Publications | Xin YANG

2025

Sensors
Sensing Techniques for Structural Health Monitoring: A State-of-the-Art Review on Performance Criteria and New-Generation Technologies

Ali Mardanshahi, Abhilash Sreekumar, Xin Yang, and 2 more authors

Sensors, 2025

Abs Bib PDF

This systematic review examines the capabilities, challenges, and practical implementations of the most widely utilized and emerging sensing technologies in structural health monitoring (SHM) for infrastructures, addressing a critical research gap. While many existing reviews focus on individual methods, comprehensive cross-method comparisons have been limited due to the highly tailored nature of each technology. We address this by proposing a novel framework comprising five specific evaluation criteria—deployment suitability in SHM, hardware prerequisites, characteristics of the acquired signals, sensitivity metrics, and integration with Digital Twin environments—refined with subcriteria to ensure transparent and meaningful performance assessments. Applying this framework, we analyze both the advantages and constraints of established sensing technologies, including infrared thermography, electrochemical sensing, strain measurement, ultrasonic testing, visual inspection, vibration analysis, and acoustic emission. Our findings highlight critical trade-offs in scalability, environmental sensitivity, and diagnostic accuracy. Recognizing these challenges, we explore next-generation advancements such as self-sensing structures, unmanned aerial vehicle deployment, IoT-enabled data fusion, and enhanced Digital Twin simulations. These innovations aim to overcome existing limitations by enhancing real-time monitoring, data management, and remote accessibility. This review provides actionable insights for researchers and practitioners while identifying future research opportunities to advance scalable and adaptive SHM solutions for large-scale infrastructure.
@article{Ali25051424, author = {Mardanshahi, Ali and Sreekumar, Abhilash and Yang, Xin and Barman, Swarup Kumar and Chronopoulos, Dimitrios}, title = {Sensing Techniques for Structural Health Monitoring: A State-of-the-Art Review on Performance Criteria and New-Generation Technologies}, journal = {Sensors}, volume = {25}, year = {2025}, number = {5}, issn = {1424-8220}, keywords = {Structural health monitoring, Damage assessment, Sensing techniques, Performance criteria}, doi = {10.3390/s25051424}, bibtex_show = true, dimensions = {true} }
Mech. Syst. Signal Process
Using removable sensors in structural health monitoring: A Bayesian methodology for attachment-to-attachment uncertainty quantification

Chen Fang, Xin Yang, Konstantinos Gryllias, and 4 more authors

Mechanical Systems and Signal Processing, 2025

Abs Bib PDF

Structural responses are vulnerable to perturbations when subjected to variable environmental and operational conditions, thereby contributing to the slow uptake of Structural Health Monitoring (SHM) beyond academic research. More importantly, SHM systems using removable sensors face additional sensing variability due to the inherent uncertainty in sensor reattachment compared to permanently attached sensors. In this study, a novel probabilistic approach is developed for output-only damage detection utilizing ultrasonic guided waves. Experimental uncertainties and sensor attachment factors are simultaneously considered for the first time in a Bayesian context. The uncertainty introduced by reattached sensors is incorporated into the likelihood function in a comprehensive way. Bayesian model class selection using an adaptive sampling scheme is adopted to evaluate the evidence of discrete damage classes. A reference case to an aluminum plate with progressive notches is utilized to demonstrate the significant effects of attachment uncertainty on guided wave signals. The optimal data normalization model for guided wave processing under different attachment states is evaluated using the Mahalanobis distance. The notch length is identified accurately along with the uncertainty, even though the latent adhesive parameters cannot be estimated directly.
@article{FANG2025111973, title = {Using removable sensors in structural health monitoring: A Bayesian methodology for attachment-to-attachment uncertainty quantification}, journal = {Mechanical Systems and Signal Processing}, volume = {224}, pages = {111973}, year = {2025}, issn = {0888-3270}, doi = {10.1016/j.ymssp.2024.111973}, author = {Fang, Chen and Yang, Xin and Gryllias, Konstantinos and Vandepitte, Dirk and Liu, Xuemei and Zhang, Lihai and Chronopoulos, Dimitrios}, keywords = {Removable sensors, Sensing variability, Structural damage detection, Bayesian inference, Guided wave}, bibtex_show = true, dimensions = {true} }

