Open Access

ARTICLE

Attention Mechanisms and FFM Feature Fusion Module-Based Modification of the Deep Neural Network for Detection of Structural Cracks

Tao Jin^1,2, Zhekun Shou¹, Hongchao Liu^1,*, Yuchun Shao¹

1 College of Civil Engineering, Zhejiang University of Technology, Hangzhou, China
2 Department of Civil Engineering, Zhejiang University, Hangzhou, China

* Corresponding Author: Hongchao Liu. Email:

(This article belongs to the Special Issue: Applied Artificial Intelligence: Advanced Solutions for Engineering Real-World Challenges)

Computer Modeling in Engineering & Sciences 2026, 146(2), 11 https://doi.org/10.32604/cmes.2026.076415

Received 20 November 2025; Accepted 22 January 2026; Issue published 26 February 2026

Abstract

This research centers on structural health monitoring of bridges, a critical transportation infrastructure. Owing to the cumulative action of heavy vehicle loads, environmental variations, and material aging, bridge components are prone to cracks and other defects, severely compromising structural safety and service life. Traditional inspection methods relying on manual visual assessment or vehicle-mounted sensors suffer from low efficiency, strong subjectivity, and high costs, while conventional image processing techniques and early deep learning models (e.g., U-Net, Faster R-CNN) still perform inadequately in complex environments (e.g., varying illumination, noise, false cracks) due to poor perception of fine cracks and multi-scale features, limiting practical application. To address these challenges, this paper proposes CACNN-Net (CBAM-Augmented CNN), a novel dual-encoder architecture that innovatively couples a CNN for local detail extraction with a CBAM-Transformer for global context modeling. A key contribution is the dedicated Feature Fusion Module (FFM), which strategically integrates multi-scale features and focuses attention on crack regions while suppressing irrelevant noise. Experiments on bridge crack datasets demonstrate that CACNN-Net achieves a precision of 77.6%, a recall of 79.4%, and an mIoU of 62.7%. These results significantly outperform several typical models (e.g., UNet-ResNet34, Deeplabv3), confirming their superior accuracy and robust generalization, providing a high-precision automated solution for bridge crack detection and a novel network design paradigm for structural surface defect identification in complex scenarios, while future research may integrate physical features like depth information to advance intelligent infrastructure maintenance and digital twin management.

---

Keywords

---