English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Th e timely detection of dangerous rail defects is extremely important since they can lead to accidents with signifi cant material costs and human victims. Th erefore, rails are systematically inspected for internal and surface defects using various non-destructive testing (NDT) techniques. Th e most common of which are ultrasonic and magnetic fl ux leakage (MFL) methods. Nowadays testing carriages based on MFL are widely used for speed inspection of the railway tracks. Th ey allow to control state of the rail head on a depth until 78 mm at velocities from 20 to 80 km/h during diff erent weather conditions. Th e most important issue in all methods of NDT is selection of information about defects from defectoscopic signals. Unfortunately, at this time, experience of a wagon-defectoscope operator is the main guideline in choosing the right testing evaluation. Th at is why automation of the defects detection process is the basic direction for improving existing NDT facilities, implementation of which is impossible without involvement of the modern digital signal processing tools (DSP). Using of the ANN is the most appropriate solution for automatic detection of signals from defects [9].

Process of Building Artificial Neural Network for Automatic Detection of Signals from Transverse Cracks in the Rail Head