2024

Measurement.
Transfer learning-based Gaussian process classification for lattice structure damage detection

Xin Yang, Amin Farrokhabadi, Ali Rauf, and 4 more authors

Measurement, 2024

Abs Bib PDF

This study presents a novel approach for real-time vision-based structural health monitoring, focusing on evaluating the deformation state of lattice structures. The structures are renowned for their remarkable recovery capabilities and exhibit similar mechanical responses under compressive loads. Despite these characteristics, quickly assessing the health status of the applied structure using knowledge from another related lattice structure is usually time-consuming and impractical. To address this, we propose to combine Gaussian process classification with transfer learning, termed TL-GPC, to detect damage states under compressive loads while also achieving uncertainty quantification. By employing structural deformations captured via the optical flow algorithm as inputs, the internal transfer kernel factor in TL-GPC is tailored to model knowledge transfer between source and target domain inputs. Experimental results show that the proposed TL-GPC model can deliver higher damage detection accuracy while ensuring stable uncertainty quantification in scenarios with limited and unbalanced experimental data.
@article{YANG2024115387, title = {Transfer learning-based Gaussian process classification for lattice structure damage detection}, journal = {Measurement}, volume = {238}, pages = {115387}, year = {2024}, issn = {0263-2241}, doi = {10.1016/j.measurement.2024.115387}, author = {Yang, Xin and Farrokhabadi, Amin and Rauf, Ali and Liu, Yongcheng and Talemi, Reza and Kundu, Pradeep and Chronopoulos, Dimitrios}, keywords = {Structural health monitoring, Damage detection, Transfer learning, Gaussian process classification, Optical flow estimation}, bibtex_show = true, dimensions = {true}, }
Mech. Syst. Signal Process
A decision-level sensor fusion scheme integrating ultrasonic guided wave and vibration measurements for damage identification

Xin Yang, Chen Fang, Pradeep Kundu, and 2 more authors

Mechanical Systems and Signal Processing, 2024

Abs Bib PDF

Structural health monitoring is designed to detect and analyze damage in mechanical, aerospace, and industrial structures to prevent potential catastrophic failures. The effectiveness of identifying structural faults and operational damage significantly relies on the sensing technology. Multisensory data fusion, as one of the promising techniques, combines data from multiple sensor modalities for reliable and accurate fault diagnosis. In this paper, we propose a novel decision-level multisensory data fusion approach. This approach combines data from an ultrasonic guided-wave sensor modality and a vibration sensor modality for the first time, aiming to achieve precise and stable damage identification. The Bayesian probabilistic distributions from each sensor modality are obtained using a multi-level Metropolis–Hastings algorithm. Subsequently, a multilayer perceptron network is trained to automatically allocate confidence scores for each sensor modality. The final fusion results are derived from the proposed decision-level fusion approach, combining the Bayesian probabilistic distributions from each sensor modality with allocated confidence scores. Simulation and experiment results indicate that the decision-level fusion approach produces more accurate and reliable outcomes for damage identification compared to relying on a single modality, especially in the case of progressive damage.
@article{YANG2024111597, title = {A decision-level sensor fusion scheme integrating ultrasonic guided wave and vibration measurements for damage identification}, journal = {Mechanical Systems and Signal Processing}, volume = {219}, pages = {111597}, year = {2024}, issn = {0888-3270}, doi = {10.1016/j.ymssp.2024.111597}, author = {Yang, Xin and Fang, Chen and Kundu, Pradeep and Yang, Jian and Chronopoulos, Dimitrios}, keywords = {Structural health monitoring, Multisensory data fusion, Ultrasonic modality, Vibration modality, Bayesian theorem}, bibtex_show = true, dimensions = {true}, }
Compos. Struct.
Energy absorption assessment of recovered shapes in 3D-printed star hourglass honeycombs: Experimental and numerical approaches

