Research on fuzzy clustering method for working status of mineral flotation process. (15th March 2021)

• Record Type: Journal Article
• Authors: Wu, Yanpeng; Peng, Xiaoqi; Mohammad, Nur; Yang, Hengfu
• Is Part Of: International journal of embedded systems. Volume 14:Number 2(2021)
• Page Start: 133
• Page End: 142
• Publication Date: 2021-03-15
• Subjects: fuzzy C-means -- FCM -- fuzzy clustering -- dosing records -- visual characteristic -- mineral flotation; Embedded computer systems -- Periodicals; 004.16
• Languages: English
• ISSNs: 1741-1068

Abstract

A fuzzy clustering method based on FCM algorithm for working status of mineral flotation process is proposed to help workers control mineral flotation process better. The working status of mineral floatation process can be determined by judging dosing records, in terms of copper sulphate, lead nitrate, xanthate, 2# oil, black medicine, etc., or observing the visual features of foam layer including the average grayscale, R-means, G-means, B-means, the average bubble size, the skewness of bubble size, the standard deviation of bubble size and bubble stability. Nearly 6, 000 continuous dosing data were collected from an automatic dosing system installed in a gold mine flotation workshop and normalised to range of [0, 1]. Those dosing data were first pre-classified into steady condition and unsteady condition according to the degree of change in neighbouring data and then clustered respectively. 96 categories of steady condition and 24 categories of unsteady condition were obtained by an FCM program using Euclidean distance. Similarity coefficient analysis on mean, standard deviation, and variation coefficient indicate that the dosing clusters in steady condition are more trustworthy to dosing operators than those in unsteady condition. Meanwhile, FCM algorithm is suitable for dosing data clustering with high consistency.