{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T03:51:39Z","timestamp":1772164299769,"version":"3.50.1"},"reference-count":39,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007694","name":"Korea Agency for Infrastructure Technology Advancement (KAIA)","doi-asserted-by":"publisher","award":["RS-2021-KA164547"],"award-info":[{"award-number":["RS-2021-KA164547"]}],"id":[{"id":"10.13039\/501100007694","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In this paper, research was conducted on anomaly detection of wheel flats. In the railway sector, conducting tests with actual railway vehicles is challenging due to safety concerns for passengers and maintenance issues as it is a public industry. Therefore, dynamics software was utilized. Next, STFT (short-time Fourier transform) was performed to create spectrogram images. In the case of railway vehicles, control, monitoring, and communication are performed through TCMS, but complex analysis and data processing are difficult because there are no devices such as GPUs. Furthermore, there are memory limitations. Therefore, in this paper, the relatively lightweight models LeNet-5, ResNet-20, and MobileNet-V3 were selected for deep learning experiments. At this time, the LeNet-5 and MobileNet-V3 models were modified from the basic architecture. Since railway vehicles are given preventive maintenance, it is difficult to obtain fault data. Therefore, semi-supervised learning was also performed. At this time, the Deep One Class Classification paper was referenced. The evaluation results indicated that the modified LeNet-5 and MobileNet-V3 models achieved approximately 97% and 96% accuracy, respectively. At this point, the LeNet-5 model showed a training time of 12 min faster than the MobileNet-V3 model. In addition, the semi-supervised learning results showed a significant outcome of approximately 94% accuracy when considering the railway maintenance environment. In conclusion, considering the railway vehicle maintenance environment and device specifications, it was inferred that the relatively simple and lightweight LeNet-5 model can be effectively utilized while using small images.<\/jats:p>","DOI":"10.3390\/s23229075","type":"journal-article","created":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T10:19:27Z","timestamp":1699525167000},"page":"9075","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["A Methodology of Condition Monitoring System Utilizing Supervised and Semi-Supervised Learning in Railway"],"prefix":"10.3390","volume":"23","author":[{"given":"Jaeseok","family":"Shim","sequence":"first","affiliation":[{"name":"Complex Research Center for Materials & Components of Railway, Seoul National University of Science and Technology, Seoul 01811, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeongseo","family":"Koo","sequence":"additional","affiliation":[{"name":"Department of Railway Safety Engineering, Seoul National University of Science and Technology, Seoul 01811, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongwoon","family":"Park","sequence":"additional","affiliation":[{"name":"A2Mind, 213, Toegye-ro, Jung-gu, Seoul 04557, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,11,9]]},"reference":[{"key":"ref_1","unstructured":"(2022, October 13). Hyundai Rotem. Available online: https:\/\/www.hyundai.co.kr\/story\/CONT0000000000058367."},{"key":"ref_2","unstructured":"Ministry of Land, Infrastructure and Transport (2013). Safety Standards for Urban Railway Vehicles, Republic of Korea, Ministry of Land, Infrastructure and Transport. Article 43, Table 3."},{"key":"ref_3","unstructured":"Korea Railroad Research Institute (2018). Preliminary Study on the Safety Sensing Technology for Railroad: Development of High Performance and High Durability Tire for Light Rail Train and Safety Health Monitoring Technology, Republic of Korea, Korea Railroad Research Institute."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhou, C., Gao, L., Xiao, H., and Hou, B. (2020). Railway Wheel Flat Recognition and Precise Positioning Method Based on Multisensor Arrays. Appl. Sci., 10.","DOI":"10.3390\/app10041297"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.proeng.2017.04.370","article-title":"Examination of Vertical Dynamics of Passenger Car with Wheel Flat Considering Suspension Parameters","volume":"187","author":"Bureika","year":"2017","journal-title":"Procedia Eng."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Peng, X., Zeng, J., Wang, Q., and Zhu, H. (2023). Research on an Identification Method for Wheelset Coaxial Wheel Diameter Difference Based on Trackside Wheelset Lateral Movement Detection. Sensors, 23.","DOI":"10.3390\/s23135803"},{"key":"ref_7","first-page":"745","article-title":"Railway Wheel Flat and Rail Surface Defect Detection by Time-Frequency Analysis","volume":"33","author":"Liang","year":"2013","journal-title":"Chem. Eng. Trans."},{"key":"ref_8","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_9","doi-asserted-by":"crossref","unstructured":"Yang, C., Sun, Y., Ladubec, C., and Liu, Y. (2020). Developing Machine Learning-Based Models for Railway Inspection. Appl. Sci., 11.","DOI":"10.3390\/app11010013"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhang, L., Liu, Y., Zhou, J., Luo, M., Pu, S., and Yang, X. (2022). An Imbalanced Fault Diagnosis Method Based on TFFO and CNN for Rotating Machinery. Sensors, 22.","DOI":"10.3390\/s22228749"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Gao, R., He, Q., Feng, Q., and Cui, J. (2020). In-Service Detection and Quantification of Railway Wheel Flat by the Reflective Optical Position Sensor. Sensors, 20.","DOI":"10.3390\/s20174969"},{"key":"ref_12","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":"2017","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"109856","DOI":"10.1016\/j.ymssp.2022.109856","article-title":"Shock detection of rotating machinery based on activated time-domain images and deep learning: An application to railway wheel flat detection","volume":"186","author":"Ye","year":"2023","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"112862","DOI":"10.1016\/j.measurement.2023.112862","article-title":"Multislice Time-Frequency image Entropy as a feature for railway wheel fault diagnosis","volume":"216","author":"Ye","year":"2023","journal-title":"Measurement"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1016\/j.trc.2011.04.004","article-title":"Railway wheel-flat detection and measurement by ultrasound","volume":"19","author":"Brizuela","year":"2011","journal-title":"Transp. Res. Part C"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1710","DOI":"10.1080\/15732479.2020.1832536","article-title":"An approach for wheel flat detection of railway train wheels using envelope spectrum analysis","volume":"17","author":"Mosleh","year":"2020","journal-title":"Struct. Infrastruct. