Summary
Cracks that develop in railway infrastructural components such as tunnel linings and track systems are not easy to detect on high‐speed rail routes, since inspection time is limited during the daytime and visibility is very poor at night. Meanwhile, cracks to structures such as those above mentioned are strictly monitored and treated to prevent possible malfunction or accident. In this regard, a track measurement vehicle is normally deployed to image track components and measure geometric information. The main goal of the present study was to detect cracks in images and to simultaneously measure the maximum crack width by means of newly introduced deep learning technology. For this, a shape‐sensitive kernel, that is, crack‐like kernel, within a semantic segmentation framework and a modified deep layer model were proposed. In addition to the conventional statistical models such as accuracy and intersection over union, the predicted results of the proposed models were verified by considering the boxplot and root mean square errors of the estimated crack widths. According to the results, the proposed shape‐sensitive kernel function was able to predict crack width more precisely by one or two pixels than the conventional semantic segmentation model. Future work will concentrate on the integration of the crack detection model with deterioration prediction of track geometry in order to enable systematic decision making for the predictive maintenance of railway systems.
Permanent deformation (rutting) is one of the major distresses in asphalt pavement. To predict permanent deformation of asphalt concrete, repeated creep and recovery (or flow number) tests are typically used in the laboratory. However, models for the prediction of permanent deformation that incorporate flow number testing cannot represent the primary region because they concentrate on the secondary region. A new simple permanent deformation model called the incremental model is proposed. The proposed model is derived from the rate model, which is a rigorous mechanical model based on viscoplasticity. Four parameters of the new model provide an understanding of the permanent deformation. Parameter A is related to the initial permanent strain level, and Parameter C provides information about where the secondary region starts. That is, Parameters A and C govern the primary region, where α (alpha) is the slope of the secondary region, and B represents the permanent deformation level of the secondary region. Two mixtures are selected to investigate the deformation characteristics, and repeated creep and recovery tests are performed in compression. The incremental model is verified by applying it to various loading conditions for two mixtures. Furthermore, it is found that α is the material constant and the time-temperature superposition principle is applicable to each parameter. All parameters, except a, depend on both deviatoric stress and reduced load time, which is the product of load time and temperature. The incremental model describes ways to apply the time-temperature supposition principle to permanent deformation.
Recent permanent deformation modeling research at North Carolina State University has resulted in the shift model, which is capable of expressing the permanent strain growth of asphalt concrete as a function of deviatoric stress, load time, and temperature on the basis of the time–temperature superposition and time–stress superposition principles. This paper presents an efficient calibration test protocol for the shift model as well as verification of the model. The proposed test protocol is comprised of triaxial stress sweep (TSS) tests and a reference test. The TSS test is suggested to reduce the number of tests required by applying three deviatoric stresses within one test. Each TSS test was performed at three temperatures: high (TH), intermediate (TI), and low (TL). The reference test was a triaxial repeated load permanent deformation test conducted at TH only. The shift model was calibrated for the polymer-modified dense-graded NY9.5B mix, and the calibrated model was applied successfully to predict strain growth for the composite tests at the three study temperatures and for random load tests at TH. The calibration testing procedure was optimized for the asphalt mixture performance tester. The TSS tests take approximately 2.9 h at TH and 1.5 h at TI and TL. Thus, about a day was required to complete one set of calibration tests under the proposed test protocol. Within 2 to 3 days of testing, depending on the number of replicates, the calibrated shift model is capable of predicting permanent strain growth for different temperatures, load times, and deviatoric stresses.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.