Hydrocyclone Operational Condition Detection: Conceptual Prototype with Edge AI

Tomás Silva, Tomás Silva, Ricardo Augusto Rabelo Oliveira, Emerson Klippel

2024

Abstract

Hydrocyclones, vital in mineral processing plants, classify materials by size and density. Operational issues, like roping, can cause inefficiencies and financial losses. This paper explores computer vision techniques for the assessment of hydrocyclone underflow operational status. Testing revealed robust performance for both a Resnet-18 and a MobileViT-V2 model. An edge device was implemented for real-time inferences on a conceptual prototype that simulates underflow scenarios. The CNN models demonstrate high precision and recall, with an F1 Score over 92% for roping detection on the edge device. The research contributes to efficient hydrocyclone monitoring, addressing challenges in remote mining locations. The findings offer potential for further optimization and industrial implementation, enhancing processing plant reliability and mitigating financial risks associated with operational irregularities.

Paper Citation

in Harvard Style

Silva T., Augusto Rabelo Oliveira R. and Klippel E. (2024). Hydrocyclone Operational Condition Detection: Conceptual Prototype with Edge AI. In Proceedings of the 26th International Conference on Enterprise Information Systems - Volume 1: ICEIS; ISBN 978-989-758-692-7, SciTePress, pages 865-872. DOI: 10.5220/0012728900003690

in Bibtex Style

@conference{iceis24,
author={Tomás Silva and Ricardo Augusto Rabelo Oliveira and Emerson Klippel},
title={Hydrocyclone Operational Condition Detection: Conceptual Prototype with Edge AI},
booktitle={Proceedings of the 26th International Conference on Enterprise Information Systems - Volume 1: ICEIS},
year={2024},
pages={865-872},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012728900003690},
isbn={978-989-758-692-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 26th International Conference on Enterprise Information Systems - Volume 1: ICEIS
TI - Hydrocyclone Operational Condition Detection: Conceptual Prototype with Edge AI
SN - 978-989-758-692-7
AU - Silva T.
AU - Augusto Rabelo Oliveira R.
AU - Klippel E.
PY - 2024
SP - 865
EP - 872
DO - 10.5220/0012728900003690
PB - SciTePress