Automatic identification and characteristics analysis of crack tips in rocks with prefabricated defects based on deep learning methods

• Published in: PloS one Vol. 20; no. 7; p. e0327906
• Main Authors: Gao, Mingtao, Li, Minhui, Chen, Lu, Guo, Zihao, Guo, Chengyang, Li, Liping, Bu, Changsen
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 15.07.2025; Public Library of Science (PLoS)
• Subjects: Accuracy; Algorithms; Analysis; Annotations; Cameras; Computer and Information Sciences; Concrete; Crack initiation; Crack propagation; Crack tips; Decisions; Deep Learning; Engineering and Technology; Fracture mechanics; Geologic Sediments; Geological Phenomena; Geology; Identification; Image Processing, Computer-Assisted - methods; Image quality; Lasers; Machine learning; Methods; Neural networks; Physical characteristics; Prefabrication; Propagation; Recall; Recognition; Research and Analysis Methods; Rock masses; Rock mechanics; Rocks; Safety engineering; Sandstone; Stress state; China

In complex geological environments, the morphology, orientation and distribution characteristics of cracks in the rock directly affect the stability assessment for rock masses and engineering safety decisions. However, the traditional manual interpretation method is inefficient and influenced by sub...