Vibration Analysis to Detect Anomalies on Railway Track Using Unsupervised Machine Learning

Sandhy, Rienetta Ichmawati Delia and Ismail, Andhi Akhmad and Bahiuddin, Irfan and Cahya, Syarif Muhammad Nur and Winarno, Agustinus and Dhaniswara, Aryadhatu (2023) Vibration Analysis to Detect Anomalies on Railway Track Using Unsupervised Machine Learning. In: 2023 IEEE 9th International Conference on Smart Instrumentation, Measurement and Applications (ICSIMA), 17 - 18 October 2023, Kuala Lumpur, Malaysia.

[thumbnail of Vibration_Analysis_to_Detect_Anomalies_on_Railway_Track_Using_Unsupervised_Machine_Learning.pdf] Text
Vibration_Analysis_to_Detect_Anomalies_on_Railway_Track_Using_Unsupervised_Machine_Learning.pdf - Published Version
Restricted to Registered users only

Download (1MB) | Request a copy

Abstract

Efficient railway maintenance is vital for a well-functioning transportation system. Indonesian Law No. 23 of 2007 mandates adherence to railway infrastructure maintenance standards carried out by qualified personnel. Damaged rails lead to disruptive vibrations, necessitating rail vibration detectors for assessment. This study employs smartphone-linked accelerometers to gather vibration data from miniature rails, simulating eight rail conditions, including normal and abnormal scenarios, using Phyphox. The research aims to develop a clustering approach for effective damage detection across diverse railway conditions. By utilizing K-Means Clustering and manual statistical analyses, distinct vibration patterns corresponding to different damage levels are identified. Machine learning experiments reveal optimal clustering with data variations up to three, as higher variations yield multiclass misclassification errors. This study demonstrates K-Means Clustering's efficacy in categorizing rail damage patterns and emphasizes limiting data variations to enhance accuracy.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Library Dosen
Uncontrolled Keywords: Vibration, Railway, Machine Learning, Clustering, K-Means, Statistical Analysis
Subjects: T Technology > TA Engineering (General). Civil engineering (General)
Divisions: Faculty of Engineering > Civil Engineering & The Enviromental Department
Depositing User: Rita Yulianti Yulianti
Date Deposited: 14 Aug 2024 03:37
Last Modified: 14 Aug 2024 03:37
URI: https://ir.lib.ugm.ac.id/id/eprint/79

Actions (login required)

View Item
View Item