontinued electrical properties at the interface are considered. The simplified model is free from multidisciplinary knowledge of chemistry, fracture mechanics, mechanics of materials, rheology and other subjects. From a practical standpoint, this emphasizes the need to establish a good relationship between electrical properties of adhesive bonds and corresponding measurements. Capacitive imaging (CI) is a technique where the dielectric property of an object is determined from external capacitance measurements. Thus, it is potentially promising since adhesive and substrate differ in terms of dielectric property. At the interface between adhesive and substrate, discontinuity of the dielectric properties causes abrupt changes in electric field spatial distribution and thus alters capacitance measurement by simulating defects in adhesive joints regarding permittivity uncertainties. Further understanding of the cause of degraded adhesion quality can be obtained. This article is part of the theme issue ‘Advanced electromagnetic non-destructive evaluation and smart monitoring’.