.png){kind=icon}
Return
A Correlation Analysis-Based Structural Load Estimation Method for RC Beams Using Machine Vision and Numerical Simulation
.png){kind=icon}
OA
AI
DOI：10.3390/buildings15020207.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The correlation analysis between current surface cracks of structures and external loads can provide important insights into determining the structural residual bearing capacity. The classical regression assessment method based on experimental data not only relies on costly structure experiments; it also lacks interpretability. Therefore, a novel load estimation method for RC beams, based on correlation analysis between detected crack images and strain contour plots calculated by FEM, is proposed. The distinct discrepancies between crack images and strain contour figures, coupled with the stochastic nature of actual crack distributions, pose considerable challenges for load estimation tasks. Therefore, a new correlation index model is initially introduced to quantify the correlation between the two types of images in the proposed method. Subsequently, a deep neural network (DNN) is trained as a FEM surrogate model to quickly predict the structural strain response by considering material uncertainties. Ultimately, the range of the optimal load level and its confidence interval are determined via statistical analysis of the load estimations under different random fields. The validation results of RC beams under four-point bending loads show that the proposed algorithm can quickly estimate load levels based on numerical simulation results, and the mean absolute percentage error (MAPE) for load estimation based solely on a single measured structural crack image is 20.68%.
Keywords:
structural assessment
machine vision
deep learning
surrogate model
reinforced concrete beam
Journal
IF:
3.1
Papers:
1.8W
Citations:
2.5W
Organization
Cited Papers
Structural Health Monitoring using deep learning with optimal finite element model generated data
PREAI
ShareSaveShareSaveShareSaveDetection and Length Measurement of Cracks Captured in Low Definitions Using Convolutional Neural Networks.png)
SENSORS
OAAI
SENSORSIF3.5
OAAIShareSaveShareSaveShareSave
View more