Prediction of the Composite Required in the Design of a Toroidal Vessel Using an Artificial Neural Network
DOI:
https://doi.org/10.53591/iti.v13i13.1093Keywords:
Toroidal Vessel, Optimization, Machine Learning, Artificial Neural NetworkAbstract
Context: Within the design of toroidal vessels, minimizing the amount of material is very important for reducing production costs; Conventional methods used to minimize the amount of material are computationally time consuming each time a new container is tested. New techniques based on artificial intelligence require the prediction of the minimum amount of material required for the design of a container in the shortest possible time. Method: The prediction methodology is based on a linear regression model through an artificial neural network, which is implemented with the Keras model of Python; In its first phase, a data set created by a script with ANSYS APDL code is handled. Results: An artificial neural network model that learned to predict the minimum amount of material, adequate accuracy and loss of the model. Conclusions: A better performance of the model was obtained, the partition of the dataset into training and testing data, a level of precision was obtained that ensures the reliability of the machine learning model compared to the traditional ones.
References
Agasi, O., Anderson, J., Cole, A., Berthold, M., Cox, M., & Dimov, D. (2018). What is an Artificial Neural Network (ANN)? - Definition from Techopedia. Techopedia.
Barbero, E. J., & Cosso, F. A. (2014). Determination of material parameters for discrete damage mechanics analysis of carbon-epoxy laminates. Composites Part B: Engineering, 56. https://doi.org/10.1016/j.compositesb.2013.08.084
Barbero, E. J., & Shahbazi, M. (2017). Determination of material properties for ANSYS progressive damage analysis of laminated composites. Composite Structures, 176, 768–779. Retrieved from https://doi.org/10.1016/j.compstruct.2017.05.074
Brownlee, J. (2016). Supervised and Unsupervised Machine Learning Algorithms. Understand Machine Learning Algorithms.
Brownlee, J. (2017). How to Use the Keras Functional API for Deep Learning. Machinelearningmastery., (1).
Chapman, A., Simperl, E., Koesten, L., Konstantinidis, G., Ibáñez, L. D., Kacprzak, E., & Groth, P. (2020). Dataset search: a survey. VLDB Journal, 29(1). https://doi.org/10.1007/s00778-019-00564-x
DeLay, T., & Roberts, K. (2003, November 1). Toroidal Tank Development for Upper-stages. Retrieved February 8, 2016, from http://ntrs.nasa.gov/search.jsp?R=20040084002
Karlijn Willems. (2019). (Tutorial) KERAS Tutorial: DEEP LEARNING in PYTHON - DataCamp.
Mathur, P. (2019). Machine Learning Applications Using Python. In Machine Learning Applications Using Python. https://doi.org/10.1007/978-1-4842-3787-8
Moore, M., Saxon, M., Venkateswara, H., Berisha, V., & Panchanathan, S. (2019). Say what? A dataset for exploring the error patterns that two ASR engines make. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2019-Septe. https://doi.org/10.21437/Interspeech.2019-3096
Patiño-Pérez, D., & Corz-Rodríguez, A. (2019). Optimum design of a toroidal pressure vessel of composite material for gas (CNG) powered vehicles. Dyna (Spain), 94(5), 546–553. https://doi.org/10.6036/9096
Patiño, D., & Corz, A. (2018). Comparative Analysis of Toroidal Pressure Vessels of Composite by Finite Elements. International Journal of Innovation and Applied Studies(IJIAS), 25(1), 162–175. Retrieved from http://www.ijias.issr-journals.org/abstract.php?article=IJIAS-18-229-30
Patiño Pérez, D., Corz Rodriguez, A., & Mora, C. M. (2020). Diseño Optimo de un Recipiente a Presión Toroidal de Espesor Variable para Almacenar Hidrogeno en Automóviles Optimal Design of a Toroidal Pressure Vessel of Variable Thickness for Storing Hydrogen in Cars. ECUADORIAN SCIENCE JOURNAL, 4(2), 94–100. https://doi.org/10.46480/esj.4.2.107
Pedrycz, W., Sillitti, A., & Succi, G. (2016). Computational intelligence: An introduction. In Studies in Computational Intelligence. https://doi.org/10.1007/978-3-319-25964-2_2
Vick, M. J., & Gramoll, K. (2012). Finite Element Study on the Optimization of an Orthotropic Composite Toroidal Shell. Journal of Pressure Vessel Technology, 134(5), 1–7. https://doi.org/10.1115/1.4005873
Yegnanarayana, B. (1994). Artificial neural networks for pattern recognition. Sadhana, 19(2). https://doi.org/10.1007/BF02811896
Zou, D., Cao, Y., Zhou, D., & Gu, Q. (2020). Gradient descent optimizes over-parameterized deep ReLU networks. Machine Learning, 109(3). https://doi.org/10.1007/s10994-019-05839-6
Downloads
Published
Issue
Section
License
Copyright (c) 2021 Darwin Patiño Pérez, Miguel Botto-Tobar, Celia Munive Mora
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
