Automatic identification and quantification of dense microcracks in high-performance fiber-reinforced cementitious composites through deep learning-based computer vision
Automatic identification and quantification of dense microcracks in high-performance fiber-reinforced cementitious composites through deep learning-based computer vision
复制标题
DOI：
10.1016/j.cemconres.2021.106532
复制
发表时间：
2021-07-13
影响因子：
11.4
通讯作者：
Bao, Yi
中科院分区：
文献类型：
--
作者：
Guo, Pengwei;Meng, Weina;Bao, Yi
高性能纤维增强水泥基复合材料(HPFRCC)具有高的机械强度、抗裂性和耐久性。在超载情况下，HPFRCC表现出致密的微裂纹，使用现有方法很难识别。提出了一种基于深度学习的高性能碾压混凝土微裂纹识别、量化和可视化的计算机视觉方法。该方法在一个层次结构中集成了多种深度学习模型和计算机视觉技术。裂缝图案(例如，裂缝的数量、宽度和间距)是从图片自动确定的，无需人工干预。研究表明，当深度学习模型仅使用200张HPFRCC图片和200张普通混凝土图片并结合数据增强时，该方法对裂缝检测的准确率为0.992，对于裂缝宽度的量化精度优于50微米(R-2>；0.984)。该方法可望适用于其他具有复杂裂纹的材料。
High-performance fiber-reinforced cementitious composites (HPFRCCs) feature high mechanical strengths, crack resistance, and durability. Under excessive loading, HPFRCCs demonstrate dense microcracks that are difficult to identify using existing methods. This study presents a computer vision method for identification, quantification, and visualization of microcracks in HPFRCCs based on deep learning. The presented method integrates multiple deep learning models and computer vision techniques in a hierarchical architecture. The crack pattern (e.g., number, width, and spacing of cracks) are automatically determined from pictures without human intervention. This study shows that the presented method achieves an accuracy of 0.992 for crack detection and an accuracy finer than 50 mu m (R-2 > 0.984) for quantification of crack width when deep learning models are trained using only 200 pictures of HPFRCCs and 200 pictures of conventional concrete with incorporation of data augmentation. The presented method is expected to be also applicable to other materials featuring complex cracks.