Ahmad Honarjoo, Ehsan Darvishan, Hassan Rezazadeh and Amir Homayoon Kosarieh
This article addresses the need for a comprehensive model for structural crack detection in the context of structural health monitoring. The main innovation of this research is…
Abstract
Purpose
This article addresses the need for a comprehensive model for structural crack detection in the context of structural health monitoring. The main innovation of this research is the introduction of a dynamic attention-based transformer model that significantly enhances the accuracy and efficiency of detecting and localizing cracks in structures. This study seeks to overcome previous limitations and contribute to advancements in structural health monitoring practices.
Design/methodology/approach
The research focuses on three primary computer vision tasks: classification, object detection and semantic segmentation applied to crack detection in concrete, brick and asphalt structures. The proposed approach employs transformer encoders with dynamic attention mechanisms to assess the severity and extent of damage accurately.
Findings
In this study, we propose a dynamic attention-based transformer model for structural crack detection, achieving a remarkable accuracy of 99.38% and an impressive F1 score. Our method demonstrates superior performance compared to existing techniques, such as the fusion features-based broad learning system and deep convolutional neural networks, while also significantly reducing execution time, highlighting its efficiency and potential for practical applications in structural health monitoring.
Originality/value
This research introduces a novel framework for crack detection, leveraging recent advancements in deep learning technology, with significant implications for the field of civil engineering and maintenance.
Details
Keywords
Ahmad Honarjoo, Ehsan Darvishan, Hassan Rezazadeh and Amir Homayoon Kosarieh
This article introduces SigBERT, a novel approach that fine-tunes bidirectional encoder representations from transformers (BERT) for the purpose of distinguishing between intact…
Abstract
Purpose
This article introduces SigBERT, a novel approach that fine-tunes bidirectional encoder representations from transformers (BERT) for the purpose of distinguishing between intact and impaired structures by analyzing vibration signals. Structural health monitoring (SHM) systems are crucial for identifying and locating damage in civil engineering structures. The proposed method aims to improve upon existing methods in terms of cost-effectiveness, accuracy and operational reliability.
Design/methodology/approach
SigBERT employs a fine-tuning process on the BERT model, leveraging its capabilities to effectively analyze time-series data from vibration signals to detect structural damage. This study compares SigBERT's performance with baseline models to demonstrate its superior accuracy and efficiency.
Findings
The experimental results, obtained through the Qatar University grandstand simulator, show that SigBERT outperforms existing models in terms of damage detection accuracy. The method is capable of handling environmental fluctuations and offers high reliability for non-destructive monitoring of structural health. The study mentions the quantifiable results of the study, such as achieving a 99% accuracy rate and an F-1 score of 0.99, to underline the effectiveness of the proposed model.
Originality/value
SigBERT presents a significant advancement in SHM by integrating deep learning with a robust transformer model. The method offers improved performance in both computational efficiency and diagnostic accuracy, making it suitable for real-world operational environments.
Details
Keywords
Ahmad Honarjoo and Ehsan Darvishan
This study aims to obtain methods to identify and find the place of damage, which is one of the topics that has always been discussed in structural engineering. The cost of…
Abstract
Purpose
This study aims to obtain methods to identify and find the place of damage, which is one of the topics that has always been discussed in structural engineering. The cost of repairing and rehabilitating massive bridges and buildings is very high, highlighting the need to monitor the structures continuously. One way to track the structure's health is to check the cracks in the concrete. Meanwhile, the current methods of concrete crack detection have complex and heavy calculations.
Design/methodology/approach
This paper presents a new lightweight architecture based on deep learning for crack classification in concrete structures. The proposed architecture was identified and classified in less time and with higher accuracy than other traditional and valid architectures in crack detection. This paper used a standard dataset to detect two-class and multi-class cracks.
Findings
Results show that two images were recognized with 99.53% accuracy based on the proposed method, and multi-class images were classified with 91% accuracy. The low execution time of the proposed architecture compared to other valid architectures in deep learning on the same hardware platform. The use of Adam's optimizer in this research had better performance than other optimizers.
Originality/value
This paper presents a framework based on a lightweight convolutional neural network for nondestructive monitoring of structural health to optimize the calculation costs and reduce execution time in processing.