Data Driven Detection of Railway Point Machines Failures
| Autor: | Christophe Marsala, Simon Fossier, Iwo Doboszewski |
|---|---|
| Přispěvatelé: | Thales Research and Technology [Palaiseau], THALES, Learning, Fuzzy and Intelligent systems (LFI), LIP6, Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS) |
| Rok vydání: | 2019 |
| Předmět: |
Centralized traffic control
Ensemble methods Computer science 010401 analytical chemistry Decision tree Early detection 020206 networking & telecommunications 02 engineering and technology Classification computer.software_genre 01 natural sciences Machine failure Ensemble learning [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI] 0104 chemical sciences Data-driven [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] Machine learning 0202 electrical engineering electronic engineering information engineering [INFO]Computer Science [cs] Point (geometry) Data mining Point machines Failures prevention computer |
| Zdroj: | SSCI IEEE Symposium Series on Computational Intelligence (SSCI)-Computational Intelligence in Vehicles and Transportation Systems (CIVTS) IEEE Symposium Series on Computational Intelligence (SSCI)-Computational Intelligence in Vehicles and Transportation Systems (CIVTS), Dec 2019, Xiamen, China. pp.1233-1240 |
| Popis: | International audience; In this paper, a novel approach to early detection of railway point machines failures is presented. Easily accessible data from Centralized Traffic Control (CTC) systems, along with meteorological data, are utilized to build a classification system recognizing risk factors for railway point machine failure. We present and discuss a framework that aims at extracting information from the raw railway logs, and discuss the issues that need to be solved to make the framework properly operational. We show that ensemble methods utilizing decision trees are able to provide meaningful classification accuracy for this problem. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|