Froth Stereo Visual Feature Extraction for the Industrial Flotation Process

Abstract

Froth visual features are closely related to flotation performance, and accurate extraction of froth visual features through machine vision allows improved control and optimization of the flotation process. However, the conventional froth features extracted from single two-dimensional (2D) images are inadequate to fully characterize froth features due to the loss of depth information. In this paper, we present a new method of stereo visual feature extraction on single 2D images for significantly improving froth characterization. First, a froth-specific reconstruction approach is proposed to derive 3D representation of froth through a model of defocus blur and illumination. Then, the froth stereo features are extracted based on the 3D representation. The new 3D reconstruction approach is validated by the effect of recovered 3D scenes under different conditions. Compared to the conventional methods, the froth stereo features have less fluctuation and improved stability. Finally, recognition of stereofeature based working conditions is investigated for the industrial flotation process. Our results show that the froth stereo features can adequately characterize the data with respect to their separability, regardless of the classifier used.

Development and tuning of algorithm for software identification of deviations in the potash flotation machine froth layer

“…Предварительно данные бликовой обработки видеопотока [11] фильтровались сглаживанием по нескольким (3,5,10,20) точкам. Использование методов неслепой фильтрации (наподобие фильтра Калмана [12,13]) в данном случае затруднительно, так как они работают в два этапа [14].…”

“…Интересно, что постоянные времени процесса при этом получаются различные (36,75 с и 5,52 с соответственно). Значение 36,75 с достаточно хорошо соответствует монографии [6] и статье [5].…”

“…Проблему можно было бы решить в том числе с применением компьютерного зрения. Существуют системы, успешно распознающие пузырьки в полиметаллических [3,4] или угольных [5][6][7] ФМ. Однако неконтрастная пена калийной ФМ может быть распознана только путем анализа бликов с поверхности пузырьков, формируемых точечным источником света [8].…”

Multiscale Convolutional Network for Repairing Coal Slime Foam Images

“…These factors include the addition of flotation reagents and the amount of aeration by observing the characteristic information of the foam surface. − However, owing to subjective bias, production environment changes, and other factors, the findings of manual judgment are frequently inaccurate, causing frequent fluctuations in flotation production indicators and low utilization of mineral resources . Consequently, using machine vision to capture the characteristic information of flotation foam, to monitor and identify the foam in the flotation process in real time, and to guide the adjustment of production factors, such as reagent dosage and liquid level, affecting flotation production increases the yield and economic benefits of the flotation concentrate in a coal washing plant. − …”