A deep learning-based bridge damage detection and localization method

Sun, Hongshuo; Li, Song

doi:10.1016/j.ymssp.2023.110277

Cited by 12 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the scope, amount, and complexity of the data, this comparison is usually carried out using automatic or semi-automatic systems based on machine learning and artificial intelligence algorithms [57][58][59]. It may include damage recognition based on the computer vision [60,61], structural condition assessment by pattern recognition and detection of anomalies [62], surrogate model-based reliability analysis [63], and dynamic measurement of displacement [64]. The results and decisions derived from the analysis are visualized in the as-built BIM model.…”

Section: Methodsmentioning

confidence: 99%

The Concept of Creating Digital Twins of Bridges Using Load Tests

Jasiński,

Łaziński,

Piotrowski

2023

Sensors

View full text Add to dashboard Cite

The paper sheds light on the process of creating and validating the digital twin of bridges, emphasizing the crucial role of load testing, BIM models, and FEM models. At first, the paper presents a comprehensive definition of the digital twin concept, outlining its core principles and features. Then, the framework for implementing the digital twin concept in bridge facilities is discussed, highlighting its potential applications and benefits. One of the crucial components highlighted is the role of load testing in the validation and updating of the FEM model for further use in the digital twin framework. Load testing is emphasized as a key step in ensuring the accuracy and reliability of the digital twin, as it allows the validation and refinement of its models. To illustrate the practical application and issues during tuning and validating the FEM model, the paper provides an example of a real bridge. It shows how a BIM model is utilized to generate a computational FEM model. The results of the load tests carried out on the bridge are discussed, demonstrating the importance of the data obtained from these tests in calibrating the FEM model, which forms a critical part of the digital twin framework.

show abstract