Amin Farrokhabadi, Houyu Lu, Xin Yang, and 5 more authors

Composite Structures, 2024

Abs Bib PDF

This study provides an experimental and numerical evaluation of the energy absorption performance of a 3D-printed star hourglass honeycomb structure with a novel design made from pure and reinforced PLA by chopped carbon fibers and continuous glass fiber. The study further investigates the energy absorption response of this structure after the shape recovery due to thermal stimuli under the quasi-static compressive loading. As an additive manufacturing process, Fused Deposition Modeling is used to produce the specimens with pure and reinforced PLA filament. The difference in the nonlinear response of PLA due to plasticity and damage in tension and compression loading directions, as a feature that helps the shape recovery, is considered in mechanical response analysis using the Finite Element approach. Then, in the obtained results distinguish constitutive laws in tension and compression mechanical properties are employed leading to a failure model using the appropriate algorithm consistent with the experiments. According to the obtained results which reveal good agreement regarding the experimental results, by designing appropriate auxetic configuration selecting suitable geometry parameters, and employing the proper material with diverse properties in tension and compression directions, it is possible to fabricate a lattice structure inherits the shape recovery after the compression deformation which exhibits acceptable energy absorption performance even the second shape recovery.
@article{FARROKHABADI2024118444, title = {Energy absorption assessment of recovered shapes in 3D-printed star hourglass honeycombs: Experimental and numerical approaches}, journal = {Composite Structures}, volume = {347}, pages = {118444}, year = {2024}, issn = {0263-8223}, doi = {10.1016/j.compstruct.2024.118444}, author = {Farrokhabadi, Amin and Lu, Houyu and Yang, Xin and Rauf, Ali and Talemi, Reza and {Hossein Behravesh}, Amir and {Kaveh Hedayati}, Seyyed and Chronopoulos, Dimitrios}, keywords = {Continuous fiber-reinforced polymer, Energy absorption, FEM, Star Hourglass Honeycomb, Shape recovery}, bibtex_show = true, dimensions = {true} }
Compos. Struct.
Deep learning uncertainty quantification for ultrasonic damage identification in composite structures

Houyu Lu, Sergio Cantero-Chinchilla, Xin Yang, and 2 more authors

Composite Structures, 2024

Abs Bib PDF

In this paper, three state-of-the-art deep learning uncertainty quantification (UQ) methods – Flipout probabilistic convolutional neural network (CNN), deep ensemble probabilistic CNN, and Bayesian probabilistic CNN – based on the Visual Geometry Group 13 architecture are proposed. They are compared with a traditional Bayesian inference approach for localizing delamination damage in composite. The law of conditional covariance is used to separate and quantify the predictive variance of the three networks into aleatoric and epistemic uncertainty. The network models’ performance is enhanced through hyperparameter optimization using Hyperband and warm-up optimization algorithms. The performance of the three networks in measuring the uncertainty is assessed on an out-of-distribution (OOD) dataset and validated on an in-distribution (ID) dataset for localization of composite delamination damage. Results indicate high accuracy in predicting damage locations for all methods on the ID dataset. On the OOD dataset, the Flipout and deep ensemble network have better performance, stably measuring aleatoric uncertainty in both trained and untrained areas, while the Bayesian network’s aleatoric uncertainty shows a discernible change across both areas. All three networks effectively measure epistemic uncertainty. Overall in both ID and OOD datasets, the Flipout network provides an optimal balance among training efficiency, UQ effectiveness and accuracy in predicting damage locations.
@article{LU2024118087, title = {Deep learning uncertainty quantification for ultrasonic damage identification in composite structures}, journal = {Composite Structures}, volume = {338}, pages = {118087}, year = {2024}, issn = {0263-8223}, doi = {10.1016/j.compstruct.2024.118087}, author = {Lu, Houyu and Cantero-Chinchilla, Sergio and Yang, Xin and Gryllias, Konstantinos and Chronopoulos, Dimitrios}, keywords = {Uncertainty quantification, Deep ensemble, Flipout networks, Bayesian network, Bayesian inference, Damage localization}, bibtex_show = true, dimensions = {true} }

2022

Conf. SAE
Deep Uncertainty Quantification of Prognostic Techniques for Proton Exchange Membrane Fuel Cell

