Prediction of Rail Contact Fatigue on Crossings Using Image Processing and Machine Learning Methods
Autor: | Olga Nabochenko, Franziska Kluge, Dmitri Gruen, Mykola Sysyn, Ulf Gerber |
---|---|
Rok vydání: | 2019 |
Předmět: |
Feature detection and selection
Surface (mathematics) Surface fatigue Computer science Geography Planning and Development Transportation Computational intelligence Image processing 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences 0502 economics and business Early prediction Electrical and Electronic Engineering Feature set 0105 earth and related environmental sciences Civil and Structural Engineering 050210 logistics & transportation Railway turnout business.industry 05 social sciences Common crossing lcsh:TA1001-1280 lcsh:HE1-9990 Rolling contact fatigue Urban Studies Contact fatigue Automotive Engineering State (computer science) Artificial intelligence lcsh:Transportation engineering lcsh:Transportation and communications business computer |
Zdroj: | Urban Rail Transit, Vol 5, Iss 2, Pp 123-132 (2019) |
ISSN: | 2199-6679 2199-6687 |
DOI: | 10.1007/s40864-019-0105-0 |
Popis: | In this paper, an application of computer vision and machine learning algorithms for common crossing frog diagnostics is presented. The rolling surface fatigue of frogs along the crossing lifecycle is analysed. The research is based on information from high-resolution optical images of the frog rolling surface and images from magnetic particle inspection. Image processing methods are used to pre-process the images and to detect the feature set that corresponds to objects similar to surface cracks. Machine learning methods are used for the analysis of crack images from the beginning to the end of the crossing lifecycle. Statistically significant crack features and their combinations that depict the surface fatigue state are found. The research result consists of the early prediction of rail contact fatigue. |
Databáze: | OpenAIRE |
Externí odkaz: |