Xudong Jian

Last Name

Jian

First Name

Xudong

ORCID

0000-0001-9973-9662

Organisational unit

03890 - Chatzi, Eleni / Chatzi, Eleni

Show all metadata

Search Results

Publications1 - 9 of 9

On the potential of aerodynamic pressure measurements for structural damage detection
Franz, Philip; Abdallah, Imad; Duthé, Gregory; et al. (2025)
Wind Energy Science
This study investigates the potential of using aerodynamic pressure time series measurements to detect structural damage in elastic, aerodynamically loaded structures. Our work is motivated by the increase in the dimensions of modern wind turbine blade (WTB) designs, whose complex behavior necessitates the adoption of improved simulation and structural monitoring solutions. In refining the tracking of aerodynamic interactions and their effects on such structures, we propose to exploit aerodynamic pressure measurements, available from a novel, cost-effective, and non-intrusive sensing system, for structural damage assessment on WTBs. This proof-of-concept study is based on a series of wind tunnel experiments on an NACA 633418 airfoil. The airfoil is mounted on a vertically oscillating cantilever beam with structural damage introduced in the form of a crack by gradually sawing the cantilever beam close to its support. The pressure distribution on the airfoil is measured under diverse configurations of inflow conditions and structural states, including different angles of attack, wind velocities, heaving frequencies, and crack lengths. We further propose an algorithm, relying on convolutional neural networks (CNNs), for damage detection and rating based on the monitored signals. Analysis of the dynamics of the system using reference acceleration measurements and a finite element (FE) model and application of the suggested method on the experimental data indicate that aerodynamic pressure measurements on airfoils can indeed be used as an indirect approach for damage detection and severity classification on elastic, beam-like structures in mildly turbulent environments.
A robust bridge weigh-in-motion algorithm based on regularized total least squares with axle constraints
Jian, Xudong; Lai, Zhilu; Xia, Ye; et al. (2022)
Structural Control and Health Monitoring
The identification of traffic loads, including the axle weight (AW) and the gross vehicle weight (GVW) of vehicles, plays an important role in bridge design refinement, safety evaluation, and maintenance strategies. Bridge weigh in motion (BWIM) is a promising technique to weigh vehicles passing through bridges. Though the state-of-the-art BWIM can accurately identify the GVW, unacceptable weighing errors are reported when identifying the AW of vehicles, particularly for those with closely spaced axles. To address the axle weighing problem, this paper aims to improve the performance of BWIM in weighing individual axle loads apart from the gross vehicle weight. The work first theoretically analyzes the possible sources of errors of existing BWIM algorithms, which are observational errors residing in the BWIM equation, no constraint imposed on individual axle loads, and ill-conditioned nature. Accordingly, three measures are taken to establish a novel robust BWIM algorithm, which is based on regularized total least squares, as well as imposing constraints on the relationship between axles. To validate the proposed algorithm, a series of weighing experiments are carried out on a high-fidelity vehicle-bridge scale model. The corresponding results indicate that the proposed BWIM algorithm significantly outperforms other existing BWIM algorithms in terms of the accuracy and robustness of identifying individual axle weight, while retaining satisfactory identification of the gross vehicle weight as well.
Neural modal ordinary differential equations: Integrating physics-based modeling with neural ordinary differential equations for modeling high-dimensional monitored structures
Lai, Zhilu; Liu, Wei; Jian, Xudong; et al. (2022)
Data-Centric Engineering
The dimension of models derived on the basis of data is commonly restricted by the number of observations, or in the context of monitored systems, sensing nodes. This is particularly true for structural systems, which are typically high-dimensional in nature. In the scope of physics-informed machine learning, this article proposes a framework - termed neural modal ordinary differential equations (Neural Modal ODEs) - to integrate physics-based modeling with deep learning for modeling the dynamics of monitored and high-dimensional engineered systems. In this initiating exploration, we restrict ourselves to linear or mildly nonlinear systems. We propose an architecture that couples a dynamic version of variational autoencoders with physics-informed neural ODEs (Pi-Neural ODEs). An encoder, as a part of the autoencoder, learns the mappings from the first few items of observational data to the initial values of the latent variables, which drive the learning of embedded dynamics via Pi-Neural ODEs, imposing a modal model structure on that latent space. The decoder of the proposed model adopts the eigenmodes derived from an eigenanalysis applied to the linearized portion of a physics-based model: a process implicitly carrying the spatial relationship between degrees-of-freedom (DOFs). The framework is validated on a numerical example, and an experimental dataset of a scaled cable-stayed bridge, where the learned hybrid model is shown to out perform a purely physics-based approach to modeling. We further show the functionality of the proposed scheme within the context of virtual sensing, that is, the recovery of generalized response quantities in unmeasured DOFs from spatially sparse data.
