Manufacturing & Industrial Engineering Faculty Publications and Presentations

Intelligent real-time flotation froth stability monitoring using embedded computer vision: lead (Pb) processing case study

Document Type

Article

Publication Date

11-2025

Abstract

Froth stability in flotation refers to the ability of the froth layer to remain intact and avoid collapsing during the flotation process. A stable froth layer is crucial to maximizing mineral recovery and ensuring the efficient operation of flotation cells. Several factors influence the stability of the froth, including the depth of the froth, the crowding, the size of the bubbles, and the rate of movement of the froth. In this study, our main objective is to analyze and evaluate froth stability in real time, since it plays a critical role in process optimization for flotation-based mineral processing. We propose and validate a novel approach to stability monitoring based on a deep understanding of the dynamic behavior of bubbles, including their size, count, and spatial distribution. These features are analyzed to define a robust collapse rate measurement using real-time computer vision techniques. This study differentiates itself from previous state-of-the-art approaches by validating the proposed froth stability monitoring framework directly in an industrial Pb flotation plant. Unlike previous works that relied mainly on offline or laboratory setups, our system demonstrates an embedded real-time implementation on edge devices, enabling practical deployment at the plant level. The framework is developed and validated using real industrial data from a differential Lead flotation circuit. Performance is assessed on the basis of precision and execution time. Our findings indicate the strong potential of the froth stability monitoring framework, which achieved more than 97.06% cosine similarity in real-time execution within 3.65 s. This offers significant added value for process optimization in flotation-based mineral processing.

Comments

Reprints and permissions

https://rdcu.be/eVw9r

DOI

10.1007/s00170-025-16740-z

Link to Full Text

Share

COinS