Edge Deep Learning Applied to Granulometric Analysis on Quasi-particles from the Hybrid Pelletized Sinter (HPS) Process

Natália Meira, Mateus Silva, Ricardo Oliveira, Aline Souza, Thiago D’Angelo, Cláudio Vieira

Abstract

The mining and metallurgical industry seeks to adapt to Industry 4.0 with the implementation of Artificial Intelligence in the processes. The purpose of this paper is to develop the first steps of an Artificial Intelligence in Deep Learning with Edge Computing to recognize the quasi-particles from the Hybrid Pelletized Sinter (HPS) process and provide its particle size distribution. We trained our model with the aXeleRate tool using the Keras-Tensorflow framework and the MobileNet architecture and tested it with an embedded system using the SiPEED MaiX Dock board. Our model obtained 98.60% accuracy in training validation using real and synthetic images and 100% accuracy in tests with synthetic images and 70% recall. The tests’ results indicate the feasibility of the proposed system, but with probable overfitting in the training stage.

Download


Paper Citation


in Harvard Style

Meira N., Silva M., Oliveira R., Souza A., D’Angelo T. and Vieira C. (2021). Edge Deep Learning Applied to Granulometric Analysis on Quasi-particles from the Hybrid Pelletized Sinter (HPS) Process. In Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-509-8, pages 527-535. DOI: 10.5220/0010458805270535


in Bibtex Style

@conference{iceis21,
author={Natália Meira and Mateus Silva and Ricardo Oliveira and Aline Souza and Thiago D’Angelo and Cláudio Vieira},
title={Edge Deep Learning Applied to Granulometric Analysis on Quasi-particles from the Hybrid Pelletized Sinter (HPS) Process},
booktitle={Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2021},
pages={527-535},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010458805270535},
isbn={978-989-758-509-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - Edge Deep Learning Applied to Granulometric Analysis on Quasi-particles from the Hybrid Pelletized Sinter (HPS) Process
SN - 978-989-758-509-8
AU - Meira N.
AU - Silva M.
AU - Oliveira R.
AU - Souza A.
AU - D’Angelo T.
AU - Vieira C.
PY - 2021
SP - 527
EP - 535
DO - 10.5220/0010458805270535