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"111268","DOI":"10.1016\/j.measurement.2022.111268","article-title":"OORNet: A deep learning model for on-board condition monitoring and fault diagnosis of out-of-round wheels of high-speed trains","volume":"199","author":"Ye","year":"2022","journal-title":"Measurement"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1329","DOI":"10.1080\/00423114.2019.1620956","article-title":"A data-driven method for estimating wheel flat length","volume":"58","author":"Ye","year":"2019","journal-title":"Veh. Syst. Dyn."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1575","DOI":"10.1080\/00423114.2019.1636098","article-title":"Wheel flat can cause or exacerbate wheel polygonization","volume":"58","author":"Ye","year":"2019","journal-title":"Veh. Syst. Dyn."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"108217","DOI":"10.1016\/j.ymssp.2021.108217","article-title":"Robustness enhancement of machine fault diagnostic models for railway applications through data augmentation","volume":"164","author":"Shi","year":"2021","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Shim, J., Koo, J., Park, Y., and Kim, J. (2022). Anomaly Detection Method in Railway Using Signal Processing and Deep Learning. Appl. Sci., 12.","DOI":"10.3390\/app122412901"},{"key":"ref_22","unstructured":"Jing, L. (2018). Modern Railway Engineering, BoD\u2014Books on Demand."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Shim, J., Kim, G., Cho, B., and Koo, J. (2021). Application of Vibration Signal Processing Methods to Detect and Diagnose Wheel Flats in Railway Vehicles. Appl. Sci., 11.","DOI":"10.3390\/app11052151"},{"key":"ref_24","unstructured":"Dassault System (2020). SIMPACK User Assistant 2020x4, Dassault System."},{"key":"ref_25","unstructured":"Shim, J.S. (2022). A Study on the Anomaly Detection of Wheel Flat Using Deep Learning Techniques. [Ph.D. Thesis, Seoul National University of Science and Technology]."},{"key":"ref_26","unstructured":"Korea Agency for Infrastructure Technology Advancement (2018). Condition-Based Smart Maintenance Technology Development Final Report, Republic of Korea, Korea Agency for Infrastructure Technology Advancement."},{"key":"ref_27","first-page":"549","article-title":"Finding Unexpected Test Accuracy by Cross Validation in Machine Learning","volume":"21","author":"Yoon","year":"2021","journal-title":"IJCSNS"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"273","DOI":"10.7467\/KSAE.2017.25.3.273","article-title":"Development of Inspection Methods for Bearing Faults with a Rapid Change of Rotation Speed and Optimization of Pass\/Fail Criteria","volume":"25","author":"Yang","year":"2017","journal-title":"Trans. Korean Soc. Automot. Eng."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc. IEEE"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., and Pang, R. (November, January 27). Searching for MobileNetV3. Proceedings of the 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref_32","unstructured":"Ramachandran, P., Zoph, B., and Le, Q.V. (2017). Searching for activation functions. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1541880.1541882","article-title":"Anomaly Detection: A Survey","volume":"41","author":"Chanodola","year":"2009","journal-title":"ACM Comput. Surv."},{"key":"ref_34","unstructured":"Ruff, L., Vandermeulen, R., Goernitz, N., Deecke, L., Siddiqui, S.A., Binder, A., M\u00fcller, E., and Kloft, M. (2018, January 10\u201315). Deep One-Class Classification. Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden."},{"key":"ref_35","unstructured":"Olson, D.L., and Delen, D. (2008). Advanced Data Mining Techniques, Springer Science & Business Media."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Cremonesi, P., Turrin, R., Lentini, E., and Matteucci, M. (2008, January 17\u201319). An Evaluation Methodology for Collaborative Recommender Systems. Proceedings of the 2008 International Conference on Automated Solutions for Cross Media Content and Multi-Channel Distribution, Florence, Italy.","DOI":"10.1109\/AXMEDIS.2008.13"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Le, N.Q.K., Do, D.T., Hung, T.N.K., Lam, L.H.T., Huynh, T.-T., and Nguyen, N.T.K. (2020). A Computational Framework Based on Ensemble Deep Neural Networks for Essential Genes Identification. Int. J. Mol. Sci., 21.","DOI":"10.3390\/ijms21239070"},{"key":"ref_38","unstructured":"Flach, P. (2016). Encyclopedia of Machine Learning and Data Mining, Springer."},{"key":"ref_39","unstructured":"Powers, D.M.W. (2003, January 24\u201326). Recall and Precision versus the Bookmaker. Proceedings of the International Conference on Cognitive Science (ICSC-2003), Rome, Italy."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/22\/9075\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:20:32Z","timestamp":1760131232000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/22\/9075"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,9]]},"references-count":39,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["s23229075"],"URL":"https:\/\/doi.org\/10.3390\/s23229075","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,9]]}}}