This paper discusses the influence of foundation pit excavation and inrushing for confined water to pile bearing capacity through a typical engineering case. In this case, the distribution of aquifer and the depth of water level are investigated by field test which are used to calculate and find the causes of inrushing for confined water, combined with the process of inrushing and engineering construction conditions, the causes of inrushing for confined water are found. Then in-situ static cone penetration test is carried out, which is used to find the disturbance depth and extend of soil layers caused by foundation pit excavation and inrushing for confined water, while the relations are suggested between disturbance degree of each soil layer and pile capacity parameters, with this relationship, it is easy to see the disturbance law of these influences. The results show that confined water going through the plug in pipe pile is the main reason of inrushing, the depth of influence of foundation pit excavation on the soil strength below the pit bottom is about 6.5 meters to 9 meters, and the disturbance degree decreases linearly with depth increase. By comparison, the inrushing's influence on the soil strength is much greater than foundation pit excavation, the influence range are from a distance of 2 meters above the pile tip to a distance of 4 meters under the pile tip, and the maximum disturbance degree reaches 0.91. Additionally, the lowest bearing capacity of pile foundation is at the location of inrushing point, the farther away from the inrushing point, the larger bearing capacity can be achieved.

With the rapid development of urban metros, the detection of shield tunnel leakages has become an important research topic. Progressive technological innovations such as deep learning-based methods provide an effective way to detect tunnel leakages accurately and automatically. However, due to the complex shapes and sizes of leakages, it is challenging for existing algorithms to detect such defects. To address these issues, this paper proposes a novel deep learning-based model named segmenting objects by locations network v2 for tunnel leakages (SOLOv2-TL), which is enhanced by ResNeXt-50, deformable convolution, and path augmentation feature pyramid network (PAFPN). In the SOLOv2-TL, ResNeXt-50 coupled with deformable convolution is the backbone for boosting feature extraction ability that would enable the model sensitivity to leakages of different shapes. The PAFPN is introduced as the neck to reduce the loss of leakage information and more accurately assign leakages of different sizes to their corresponding feature levels. The superior performances of ResNeXt-50 with deformable convolution and PAFPN were validated by ablation tests. Moreover, the segmentation results obtained by SOLOv2-TL were compared with those by the mask region-based convolutional neural network (Mask R-CNN), Cascade Mask R-CNN, and SOLO which demonstrated that the mAP, mAP₅₀, and mAP₇₅ of SOLOv2-TL are higher than those of the other methods, where mAP indicates the mean mask average precision (AP) at intersection over union (IoU) = 0.50:0.05:0.95, mAP₅₀ refers to the mean mask AP with an IoU threshold of 0.50, and mAP₇₅ denotes the mean mask AP with an IoU threshold of 0.75. Finally, a leakage area quantification method is presented.