Bridge influence surface identification using a deep multilayer perceptron and computer vision techniques
Chatzi, Eleni; Lai, Zhilu; Jian, Xudong; et al. (2024)
Structural Health Monitoring
The identification of influence surfaces (ISs) for bridge structures offers an efficient tool for understanding traffic loads and assessing structural conditions. In general, ISs of a real bridge can be identified through calibration tests using calibration vehicles with known weights moving across the bridge. However, the existing methods face difficulties in considering comprehensive factors, such as the lateral movement, speed variation, and track width of the calibration vehicle, as well as bridge dynamic effects. These factors inevitably introduce inaccuracies into the task of identification. To comprehensively consider these factors, this study proposes a deep learning-based method that combines deep multilayer perceptrons (MLPs) and computer vision (CV), with deep MLP adopted to identify bridge ISs and CV employed to obtain the position coordinates of the calibration vehicle’s wheels. A series of numerical simulations and field experiments on an in-service bridge were carried out to validate the proposed framework and compare it against a broadly established method to such an end—Quilligan’s method. The results show the accuracy, robustness, and practicability of the proposed framework.
Using graph neural networks and frequency domain data for automated operational modal analysis of populations of structures
Jian, Xudong; Xia , Yutong; Duthé, Gregory; et al. (2025)
Data-Centric Engineering
The population-based structural health monitoring paradigm has recently emerged as a promising approach to enhance data-driven assessment of engineering structures by facilitating transfer learning between structures with some degree of similarity. In this work, we apply this concept to the automated modal identification of structural systems. We introduce a graph neural network (GNN)-based deep learning scheme to identify modal properties, including natural frequencies, damping ratios, and mode shapes of engineering structures based on the power spectral density of spatially sparse vibration measurements. Systematic numerical experiments are conducted to evaluate the proposed model, employing two distinct truss populations that possess similar topological characteristics but varying geometric (size and shape) and material (stiffness) properties. The results demonstrate that, once trained, the proposed GNN-based model can identify modal properties of unseen structures within the same structural population with good efficiency and acceptable accuracy, even in the presence of measurement noise and sparse measurement locations. The GNN-based model exhibits advantages over the classic frequency domain decomposition method in terms of identification speed, as well as against an alternate multilayer perceptron architecture in terms of identification accuracy, rendering this a promising tool for PBSHM purposes.
Population-Based Mode Shape Identification of Structures via Graph Neural Networks
Jian, Xudong; Duthé, Gregory; Chatzi, Eleni (2025)
Conference Proceedings of the Society for Experimental Mechanics Series ~ Model Validation and Uncertainty Quantification, Vol. 3
The Population-Based Structural Health Monitoring (PBSHM) paradigm has recently emerged aiming to enhance data-driven assessment of engineering structures by allowing data to be shared and learning to be transferred between similar structures. In this work, we gear this concept toward automated modal identification of structural systems. Toward modal identification from a PBSHM perspective, we here present a Graph Neural Network (GNN)-based deep learning scheme to identify mode shapes of engineering structures on the basis of monitored (measured) responses. The generation of the training dataset, which includes mode shapes and noise-polluted dynamic responses, relies on availability of an engineering model. Finite element (FE)-based modal and dynamic analyses are first carried out on a population of structures that share certain morphological/typological characteristics but comprise different geometric (size and shape) and material (stiffness) characteristics. The trained model is in a next step fed with dynamic response data from unseen structures and is able to output, in an automated fashion, the corresponding mode shapes. These unseen structures form members of the explored “population” but have not been generated for use within the training set. Moreover, we show that mode shape inference under availability of sparse measurements can be achieved by coupling the GNN with a Feature Propagation operator in what we here term a GNN-OMA approach. A series of numerical experiments are conducted to test the performance of the proposed method. Results show that the proposed model exhibits good accuracy and generalization ability when identifying mode shapes for structures within the same population, rendering its use promising for PBSHM purposes.
