A Novel Approach to Automated 3D Spalling Defects Inspection in Railway Tunnel Linings Using Laser Intensity and Depth Information

The detection of concrete spalling is critical for tunnel inspectors to assess structural risks and guarantee the daily operation of the railway tunnel. However, traditional spalling detection methods mostly rely on visual inspection or camera images taken manually, which are inefficient and unreliable. In this study, an integrated approach based on laser intensity and depth features is proposed for the automated detection and quantification of concrete spalling. The Railway Tunnel Spalling Defects (RTSD) database, containing intensity images and depth images of the tunnel linings, is established via mobile laser scanning (MLS), and the Spalling Intensity Depurator Network (SIDNet) model is proposed for automatic extraction of the concrete spalling features. The proposed model is trained, validated and tested on the established RSTD dataset with impressive results. Comparison with several other spalling detection models shows that the proposed model performs better in terms of various indicators such as MPA (0.985) and MIoU (0.925). The extra depth information obtained from MLS allows for the accurate evaluation of the volume of detected spalling defects, which is beyond the reach of traditional methods. In addition, a triangulation mesh method is implemented to reconstruct the 3D tunnel lining model and visualize the 3D inspection results. As a result, a 3D inspection report can be outputted automatically containing quantified spalling defect information along with relevant spatial coordinates. The proposed approach has been conducted on several railway tunnels in Yunnan province, China and the experimental results have proved its validity and feasibility.

Mechanism Analysis of Spalling Defect on Rail Surface under Rolling Contact Conditions

Under the wheel/rail contact loading conditions, the microcracks on the rail surface propagate, leading to spalling defect or rail fracture and threatening the travelling safety of high-speed railway directly. In order to analyze the mechanism of the crack propagation on the rail surface, the calculation model of the wheel/rail contact fatigue was established, and the variation of the stress intensity factor at the crack tip when the crack length was increased from 0.1 mm to 2 mm was obtained. Based on the mixed-mode fracture criterion and Paris growth theory, the mechanism of the crack propagation on the rail surface was analyzed. The results show that when the microcrack grows to macrocrack, the mode of the fatigue crack on the rail surface is mixed including sliding mode and open mode. With the increase of the crack length, the stress intensity factor KI increases first and then decreases gradually, and the relative dangerous location of the open-mode crack moves from the inner edge of the contact area to the outer edge, while the factor KII is increasing during the whole propagation process, and the relative dangerous location of the sliding-mode crack remains unchanged basically. The main failure mode of crack is open during the initial stage and then transforms into sliding mode with the crack length increasing. The crack tends to propagate upward and leads to spalling defect when the crack length is between 0.3 and 0.5 mm. This propagation path is basically identical with the spalling path of the service rail. The research results will provide a basis for improving the antifatigue performance of rail and establishing the grinding procedure.

Early Diagnosis of Spalling in the Gear Teeth

The monitoring and vibratory analysis of gear transmission allow the prediction of a possible malfunction and breakdowns. As the gear transmission product non-stationary signals its treatment is too difficult with the usual tools of signal processing witch can product errors in its interpretation. As the characteristics of gear frequencies are predetermined, it is proposed to monitor (fault identification) using wavelet analysis. To simulate the signal to be analyzed, we intentionally introduced a spalling defect. We chose the Daubechies wavelet type which are the most used in diagnostic. The aim of this work is to try to control the various parameters related to the wavelet analysis for reliable and inexpensive detection, i.e., the order of the wavelet and level decomposition. The approach witch was previously used for bearings, consists on observing the kurtosis for several orders wavelet based on the default severity..