Early and intelligent recognition of dynamic cracks during damage of complex fractured rock masses based on DIC and YOLO algorithms

In order to quantitatively study the deformation and failure laws of complex fractured rocks and the characteristics of fracture expansion, the fracture network model 3 D printing technology was used to produce rock-like specimens with 20 random joints, and the digital image correlation method(DIC)was used to study the strain field during the failure process of the specimens. The evolution process is analyzed, and the expansion process of each crack is analyzed, and the influence of dynamic cracks on the overall strength of the specimen is discussed. Based on the YOLOv5 deep learning network model, combined with the DIC cloud image, an algorithm for intelligent and accurate identification of dynamic cracks is proposed. Studies have shown that the failure process of specimens with complex cracks is often accompanied by the expansion and penetration of multiple cracks. The overall strength of the specimens has an important relationship with the expansion of dynamic cracks. Statistics on the expansion of dynamic cracks can determine the overall strength of the specimens semi-quantitatively. Before each original crack starts to crack, the strain-concentrated area always appears first, and the strain-concentrated area has precursory properties, which indicates the initiation of new cracks. The dynamic evolution of primary cracks can be basically divided into four types: primary cracks, strain concentration zone, new cracks and cross cracks. Among them, cross cracks have the greatest impact on the overall strength of the specimen. The accuracy, recall, and P_mA of the proposed intelligent and accurate identification of dynamic fissure algorithms are all above 80%,and the maximum average accuracy mean(P_mA)is 91%. The GIoU loss parameter reaches 0.01 after iterative training. The F₁ values corresponding to the four types of fissures are respectively 83%,89%,87% and 85%,the overall recognition accuracy of the four types of cracks can reach 86%. It shows that this method is fast, accurate and effective in the identification, location and classification of cracks in complex fractured rock masses.