A Robotic Automated Solution for Operational Modal Analysis of Bridges with High-Resolution Mode Shape Recovery
Jian, Xudong; Lai, Zhilu; Bacsa, Kiran; et al. (2024)
Journal of Structural Engineering
This study presents a robot-assisted solution for the automated identification of bridge frequencies and high-spatial-resolution mode shapes using a minimal number of sensors. The proposed approach employs programmable wheeled robots, whose movement can be remotely controlled, as the mobile platform carrying accelerometers. The output-only frequency domain decomposition (FDD) algorithm is adopted for use with the proposed stop-and-go mobile sensing scheme, resulting in the identification of frequencies and high-resolution mode shapes. The solution was verified via two numerical case studies and was validated on a full-scale test of a footbridge. The results reveal that the frequencies and high-resolution shapes of the excited structural modes are identified successfully using only two accelerometers, confirming the satisfactory practicality and efficiency of the proposed solution.
Modal decomposition and identification for a population of structures using physics-informed graph neural networks and transformers
Jian, Xudong; Bacsa, Kiran; Duthé, Gregory; et al. (2025)
Mechanical Systems and Signal Processing
Modal identification is key to structural health monitoring and control, offering vital insights into dynamic behavior. This study proposes a novel deep learning framework that combines graph neural networks (GNNs), transformers, and a physics-informed loss to perform modal decomposition and identification among a population of structures. The transformer extracts single-degree-of-freedom (SDOF)-equivalent modal response estimates from multi-degree-of-freedom (MDOF) measurements, enabling the identification of natural frequencies and damping ratios. The GNN encodes structural topology to infer the corresponding mode shapes. Trained in a fully unsupervised, physics-informed manner, the model leverages modal decomposition theory and mode independence, requiring no labeled data. Validation through simulations and lab experiments demonstrates accurate recovery of modal properties from sparse measurements under varying loading and structural conditions. Comparisons with conventional modal identification methods highlight the framework's effectiveness, robustness, and superior performance, establishing it as a powerful tool for population-level structural monitoring.
Robotic mobile sensing for robust modal identification across a population of bridges: Uncertainty analysis, algorithm development, hardware realization, and field validation
Jian, Xudong; Bacsa, Kiran; Varga, Matej; et al. (2026)
Mechanical Systems and Signal Processing
Population-Based Structural Health Monitoring (PBSHM) has recently emerged as a promising paradigm to enhance monitoring capabilities across populations of structures. A central requirement for PBSHM is the collection of data from multiple population members. Conventional fixed sensing strategies, whether permanently installed or temporarily deployed, are impractical for this purpose, as they require significant time, labour, and cost. This study introduces a novel robotic mobile sensing framework designed to overcome these challenges. The framework develops a customized portable accelerometer and an intelligent wheeled robot carrying multiple sensors to conduct vibration-based measurements on bridge structures. The collected data enable modal identification, a cornerstone task in PBSHM. To address uncertainties inherent to mobile sensing, we conduct a theoretical uncertainty analysis and develop a robust automated frequency domain decomposition algorithm tailored for mobile data. The proposed framework, which encompasses sensing hardware, uncertainty analysis, and a modal identification algorithm, is validated through field deployment on ten simply supported bridge spans, representative of a bridge population. Using only two sensors, we successfully extract multiple modal frequencies and mode shapes for each span, while quantifying uncertainties in the results. Comparisons with finite element analyses and population-level assessment further confirm the effectiveness of the framework, highlighting its scalability, cost efficiency, and suitability for practical PBSHM implementation.

Publications1 - 9 of 9

Xudong Jian

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results