Recent advances and applications of machine learning in experimental solid mechanics: A review
For many decades, experimental solid mechanics has played a crucial role in characterizing
and understanding the mechanical properties of natural and novel artificial materials …
and understanding the mechanical properties of natural and novel artificial materials …
[HTML][HTML] A review of synthetic and augmented training data for machine learning in ultrasonic non-destructive evaluation
Ultrasonic Testing (UT) has seen increasing application of machine learning (ML) in recent
years, promoting higher-level automation and decision-making in flaw detection and …
years, promoting higher-level automation and decision-making in flaw detection and …
Modeling finite-strain plasticity using physics-informed neural network and assessment of the network performance
Physics-informed neural networks (PINN) can solve partial differential equations (PDEs) by
encoding the mathematical information explicitly into the loss functions. In the context of …
encoding the mathematical information explicitly into the loss functions. In the context of …
Mechanics-informed, model-free symbolic regression framework for solving fracture problems
Data-driven methods have recently been introduced to address complex mechanics
problems. While model-based, data-driven approaches are predominantly used, they often …
problems. While model-based, data-driven approaches are predominantly used, they often …
The detection of PAUT pseudo defects in ultra-thick stainless-steel welds with a multimodal deep learning model
W Cao, X Sun, Z Liu, Z Chai, G Bao, Y Yu, X Chen - Measurement, 2025 - Elsevier
The pseudo defects are difficult to distinguish in Phased Array Ultrasonic Testing (PAUT)
thick-walled weldments. In this work, a multimodal feature fusion model is proposed to …
thick-walled weldments. In this work, a multimodal feature fusion model is proposed to …
A large deformation model for quasi-static to high strain rate response of a rate-stiffening soft polymer
Polyborosiloxane (PBS) is an important rate-stiffening soft polymer with dynamic, reversible
crosslinks used in applications ranging from self-healing sensing and actuation to body and …
crosslinks used in applications ranging from self-healing sensing and actuation to body and …
Ultrasonic characterization of small defects based on Res-ViT and unsupervised domain adaptation
C Guo, M Li, J Xu, L Bai - Ultrasonics, 2024 - Elsevier
This paper investigated the application of deep neural networks and domain adaptation for
ultrasonic characterization of elliptical defects that are small and inclined. Based on …
ultrasonic characterization of elliptical defects that are small and inclined. Based on …
Performance Enhancement of Ultrasonic Weld Defect Detection Network Based on Generative Data
Z Yuan, X Gao, K Yang, J Peng, L Luo - Journal of Nondestructive …, 2024 - Springer
The lack of real defect data samples has become a challenging problem for the effective
application of deep learning networks in ultrasound target detection. This paper proposes a …
application of deep learning networks in ultrasound target detection. This paper proposes a …
Hygroscopic damage of fiber–matrix interface in unidirectional composites: A computational approach
The mechanical properties of fiber-reinforced composites are significantly affected by
hygroscopic exposure. Recent experimental findings reveal that the diffusion of water …
hygroscopic exposure. Recent experimental findings reveal that the diffusion of water …
Wastewater pipe defect rating model for pipe maintenance using natural language processing
Introduction Closed-circuit video (CCTV) inspection has been the most popular technique for
visually evaluating the interior status of pipelines in recent decades. Certified inspectors …
visually evaluating the interior status of pipelines in recent decades. Certified inspectors …