Xin Yang, and Fengxiang Chen

Nov 2022

Abs Bib PDF

An accurate voltage prediction associated with uncertainty quantification is of great importance to predict the remaining useful life for proton exchange membrane fuel cell in automobile applications. This paper achieves the remaining useful life prediction using deep neural networks, with an emphasis on uncertainty quantification in voltage prognostics for proton exchange membrane fuel cell systems. The trend and pattern of voltage degradation data was investigated by using long-short term memory and the voltage prediction trend was represented with prediction interval. The experimental results show that the deep learning model with corresponding uncertainty techniques can achieve prediction root mean square error values within 0.02 and represent the voltage prediction with a prediction interval.
@proceedings{YANG2022SAE, author = {Yang, Xin and Chen, Fengxiang}, booktitle = {Vehicle Electrification and Powertrain Diversification Technology Forum Part II}, title = {Deep Uncertainty Quantification of Prognostic Techniques for Proton Exchange Membrane Fuel Cell}, year = {2022}, month = nov, address = {Shanghai, China}, publisher = {Society of Automotive Engineers (SAE)}, doi = {10.4271/2022-01-7001}, bibtex_show = true, dimensions = {true} }

2021

J. Dyn. Sys., Meas., Control.
A Particle Filter and Long Short-Term Memory Fusion Technique for Lithium-Ion Battery Remaining Useful Life Prediction

Xiaosong Hu, Xin Yang, Fei Feng, and 2 more authors

Journal of Dynamic Systems, Measurement, and Control, Jan 2021

Abs Bib PDF

Accurate prediction of the remaining useful life (RUL) of lithium-ion batteries can improve the durability, reliability, and maintainability of battery system operation in electric vehicles. To achieve high-accuracy RUL predictions, it is necessary to develop an effective method for long-term nonlinear degradation prediction and quantify the uncertainty of the prediction results. To this end, this paper proposes a hybrid approach for lithium-ion battery RUL prediction based on particle filter (PF) and long short-term memory (LSTM) neural network. First, based on the training set, the model parameters are iteratively updated using the PF algorithm. Second, the LSTM model parameters are obtained using the training set. The mean and standard deviation in the prediction stage are obtained through Monte Carlo (MC) dropout. Finally, the mean value predicted by MC-dropout is used as the measurement for the PF in the prediction phase, the standard deviation represents the uncertainty of the prediction result, and the mean and standard deviation are integrated into the measurement equation of the model. The experimental results show that the proposed hybrid approach has better prediction accuracy than the PF, LSTM algorithm, and two other types of hybrid approaches. The hybrid approach can obtain a narrower confidence interval.
@article{Hu2021, author = {Hu, Xiaosong and Yang, Xin and Feng, Fei and Liu, Kailong and Lin, Xianke}, title = {A Particle Filter and Long Short-Term Memory Fusion Technique for Lithium-Ion Battery Remaining Useful Life Prediction}, journal = {Journal of Dynamic Systems, Measurement, and Control}, volume = {143}, number = {6}, pages = {061001}, year = {2021}, month = jan, issn = {0022-0434}, doi = {10.1115/1.4049234}, bibtex_show = true, dimensions = {true}, }
Conf. CVCI
Machine learning-based voltage degradation prediction with uncertainty quantifications for PEMFC

Xin Yang, Fengxiang Chen, Jieran Jiao, and 1 more author

Oct 2021

Abs Bib PDF

The voltage degradation trend prediction has been attached great importance to the application of proton exchange membrane fuel cell systems. Based on Gaussian process regression (GPR) and Bayesian neural network (BNN), this paper uses proton exchange membrane fuel cell dataset to predict the voltage degradation trend. Further, the uncertainty representation of prediction results is realized based on GPR and BNN. Finally, the mean absolute error and root mean square error are used as performance indicators to evaluate the prediction performance. The experimental results show that the evaluation indexes of BNN reach 0.00523, 0.00486 for mean absolute error and 0.007145, 0.007283 for root mean square error, which are less than that of GPR.
@proceedings{YANG2022CVCI, author = {Yang, Xin and Chen, Fengxiang and Jiao, Jieran and Liu, Shiguang}, booktitle = {2021 5th CAA International Conference on Vehicular Control and Intelligence (CVCI)}, title = {Machine learning-based voltage degradation prediction with uncertainty quantifications for PEMFC}, year = {2021}, month = oct, address = {Tianjin, China}, pages = {1-5}, doi = {10.1109/CVCI54083.2021.9661176}, bibtex_show = true, dimensions = {true} }