Detection of coal wagon load distributions based on geometrical features using extreme learning machine methods

Anagra, Ignatius and Bahiuddin, Irfan and Priatomo, Herjuno Rizki and Winarno, Agustinus and Darmo, Suryo and Sandhy, Rienetta Ichmawati Delia and Mazlan, Saiful Amri (2023) Detection of coal wagon load distributions based on geometrical features using extreme learning machine methods. International Journal of Information Technology (Singapore), 16 (2). pp. 939-947. ISSN 25112112

[thumbnail of Detection of coal wagon load.pdf] Text
Detection of coal wagon load.pdf
Restricted to Registered users only

Download (1MB)

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.

Item Type: Article
Uncontrolled Keywords: Coal wagon,Geometrical features,Load distribution,Machine learning,Train
Subjects: T Technology > TJ Mechanical engineering and machinery
Divisions: Faculty of Engineering > Mechanical and Industrial Engineering Department
Depositing User: Rita Yulianti Yulianti
Date Deposited: 16 Apr 2024 07:56
Last Modified: 16 Apr 2024 07:56
URI: https://ir.lib.ugm.ac.id/id/eprint/507

Actions (login required)

View Item
View Item