Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Deep learning based water leakage detection for shield tunnel lining
Shield tunnel lining is prone to water leakage, which may further bring about corrosion and structural damage to the walls, potentially leading to dangerous accidents. To avoid tedious and inefficient manual inspection, many projects use artificial intelligence (AI) to detect cracks and water leakage. A novel method for water leakage inspection in shield tunnel lining that utilizes deep learning is introduced in this paper. Our proposal includes a ConvNeXt-S backbone, deconvolutional-feature pyramid network (D-FPN), spatial attention module (SPAM). and a detection head. It can extract representative features of leaking areas to aid inspection processes. To further improve the model’s robustness, we innovatively use an inversed low-light enhancement method to convert normally illuminated images to low light ones and introduce them into the training samples. Validation experiments are performed, achieving the average precision (AP) score of 56.8%, which outperforms previous work by a margin of 5.7%. Visualization illustrations also support our method’s practical effectiveness.
Deep learning based water leakage detection for shield tunnel lining
Shield tunnel lining is prone to water leakage, which may further bring about corrosion and structural damage to the walls, potentially leading to dangerous accidents. To avoid tedious and inefficient manual inspection, many projects use artificial intelligence (AI) to detect cracks and water leakage. A novel method for water leakage inspection in shield tunnel lining that utilizes deep learning is introduced in this paper. Our proposal includes a ConvNeXt-S backbone, deconvolutional-feature pyramid network (D-FPN), spatial attention module (SPAM). and a detection head. It can extract representative features of leaking areas to aid inspection processes. To further improve the model’s robustness, we innovatively use an inversed low-light enhancement method to convert normally illuminated images to low light ones and introduce them into the training samples. Validation experiments are performed, achieving the average precision (AP) score of 56.8%, which outperforms previous work by a margin of 5.7%. Visualization illustrations also support our method’s practical effectiveness.
Deep learning based water leakage detection for shield tunnel lining
Front. Struct. Civ. Eng.
Liu, Shichang (Autor:in) / Xu, Xu (Autor:in) / Jeon, Gwanggil (Autor:in) / Chen, Junxin (Autor:in) / He, Ben-Guo (Autor:in)
Frontiers of Structural and Civil Engineering ; 18 ; 887-898
01.06.2024
12 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Deep learning based water leakage detection for shield tunnel lining
| Springer Verlag | 2024
Deep learning-based instance segmentation of cracks from shield tunnel lining images
| Taylor & Francis Verlag | 2022