Abstract
This paper proposes a new method to predict the unbalanced load distribution at coal-loaded wagons based on geometrical features by utilizing extreme learning machines. The proposed method is varied at various hyperparameter values and activation functions, also compared with back propagation artificial neural networks using various activation functions. The proposed inputs of the model are the geometrical features extracted from load shape with the pre-determined rule. The model’s output is the load value for each bogie by considering transverse and longitudinal unbalanced load conditions. For developing the model, the training data is obtained from finite element simulation by defining the coal geometries and the weights. The simulation is based on a coal wagon with a 50-Ton capacity. The proposed machine learning model has been evaluated and shows a good agreement between the prediction and the modeling data. Then, the predicted load/stress values can be utilized to assess whether the safety condition is disregarded.
Similar content being viewed by others
Availability of data
The data that support the findings of this study are available upon reasonable request from the authors.
References
Li M, Shao B, Shi X (2022) Impact of high-speed rail on the development efficiency of low-carbon tourism: a case study of an agglomeration in China. Sustainability 14(16):9879. https://doi.org/10.3390/su14169879
Mishra S, Sharan P, Saara K (2022) Compactness measure of rail wheel rolling contact of the freight wagon. Int J Inf Technol (Singap) 14(5):2335–2342. https://doi.org/10.1007/s41870-022-00977-y
Batig A, Hrytsyshyn P, Kuzyshyn A, Milyanych A, Voznyak O, Tereshchak Y (2019) Development of an algorithm for investigation of technical state of wagons’ running gears during their derailment. In: MATEC web of conferences 2019, vol 294, p 03005. https://doi.org/10.1051/matecconf/201929403005
Mańka A, Sitarz M (2016) Effects of a thermal load on the wheel/brake-block subsystem: the thermal conicity of railway wheels. Proc Inst Mech Eng Part F: J Rail Rapid Transit 230(1):193–205. https://doi.org/10.1177/0954409714533106
Miri A, Dhanasekar M, Thambiratnam D, Weston B, Chan THT (2020) Analysis of buckling failure in continuously welded railway tracks. Eng Fail Anal 2021(119):104989. https://doi.org/10.1016/j.engfailanal.2020.104989
Man J, Dong H, Yang X, Meng Z, Jia L, Qin Y et al (2020) GCG: graph convolutional network and gated recurrent unit method for high-speed train axle temperature forecasting. Mech Syst Signal Process 2022(163):108102. https://doi.org/10.1016/j.ymssp.2021.108102
Darmo S, Bahiuddin I, Handoko P, Rizki Priatomo H, Kuncoro M, Priyambodo S et al (2021) Failure analysis of double-row tapered roller bearing outer ring used in Coal Wagon Wheelset. Eng Fail Anal 2022(135):106153. https://doi.org/10.1016/j.engfailanal.2022.106153
Dikmen F, Bayraktar M, Guclu R (2019) Determination of critical section of wagon axle by considering dynamic and safety factors. Alex Eng J 58(2):611–624. https://doi.org/10.1016/j.aej.2019.05.010
Corni I, Symonds N, Wasenczuk A, Vincent D (2018) On-board condition monitoring of rail axle bearings using vibration data. Int J Cond Monit 8(1):2–8. https://doi.org/10.1784/204764218822441988
Pintão B, Mosleh A, Vale C, Montenegro P, Costa P (2022) Development and validation of a weigh-in-motion methodology for railway tracks. Sensors 22(5):1976. https://doi.org/10.3390/s22051976
Silva R, Guedes A, Ribeiro D, Vale C, Meixedo A, Mosleh A et al (2023) Early identification of unbalanced freight traffic loads based on wayside monitoring and artificial intelligence. Sensors (Basel, Switz). https://doi.org/10.3390/s23031544
Rathod N, Wankhade S (2021) Review of optimization in improving extreme learning machine. EAI Endorsed Trans Ind Netw Intell Syst 8(28):1–13. https://doi.org/10.4108/EAI.17-9-2021.170960
Pan J, Li W, Dai X (2013) Train overload and unbalanced load detection based on FBG gauge. In: Fourth Asia Pacific optical sensors conference 2013, vol 8924, p 89242D. https://doi.org/10.1117/12.2031546
Ding Y, Cheng LR (2018) High speed overload and imbalance load system in China. In: 2018 Joint rail conference, JRC 2018, pp 1–6. https://doi.org/10.1115/JRC2018-6223
Mohammadi M, Mosleh A, Vale C, Ribeiro D, Montenegro P, Meixedo A (2023) An unsupervised learning approach for wayside train wheel flat detection. Sensors. https://doi.org/10.3390/s23041910
Su J, Wang X, Chen R, Xu G, Tian Z (2012) Design and research on monitoring system of overload and unbalanced load of freight cars. In: World automation congress proceedings 2012, vol 1(c), pp 1–4
Chang Q, Han M (2011) Study on a combined method of Butterworth high-pass filter and Canny edge detector in the application of detecting cargo loading position on railway vehicles. In: Proceedings of 2011 international conference on computer science and network technology, ICCSNT 2011, vol 3, pp 1959–1963. https://doi.org/10.1109/ICCSNT.2011.6182355
Tripathi K, Khan FA, Khanday AMUD, Nisa KUL (2023) The classification of medical and botanical data through majority voting using artificial neural network. Int J Inf Technol. https://doi.org/10.1007/s41870-023-01361-0
Nidhi N, Lobiyal DK (2022) Traffic flow prediction using support vector regression. Int J Inf Technol 14(2):619–626. https://doi.org/10.1007/s41870-021-00852-2
Pandey P, Bandhu KC (2022) A credit risk assessment on borrowers classification using optimized decision tree and KNN with bayesian optimization. Int J Inf Technol 14(7):3679–3689. https://doi.org/10.1007/s41870-022-00974-1
El Bourakadi D, Ramadan H, Yahyaouy A, Boumhidi J (2023) A novel solar power prediction model based on stacked BiLSTM deep learning and improved extreme learning machine. Int J Inf Technol (Singap) 15(2):587–594. https://doi.org/10.1007/s41870-022-01118-1
Kumar A, Kumar R (2021) A novel approach for ISL alphabet recognition using Extreme Learning Machine. Int J Inf Technol (Singap) 13(1):349–357. https://doi.org/10.1007/s41870-020-00525-6
Kale AP, Sonavane SP (2018) IoT based Smart Farming: feature subset selection for optimized high-dimensional data using improved GA based approach for ELM. Comput Electron Agric 2018(161):225–232. https://doi.org/10.1016/j.compag.2018.04.027
Nikulin SA, Oguenko VN, Rozhnov AB, Turilina VY, Nechaikina TA, Rogachev SO (2016) Strength of freight bogie solebar fragments after volume–surface quenching. Russ Metall (Metally) 2016(10):986–991. https://doi.org/10.1134/S0036029516100153
Hemmati-Sarapardeh A, Varamesh A, Husein MM, Karan K (2017) On the evaluation of the viscosity of nanofluid systems: modeling and data assessment. Renew Sustain Energy Rev 2018(81):313–329. https://doi.org/10.1016/j.rser.2017.07.049
Aminian A, ZareNezhad B (2018) Accurate predicting the viscosity of biodiesels and blends using soft computing models. Renew Energy 120:488–500. https://doi.org/10.1016/j.renene.2017.12.038
Bahiuddin I, Imaduddin F, Mazlan SA, Shapiai MI, Ubaidillah, Nazmi N et al (2021) A machine learning approach to estimate magnetorheological suspension composition based on magnetic field dependent-rheological properties. Smart Mater Struct 30(10):105013. https://doi.org/10.1088/1361-665X/ac1d92
Huang G-B, Zhou H, Ding X, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern Part B (Cybern) 42(2):513–529. https://doi.org/10.1109/TSMCB.2011.2168604
Bahiuddin I, Mazlan SA, Shapiai MI, Imaduddin F, Ubaidillah (2017) Study of extreme learning machine activation functions for magnetorheological fluid modelling in medical devices application. In: 2017 international conference on robotics, automation and sciences (ICORAS), pp 1–5. https://doi.org/10.1109/ICORAS.2017.8308053
Bahiuddin I, Mazlan SA, Shapiai MI, Choi SB, Imaduddin F, Rahman MAA et al (2018) A new constitutive model of a magneto-rheological fluid actuator using an extreme learning machine method. Sens Actuators A 281:209–221. https://doi.org/10.1016/j.sna.2018.09.010
Karimipour A, Ghasemi S, Darvanjooghi MHK, Abdollahi A (2018) A new correlation for estimating the thermal conductivity and dynamic viscosity of CuO/liquid paraffin nanofluid using neural network method. Int Commun Heat Mass Transf 92(March):90–99. https://doi.org/10.1016/j.icheatmasstransfer.2018.02.002
Acknowledgements
This work is funded by Direktorat Jenderal Pendidikan Vokasi, Ministry of Education, Culture, Research, and Technology, Indonesia, through the P2V program with contract number 15/D4/RA.02.02/2022 and 059/SPK/D4/PPK.01.APTV/VI/2022.
Author information
Authors and Affiliations
Contributions
Writing—original draft, IA, RIDS, IB; supervision, IB; review and revision, AW, SAM, IB; methodology, IA, SD, IB; software, IA, IB; data curation, AW, HRP. All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Anagra, I., Bahiuddin, I., Priatomo, H.R. et al. Detection of coal wagon load distributions based on geometrical features using extreme learning machine methods. Int. j. inf. tecnol. 16, 939–947 (2024). https://doi.org/10.1007/s41870-023-01499-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41870-023-01499-x