To ensure traffic safety of railway transport, non-destructive test of rails is regularly carried out by using various approaches and methods, including magnetic and eddy current flaw detection methods. An automatic analysis of large data sets (defectgrams) that come from the corresponding equipment is an actual problem. The analysis means a process of determining the presence of defective sections along with identifying structural elements of railway tracks on defectograms. This article is devoted to the problem of recognition of rail structural element images in magnetic and eddy current defectograms. Three classes of rail track structural elements are considered: 1) a bolted joint with straight or beveled connection of rails, 2) a butt weld of rails, and 3) an aluminothermic weld of rails. Images that cannot be assigned to these three classes are conditionally considered as defects and are placed in a separate fourth class. For image recognition of structural elements in defectograms a neural network is applied. The neural network is implemented by using the open library TensorFlow. To this purpose each selected (picked out) area of a defectogram is converted into a graphic image in a grayscale with size of 20 x 39 pixels.
To ensure tra c safety of railway transport, non-destructive test of rails is regularly carried out by using various approaches and methods, including eddy-current aw detection methods. An automatic analysis of large data sets (defectograms) that come from the corresponding equipment is an actual problem. e analysis means a process of determining the presence of defective sections along with identifying structural elements of railway tracks in defectograms. is article is devoted to the problem of recognizing images of long structural elements of rails in eddy-current defectograms. Two classes of rail track structural elements are considered: 1) rolling stock axle counters, 2) rail crossings. Long marks that cannot be assigned to these two classes are conditionally considered as defects and are placed in a separate third class. For image recognition of structural elements in defectograms a convolutional neural network is applied. e neural network is implemented by using the open library TensorFlow. To this purpose each selected (picked out) area of a defectogram is converted into a graphic image in a grayscale with size of 30 x 140 points.
To ensure traffic safety of railway transport, non-destructive tests of rails are regularly carried out by using various approaches and methods, including eddy-current flaw detection methods. An automatic analysis of large data sets (defectograms) that come from the corresponding equipment is an actual problem. The analysis means a process of determining the presence of defective sections along with identifying structural elements of railway tracks in defectograms. This article continues the cycle of works devoted to the problem of automatic recognizing images of defects and structural elements of rails in eddy-current defectograms. In the process of forming these images, only useful signals are taken into account, the threshold levels of amplitudes of which are determined automatically from eddy-current data. The previously used algorithm for finding threshold levels was focused on situations in which the vast majority of signals coming from the flaw detector is a rail noise. A signal is considered useful and is subject to further analysis if its amplitude is twice the corresponding noise threshold. The article is devoted to the problem of correcting threshold levels, taking into account the need to identify extensive surface defects of rails. An algorithm is proposed for finding the values of threshold levels of rail noise amplitudes with their subsequent correction in the case of a large number of useful signals from extensive defects. Examples of the algorithm’s operation on real eddy-current data are given.
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.