Next Article in Journal
SCADA-Based Stator-Winding Prognostics: A Temperature-Weighted Work Index for Industrial Motor Health Monitoring
Next Article in Special Issue
An AI-Based Framework Combining Categorical Alarm and Continuous Data for Power Estimation and Anomaly Detection in Photovoltaic Systems
Previous Article in Journal
Design Framework for Ground-Vehicle Suspension Actuators Using Digital Twin Technology
Previous Article in Special Issue
Condition Monitoring Model Development for Belt Systems Using Hybrid CNN–BiLSTM Deep-Learning Techniques
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Machines
Volume 14
Issue 4
10.3390/machines14040424
machines-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Online Track Anomaly Detection: Comparison of Different Machine Learning Techniques Through Injection of Synthetic Defects on Experimental Datasets

by
Giovanni Bellacci
1,
Luca Di Carlo
2,
Marco Fiaschi
2,
Luca Bocciolini
2,
Carmine Zappacosta
2 and
Luca Pugi
1,*
1
Department of Industrial Engineering, University of Florence, 50139 Florence, Italy
2
Italcertifer, 50123 Florence, Italy
*
Author to whom correspondence should be addressed.
Machines 2026, 14(4), 424; https://doi.org/10.3390/machines14040424
Submission received: 28 February 2026 / Revised: 23 March 2026 / Accepted: 6 April 2026 / Published: 10 April 2026
(This article belongs to the Special Issue AI-Driven Reliability Analysis and Predictive Maintenance)
Browse Figures
Versions Notes

Abstract

The adoption of instrumented wheelsets on diagnostic trains offers the possibility of continuous monitoring of wheel–rail contact forces. The collection of large datasets can be exploited for diagnostic purposes, aiming to localize specific track defects, allowing significant improvements in terms of safety and maintenance costs. Machine learning (ML) techniques can be used to automate anomaly detection. In this work, the authors compare the application of various ML algorithms based on the identification of different frequency or time-based features of analyzed signals. To perform the activity, a significant number and variety of local defects have been included in the recorded data. From a practical point of view, the insertion of real known defects into an existing line is extremely time-consuming, expensive, and not immune to safety issues. On the other hand, the design of anomaly detection algorithms involves the usage of relatively extended datasets with different faulty conditions. The authors propose deliberately adding real contact force profiles of healthy lines to a mix of synthetic signals, which substantially reproduce the behavior and the variability of foreseen faulty conditions. The results of this work, although preliminary and still to be completed, offer a contribution to the scientific community both in terms of obtained results and adopted methodologies.
Keywords: anomaly detection on railway tracks; machine learning; measurement of contact forces; one-class support vector machine; isolation forest; local outlier factor; condition monitoring anomaly detection on railway tracks; machine learning; measurement of contact forces; one-class support vector machine; isolation forest; local outlier factor; condition monitoring

Share and Cite

MDPI and ACS Style

Bellacci, G.; Di Carlo, L.; Fiaschi, M.; Bocciolini, L.; Zappacosta, C.; Pugi, L. Online Track Anomaly Detection: Comparison of Different Machine Learning Techniques Through Injection of Synthetic Defects on Experimental Datasets. Machines 2026, 14, 424. https://doi.org/10.3390/machines14040424

AMA Style

Bellacci G, Di Carlo L, Fiaschi M, Bocciolini L, Zappacosta C, Pugi L. Online Track Anomaly Detection: Comparison of Different Machine Learning Techniques Through Injection of Synthetic Defects on Experimental Datasets. Machines. 2026; 14(4):424. https://doi.org/10.3390/machines14040424

Chicago/Turabian Style

Bellacci, Giovanni, Luca Di Carlo, Marco Fiaschi, Luca Bocciolini, Carmine Zappacosta, and Luca Pugi. 2026. "Online Track Anomaly Detection: Comparison of Different Machine Learning Techniques Through Injection of Synthetic Defects on Experimental Datasets" Machines 14, no. 4: 424. https://doi.org/10.3390/machines14040424

APA Style

Bellacci, G., Di Carlo, L., Fiaschi, M., Bocciolini, L., Zappacosta, C., & Pugi, L. (2026). Online Track Anomaly Detection: Comparison of Different Machine Learning Techniques Through Injection of Synthetic Defects on Experimental Datasets. Machines, 14(4), 424. https://doi.org/10.3390/machines14040424

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop