{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:26:10Z","timestamp":1783009570527,"version":"3.54.5"},"reference-count":28,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2023,7,8]],"date-time":"2023-07-08T00:00:00Z","timestamp":1688774400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Defective wheels pose a significant challenge in railway transportation, impacting operational performance and safety. Excessive traction and braking forces give rise to deviations from the intended conical tread shape, resulting in amplified vibrations and noise. Moreover, these deviations contribute to the accelerated damage of track components. Detecting wheel defects at an early stage is crucial to ensure safe and comfortable operation, as well as to minimize maintenance costs. However, the presence of various vibrations, such as those induced by the track, traction motors, and other rolling stock subsystems, poses a significant challenge for onboard detection techniques. These vibrations create difficulties in accurately identifying wheel defects in real-time during operational activities, often resulting in false alarms. This research paper aims to address this issue by using a hybrid deep learning-based approach for the accurate detection of various types of wheel defects using accelerometer data. The proposed approach aims to enhance wheel defect detection accuracy while considering onboard techniques\u2019 cost-effectiveness and efficiency. A realistic simulation model of the railway wheelset is developed to generate a comprehensive dataset. To generate vibration data in various scenarios, the model is simulated for 20 s under different conditions, including one non-faulty scenario and six faulty scenarios. The simulations are conducted at different speeds and track conditions to capture a wide range of operating conditions. Within each simulation iteration, a total of 200,000 data points are generated, providing a comprehensive dataset for analysis and evaluation. The generated data are then utilized to train and evaluate a hybrid deep learning model, employing a multi-layer perceptron (MLP) as a feature extractor and multiple machine learning models (support vector machine, random forest, decision tree, and k-nearest neighbors) for performance comparison. The results demonstrate that the MLP-RF (multi-layer perceptron with random forest) model achieved an accuracy of 99%, while the MLP-DT (multi-layer perceptron with decision tree) model achieved an accuracy of 98%. These high accuracy values indicate the effectiveness of the models in accurately classifying and predicting the outcomes. The contributions of this research work include the development of a realistic simulation model, the evaluation of sensor layout effectiveness, and the application of deep learning techniques for improved wheel flat detections.<\/jats:p>","DOI":"10.3390\/s23146248","type":"journal-article","created":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T01:02:50Z","timestamp":1688950970000},"page":"6248","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Wheel Defect Detection Using a Hybrid Deep Learning Approach"],"prefix":"10.3390","volume":"23","author":[{"given":"Khurram","family":"Shaikh","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Mehran University of Engineering and Technology, Jamshoro 76062, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7947-9178","authenticated-orcid":false,"given":"Imtiaz","family":"Hussain","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4340-9602","authenticated-orcid":false,"given":"Bhawani Shankar","family":"Chowdhry","sequence":"additional","affiliation":[{"name":"NCRA-Condition Monitoring Lab, Mehran University of Engineering and Technology, Jamshoro 76062, Pakistan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,7,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1176","DOI":"10.1109\/TITS.2017.2720721","article-title":"Wheel Defect Detection with Machine Learning","volume":"19","author":"Krummenacher","year":"2018","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1177\/0954409716656218","article-title":"Condition monitoring approaches for the detection of railway wheel defects","volume":"231","author":"Alemi","year":"2017","journal-title":"Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Mohammadi, M., Mosleh, A., Vale, C., Ribeiro, D., Montenegro, P., and Meixedo, A. (2023). An Unsupervised Learning Approach for Wayside Train Wheel Flat Detection. Sensors, 23.","DOI":"10.3390\/s23041910"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"443","DOI":"10.22581\/muet1982.2102.18","article-title":"Signal-Based Indirect Wheel Profile Estimation Technique for Solid Axle Railway Wheelset","volume":"40","author":"Shaikh","year":"2021","journal-title":"Mehran Univ. Res. J. Eng. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1644","DOI":"10.1080\/00423114.2022.2103436","article-title":"Early wheel flat detection: An automatic data-driven wavelet-based approach for railways","volume":"61","author":"Mosleh","year":"2023","journal-title":"Veh. Syst. Dyn."