Accuracy Assessment of Railway Track Inspection Equipment 'Void Meter' Based on the Internet of Things
DOI:
https://doi.org/10.71225/jstn.v2i3.115Keywords:
Void Meter, Internet of Things, Dynamic Skilu, Ballast Void Measurement, Data AccuracyAbstract
Dynamic skilu caused by ballast voids is one of the main causes of train derailments in Indonesia. Early detection of this condition still relies on measurement trains, which have limited inspection intervals. This study aims to test the accuracy of the third-generation void meter based on the Internet of Things (IoT), which has been redesigned to enhance the precision of measuring ballast voids, train speed, and rail temperature. The research methods include the collection of primary and secondary data, field testing of the device, and statistical analysis. Analysis was conducted using standard deviation tests, ANOVA, the Mann–Whitney test, and MAPE. Test results showed that the system can display data in real-time through the Blynk and ThingSpeak platforms and provide automatic notifications when measurement values exceed tolerance limits. The standard deviation of the device is lower than that of conventional devices, MAPE for all parameters is <10%, and the results of the ANOVA and Mann–Whitney tests show no significant differences between data groups. Thus, the third-generation void meter has proven to have high accuracy and consistency, making it suitable for continuous railway track inspections. Additionally, the void meter has been proven to be 59.70% more cost-effective than the densometer.
References
[1] X. Liu, M. R. Saat, and C. P. L. Barkan, “Analysis of causes of major train derailment and their effect on accident rates,” Transp. Res. Rec., no. 2289, pp. 154–163, 2012, doi: 10.3141/2289-20.
[2] Laporan Tahunan Komite Nasional Keselamatan Transportasi (KNKT) Tahun 2020, “Laporan Tahunan 2021,” pp. 220–225, 2021.
[3] A. Friscilya and A. F. Ismaili, “Analysis Of Damage and Track Quality Index (TQI) On Rail Road Components (Case Study: Cross Wates Station-Sentolo Station Km.516+300-Km.520+300 Operational Area 6 Yogyakarta),” pp. 1–2, 2021.
[4] M. Sysyn, O. Nabochenko, and V. Kovalchuk, “Experimental investigation of the dynamic behavior of railway track with sleeper voids,” Railw. Eng. Sci., vol. 28, no. 3, pp. 290–304, 2020, doi: 10.1007/s40534-020-00217-8.
[5] S. Kaewunruen, J. Sresakoolchai, and H. Stittle, Machine Learning to Identify Dynamic Properties of Railway Track Components, vol. 22, no. 11. 2022. doi: 10.1142/S0219455422501097.
[6] B. Leitner, “A General Model for Railway Systems Risk Assessment with the Use of Railway Accident Scenarios Analysis,” Procedia Eng., vol. 187, pp. 150–159, 2017, doi: 10.1016/j.proeng.2017.04.361.
[7] A. De Rosa et al., “Monitoring of lateral and cross level track geometry irregularities through onboard vehicle dynamics measurements using machine learning classification algorithms,” Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit, vol. 235, no. 1, pp. 107–120, 2021, doi: 10.1177/0954409720906649.
[8] B. Environment and W. I. T. Press, “Transactions on the Built Environment vol 11, © 1995 WIT Press, www.witpress.com, ISSN 1743-3509,” vol. 11, 1995.
[9] K. Marciniak, P. Majewski, and J. Reiner, “Inspection of railway catenary systems using machine learning with domain knowledge integration,” Sci. Rep., vol. 15, no. 1, pp. 1–17, 2025, doi: 10.1038/s41598-025-15289-x.
[10] D. Sanjaya Atmaja, P. Mahendra Shakti, and M. Willy Eka Pratama, “Perencanaan dan Pembuatan Alat Pendeteksi Skilu Dinamis pada jalan rel kereta api,” J. Perkeretaapi. Indones., vol. I, no. November, pp. 75–79, 2017.
[11] N. Kaviani, P. S. Ricci, P. R. Licciardello, and P. L. Rizzetto, Track Geometry Monitoring using Measured Data from. 2024.
[12] B. B. Y. Afriansyah, “Re-Desain Alat Void Meter Berbasis Mikrokontroler Untuk Pemeriksaan Jalan Rel,” 2024.
[13] B. R. Nugroho, W. T. Adi, and H. W. Puruhita, “RE – DESAIN DAN PENINGKATAN ALAT PEMERIKSAAN JALAN REL ‘ VOID METER ’ BERBASIS INTERNET OF THINGS,” vol. x, no. x, pp. 1–10, 2025.
[14] S. Pitou, “A Guide for Students,” Renascence, vol. 13, no. 1, pp. 52–53, 1960, doi: 10.5840/renascence196013115.
[15] O. Jurjut, P. Georgieva, L. Busse, and S. Katzner, “Learning enhances sensory processing in mouse V1 before improving behavior,” J. Neurosci., vol. 37, no. 27, pp. 6460–6474, 2017, doi: 10.1523/JNEUROSCI.3485-16.2017.
[16] B. S. Qolby, “Uji mann whitney dalam statistika non parametrik perbedaan tingkat penggunaan kendaraan umum dengan kendaraan pribadi,” J. PkM Pengabdi. Kpd. Masy., vol. 2, no. 8, p. 15, 2014.
[17] C. Kasemset, N. Sae-Haew, and A. Sopadang, “Multiple regression model for forecasting quantity of supply of off-season longan,” Chiang Mai Univ. J. Nat. Sci., vol. 13, no. 3, pp. 391–402, 2014, doi: 10.12982/cmujns.2014.0044.
[18] I. Nurvianti, B. D. Setiawan, and F. A. Bachtiar, “Peramalan Jumlah Penumpang Keberangkatan Kereta Api di DKI Jakarta Menggunakan Metode Double Exponential Smoothing dan Triple Exponential Smoothing,” Pengemb. Teknol. Inf. dan Ilmu Komput., vol. 3, no. 6, pp. 5257–5263, 2019, [Online]. Available: http://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/5458%0Ahttp://j-ptiik.ub.ac.id/index.php/j-ptiik/article/download/5458/2567
[19] D. Abas, A. Ghany, T. Shekhan, and U. P. Duhok, “Perancangan Sistem Pemantauan EKG Berbasis Kesehatan Aplikasi Blynk untuk Internet of Things Machine,” vol. 01, no. 02, pp. 106–111, 2020.
[20] Wijayanti and Dewi Nurhidayati, “Perbandingan Alat Ukur dalam Penentuan Ketebalan Kulit Imitasi,” Berk. Penelit. Teknol. Kulit, Sepatu, dan Prod. Kulit, vol. 21, no. 1, pp. 18–23, 2022, doi: 10.58533/bptkspk.v21i1.156.
