The study investigates the cracking and damage of shield tunnel segmented lining via the field observations and measurements of a case in Shanghai metro system. The observations are carried out on local damage of segment, segment cracking and joint dislocation, respectively. Notable deformation can be observed on several lining rings. Two parameters, proportion of damaged rings and radius ovality (O_R), are introduced to describe to what extent the lining rings are damaged in a tunnel section and how large the transverse deformation of the lining ring is. The construction-relevant data, such as attitude of shield machine and assembled lining rings, are collected and analysed to explore the exact causes for tunnel sections with different characteristics of cracking and damage. Surrounding environment was checked and numerical results are also presented to validate our speculation.

Finding a low-cost and highly efficient method for identifying subway tunnel damage can greatly reduce catastrophic accidents. At present, tunnel health monitoring is mainly based on the observation of apparent diseases and vibration monitoring, which is combined with a manual inspection to perceive the tunnel health status. However, these methods have disadvantages such as high cost, short working time, and low identification efficiency. Thus, in this study, a tunnel damage identification algorithm based on the vibration response of in-service train and WPE-CVAE is proposed, which can automatically identify tunnel damage and give the damage location. The method is an unsupervised novelty detection that requires only sufficient normal data on healthy structure for training. This study introduces the theory and implementation process of this method in detail. Through laboratory model tests, the damage of the void behind the tunnel wall is designed to verify the performance of the algorithm. In the test case, the proposed method achieves the damage identification performance with a 96.25% recall rate, 86.75% hit rate, and 91.5% accuracy. Furthermore, compared with the other unsupervised methods, the method performance and noise immunity are better than others, so it has a certain practical value.

Under the dual effects of the rapid growth of tunnel mileage and operating years, the application and research of tunnel crack identification based on machine vision are increasing with the vigorous development of machine vision. However, due to the complex environment in tunnels, it is difficult to quickly obtain tunnel lining cracks via computer visions in the tunnel. Therefore, this paper presents the design of a fast acquisition system with the geometric feature analysis for tunnel lining cracks, which has been integrated into a tunnel fast inspection vehicle with a machine vision module. Through the research on the image acquisition system of the tunnel lining, the parameter selection of the crack shooting hardware system is determined, and the fast calculation method of shooting parameters is proposed. The geometric characteristic analysis of the tunnel lining crack image is employed to calculate crack width and determine the optimal gray value of crack extraction. Field tests have been conducted in the highway tunnels in Zhejiang and Yunnan provinces in China and the result indicates that the proposed approach yields much better performance in the detection efficiency, whose time of detection is only 1%, and the number of personnel required is only 40% of the traditional pure manual method. Compared with similar systems, it also has significant advantages in crack resolution and detection speed. This research provides a means of rapid acquisition of tunnel cracks and laying a foundation for the evaluation of the service performance of the tunnel.

A series of field vibration tests were carried out at an underground metro station underneath the high speed railway by installing accelerometers both on the side wall of the metro station and in the surrounding soil. Within the frequency domain of 0–200 Hz, the attenuation, transmission, and frequency response properties of vibration for both the underground structure and the surrounding soil were analyzed and compared. The attenuation index is found to be decreased with the increase of underground structure stiffness. The existence of damping and coupling effect of the surrounding soil, as well as the interference of axle spectrum from excitation sources, makes it very challenging to separate the frequency response characteristics of structures from soil at FFT (Fast Fourier Transform) spectrum. The combined NExT (Natural Excitation Technique) and HHT (Hilbert–Huang Transform) method are thus used to study the waveforms and propagation velocities of vibration waves in underground structure and surrounding soil. The wave types and their speeds are determined and used for evaluating the structural elastic modulus. Compared with the attenuation index or natural frequency, wave velocity is easier to be recognized, is sensitive to the change of the structural stiffness, and requires limited number of sensors in the field. Based on the properties of the vibration characteristics studied in this work, the wave velocity based method is recommended for the health monitoring of underground structures.

The application of Light Detection And Ranging (LiDAR) technology has become increasingly extensive in tunnel structure monitoring. The proposed processing method aims to carry out non-contact monitoring for circular stormwater sewage tunnels and provides an efficient workflow. This allows the automatic processing of raw point data and the acquisition of visualization results to analyze the health state of a tunnel within a short period of time. The proposed processing method employs a series of algorithms to extract the point cloud of a single tunnel segment without obvious noise by main three steps: axis acquisition, segment extraction, and denoising. The tunnel axis is extracted by fitting boundaries of the tunnel point cloud projection in the plane. With the guidance of the axis, the entire preprocessed tunnel point cloud is segmented by equal division to get a section of the tunnel point cloud which corresponds to a single tunnel segment. Then, the noise in every single point cloud segment is removed by clustering the algorithm twice, based on the distance and intensity. Finally, clean point clouds of tunnel segments are processed by an effective deformation extraction processor to determine the ovality and to get a three-dimensional visual deformation nephogram. The proposed method can significantly improve the efficiency of LiDAR data processing and extend the application of LiDAR technology in circular stormwater sewage tunnel monitoring.