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1243\/0954409001531351","article-title":"Out-of-round railway wheels-a literature survey","volume":"214","author":"Nielsen","year":"2000","journal-title":"Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"107540","DOI":"10.1016\/j.ymssp.2020.107540","article-title":"An on-board detection framework for polygon wear of railway wheel based on vibration acceleration of axle-box","volume":"153","author":"Sun","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1088","DOI":"10.1177\/0954409715576015","article-title":"A comprehensive prediction model for vehicle\/track\/soil dynamic response due to wheel flats","volume":"230","author":"Alexandrou","year":"2016","journal-title":"Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1177\/0954409719838115","article-title":"A new strategy to estimate static loads for the dynamic weighing in motion of railway vehicles","volume":"234","author":"Mosleh","year":"2019","journal-title":"Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.measurement.2018.03.072","article-title":"Wheel flat detection algorithm for onboard diagnostic","volume":"123","author":"Bosso","year":"2018","journal-title":"Measurement"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.measurement.2015.11.014","article-title":"Train wheel diagnostics by laser ultrasonics","volume":"80","author":"Cavuto","year":"2016","journal-title":"Measurement"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1687814016676000","DOI":"10.1177\/1687814016676000","article-title":"Wayside detection of faults in railway axle bearings using time spectral kurtosis analysis on high-frequency acoustic emission signals","volume":"8","author":"Amini","year":"2016","journal-title":"Adv. Mech. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"607","DOI":"10.3390\/e16010607","article-title":"Defect Detection for Wheel-Bearings with Time-Spectral Kurtosis and Entropy","volume":"16","author":"Chen","year":"2014","journal-title":"Entropy"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1177\/0954409714559758","article-title":"Online condition monitoring of rolling stock wheels and axle bearings","volume":"230","author":"Papaelias","year":"2016","journal-title":"Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"111959","DOI":"10.1016\/j.measurement.2022.111959","article-title":"Rail wheel tread defect detection using improved YOLOv3","volume":"203","author":"Xing","year":"2022","journal-title":"Measurement"},{"key":"ref_16","unstructured":"Asplund, M. (2016). Wayside Condition Monitoring System for Railway Wheel Profiles: Applications and Performance Assessment. [Ph.D. Dissertation, Lule\u00e5 Tekniska Universitet]."},{"key":"ref_17","first-page":"1","article-title":"Condition Monitoring of Metro Wheelsets Using Wayside Vibration and Acoustic Sensors","volume":"1","author":"Kilinc","year":"2022","journal-title":"Res. Sq."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Saba, E., Kalwar, I.H., Unar, M.A., Memon, A.L., and Pirzada, N. (2021). Fuzzy Logic-Based Identification of Railway Wheelset Conicity Using Multiple Model Approach. Sustainability, 13.","DOI":"10.3390\/su131810249"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1080\/23248378.2020.1795942","article-title":"Designing a lightweight 1D convolutional neural network with Bayesian optimization for wheel flat detection using car body accelerations","volume":"9","author":"Shi","year":"2021","journal-title":"Int. J. Rail Transp."},{"key":"ref_20","unstructured":"Hussain, I. (2012). Multiple Model-Based Real-Time Estimation of Wheel-Rail Contact Conditions. [Ph.D. Thesis, University of Salford]."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1080\/00423114.2012.708759","article-title":"Estimation of wheel-rail contact conditions and adhesion using the multiple model approach","volume":"51","author":"Hussain","year":"2013","journal-title":"Veh. Syst. Dyn."},{"key":"ref_22","unstructured":"Hussain, I., and Mei, T.X. (2011, January 14\u201319). Identification of the wheel-rail contact condition for traction and braking control. Proceedings of the 22nd International Symposium on Dynamics of Vehicles on Roads and Tracks, Manchester, UK."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"753","DOI":"10.22581\/muet1982.2104.06","article-title":"Model-based indirect conicity estimation technique for solid axle railway wheelset","volume":"40","author":"Saba","year":"2021","journal-title":"Mehran Univ. Res. J. Eng. Technol."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Baasch, B., Heusel, J., Roth, M., and Neumann, T. (2021). Train Wheel Condition Monitoring via Cepstral Analysis of Axle Box Accelerations. Appl. Sci., 11.","DOI":"10.3390\/app11041432"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Vale, C. (2021). Wheel Flats in the Dynamic Behavior of Ballasted and Slab Railway Tracks. Appl. Sci., 11.","DOI":"10.3390\/app11157127"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1080\/00423114.2017.1296963","article-title":"An overview: Modern techniques for railway vehicle on-board health monitoring systems","volume":"55","author":"Li","year":"2017","journal-title":"Veh. Syst. Dyn."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Tsunashima, H. (2019). Condition Monitoring of Railway Tracks from Car-Body Vibration Using a Machine Learning Technique. Applied Sciences. Appl. Sci., 9.","DOI":"10.3390\/app9132734"},{"key":"ref_28","first-page":"3351","article-title":"FPGA implementation of extended Kalman filter for parameters estimation of railway wheelset","volume":"74","author":"Mal","year":"2023","journal-title":"Comput. Mater. Contin."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/14\/6248\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:08:52Z","timestamp":1760126932000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/14\/6248"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,8]]},"references-count":28,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2023,7]]}},"alternative-id":["s23146248"],"URL":"https:\/\/doi.org\/10.3390\/s23146248","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,8]]}}}