Abstract
The article presents selected results of research in the area of reducing the risk of defects in railway infrastructure and traffic control devices. The first part of the article will discuss selected topics used in a defectoscope car for automated ultrasonic rail inspections related to the identification of joints and flaws. A method based on the identification of joints and flaws using a neural network will be presented. The second part of the article will cover research on the automatic collection of diagnostic data from railway traffic control devices. The solutions presented concern a simulator of railway traffic control device malfunctions, from which data is extracted to populate a database of malfunctions and then used in the inference process. The article will present partial results of research on both systems.
Publisher
Lukasiewicz Research Network - Poznan Technology Institute
Reference17 articles.
1. Rail Flaw Detection Technologies for Safer, Reliable Transportation: A Review
2. Application of Deep Learning Networks to Segmentation of Surface of Railway Tracks
3. Research on vibration employed for the train traffic control
4. Ciszewski T, Nowakowski W, Bojarczak P. Application of RAMS methodology to computerized railway systems. Transport Means. 2022;1:212-217.
5. Ciszewski T, Nowakowski W, Chrzan M. RailTopoModel and RailML – data exchange standards in railway sector. Archives of Transport System Telematics. 2017;10(4):10-15.