arXiv:2512.03115v1 Announce Type: new 
Abstract: Reliable real-time analysis of sensor data is essential for structural health monitoring (SHM) of high-value assets, yet a major challenge is to obtain spatially resolved full-field aleatoric and epistemic uncertainties for trustworthy decision-making. We present an integrated SHM framework that combines principal component analysis (PCA), a Bayesian neural network (BNN), and Hamiltonian Monte Carlo (HMC) inference, mapping sparse strain gauge measurements onto leading PCA modes to reconstruct full-field strain distributions with uncertainty quantification. The framework was validated through cyclic four-point bending tests on carbon fiber reinforced polymer (CFRP) specimens with varying crack lengths, achieving accurate strain field reconstruction (R squared value > 0.9) while simultaneously producing real-time uncertainty fields. A key contribution is that the BNN yields robust full-field strain reconstructions from noisy experimental data with crack-induced strain singularities, while also providing explicit representations of two complementary uncertainty fields. Considered jointly in full-field form, the aleatoric and epistemic uncertainty fields make it possible to diagnose at a local level, whether low-confidence regions are driven by data-inherent issues or by model-related limitations, thereby supporting reliable decision-making. Collectively, the results demonstrate that the proposed framework advances SHM toward trustworthy digital twin deployment and risk-aware structural diagnostics.

تم تطوير إطار متكامل جديد لمراقبة صحة الهياكل في الوقت الحقيقي (SHM) يستخدم الشبكات العصبية البايزية (BNNs) واستدلال مونت كارلو هاملتوني لتحديد عدم اليقين في قياسات الإجهاد. يقوم هذا الإطار بإعادة بناء توزيعات الإجهاد بشكل فعال من بيانات متفرقة، وتم التحقق من صحته من خلال اختبارات على عينات من البوليمر المقوى بالألياف الكربونية.

Se ha desarrollado un nuevo marco integrado para la monitorización de la salud estructural en tiempo real (SHM), que utiliza Redes Neuronales Bayesiana (BNNs) y la inferencia de Monte Carlo Hamiltoniano para cuantificar las incertidumbres en las mediciones de tensión. Este marco reconstruye eficazmente las distribuciones de tensión a partir de datos escasos, validado a través de pruebas en especímenes de polímero reforzado con fibra de carbono.

Un nouveau cadre intégré pour la surveillance de la santé structurelle en temps réel (SHM) a été développé, utilisant des réseaux de neurones bayésiens (BNNs) et l'inférence de Monte Carlo Hamiltonien pour quantifier les incertitudes dans les mesures de contrainte. Ce cadre reconstruit efficacement les distributions de contrainte à partir de données éparses, validé par des tests sur des spécimens en polymère renforcé de fibres de carbone.

A new integrated framework for real-time structural health monitoring (SHM) has been developed, utilizing Bayesian Neural Networks (BNNs) and Hamiltonian Monte Carlo inference to quantify uncertainties in strain measurements. This framework effectively reconstructs full-field strain distributions from sparse data, validated through tests on carbon fiber reinforced polymer specimens.

Real-Time Structural Health Monitoring with Bayesian Neural Networks: Distinguishing Aleatoric and Epistemic Uncertainty for Digital Twin Frameworks

arXiv:2512.04323v1 Announce Type: cross 
Abstract: This paper introduces a novel method for generating high-quality Digital Image Correlation (DIC) dataset based on non-uniform B-spline surfaces. By randomly generating control point coordinates, we construct displacement fields that encompass a variety of realistic displacement scenarios, which are subsequently used to generate speckle pattern datasets. This approach enables the generation of a large-scale dataset that capture real-world displacement field situations, thereby enhancing the training and generalization capabilities of deep learning-based DIC algorithms. Additionally, we propose a novel network architecture, termed Bayes-DIC Net, which extracts information at multiple levels during the down-sampling phase and facilitates the aggregation of information across various levels through a single skip connection during the up-sampling phase. Bayes-DIC Net incorporates a series of lightweight convolutional blocks designed to expand the receptive field and capture rich contextual information while minimizing computational costs. Furthermore, by integrating appropriate dropout modules into Bayes-DIC Net and activating them during the network inference stage, Bayes-DIC Net is transformed into a Bayesian neural network. This transformation allows the network to provide not only predictive results but also confidence levels in these predictions when processing real unlabeled datasets. This feature significantly enhances the practicality and reliability of our network in real-world displacement field prediction tasks. Through these innovations, this paper offers new perspectives and methods for dataset generation and algorithm performance enhancement in the field of DIC.

تم تقديم طريقة جديدة تُسمى Bayes-DIC Net لتقدير عدم اليقين في ارتباط الصور الرقمية (DIC) باستخدام الشبكات العصبية البايزية. تُولد هذه الطريقة مجموعات بيانات عالية الجودة تعتمد على أسطح B-spline غير المنتظمة، مما يسمح بإنشاء مجالات إزاحة واقعية لتدريب خوارزميات التعلم العميق في تطبيقات DIC.

Se ha introducido un nuevo método llamado Bayes-DIC Net para estimar la incertidumbre en la Correlación de Imágenes Digitales (DIC) utilizando Redes Neuronales Bayesianas. Este método genera conjuntos de datos de alta calidad basados en superficies B-spline no uniformes, lo que permite la construcción de campos de desplazamiento realistas para entrenar algoritmos de aprendizaje profundo en aplicaciones de DIC.

Une nouvelle méthode appelée Bayes-DIC Net a été introduite pour estimer l'incertitude dans la Corrélation d'Image Numérique (DIC) en utilisant des Réseaux de Neurones Bayésiens. Cette méthode génère des ensembles de données de haute qualité basés sur des surfaces B-spline non uniformes, permettant la construction de champs de déplacement réalistes pour former des algorithmes d'apprentissage profond dans des applications DIC.

A novel method called Bayes-DIC Net has been introduced to estimate uncertainty in Digital Image Correlation (DIC) using Bayesian Neural Networks. This method generates high-quality datasets based on non-uniform B-spline surfaces, enabling the construction of realistic displacement fields for training deep learning algorithms in DIC applications.

Real-Time Structural Health Monitoring with Bayesian Neural Networks: Distinguishing Aleatoric and Epistemic Uncertainty for Digital Twin Frameworks

Was this article worth reading? Share it

LucidQuery AI

MatosShere

Dyad