Intelligent Setting Method of Reagent Dosage Based on Time Series Froth Image in Zinc Flotation Process

被引：9

作者：

Tang, Zhaohui ^{[1
]}

Tang, Liyong ^{[1
]}

Zhang, Guoyong ^{[1
]}

Xie, Yongfang ^{[1
]}

Liu, Jinping ^{[2
]}

机构：

[1] Cent South Univ, Sch Automat, Changsha 410083, Peoples R China

[2] Hunan Normal Univ, Sch Informat Sci & Engn, Changsha 410081, Peoples R China

来源：

PROCESSES | 2020年 / 8卷 / 05期

基金：

中国国家自然科学基金;

关键词：

flotation process; reagent dosage; time series froth image; cumulative distribution function; BUBBLE-SIZE;

D O I：

10.3390/pr8050536

中图分类号：

TQ [化学工业];

学科分类号：

0817 ;

摘要：

It is well known that the change of the reagent dosage during the flotation process will cause the froth image to change continuously with time. Therefore, an intelligent setting method based on the time series froth image in the zinc flotation process is proposed. Firstly, the sigmoid kernel function is used to estimate the cumulative distribution function of bubble size, and the cumulative distribution function shape is characterized by sigmoid kernel function parameters. Since the reagent will affect the froth image over a period of time, the time series of bubble size cumulative distribution function is processed by the ELMo model and the dynamic feature vectors are output. Finally, XGBoost is used to establish the nonlinear relationship modeling between reagent dosage and dynamic feature vectors. Industrial experiments have proved the effectiveness of the proposed method.

引用

页数：14

共 27 条

[11] Soft computing-based modeling of flotation processes - A review [J].

Jovanovic, Ivana ;

Miljanovic, Igor ;

Jovanovic, Tomislav .

MINERALS ENGINEERING, 2015, 84 :34-63

[12]

Li HB, 2012, P AMER CONTR CONF, P4891

[13] The Method of Reagent Control Based on Time Series Distribution of Bubble Size in a Gold-Antimony Flotation Process [J].

Li, Zhongmei ;

Gui, Weihua .

ASIAN JOURNAL OF CONTROL, 2018, 20 (06) :2223-2236

[14] Illumination-Invariant Flotation Froth Color Measuring via Wasserstein Distance-Based CycleGAN With Structure-Preserving Constraint [J].

Liu, Jinping ;

He, Jiezhou ;

Xie, Yongfang ;

Gui, Weihua ;

Tang, Zhaohui ;

Ma, Tianyu ;

He, Junbin ;

Niyoyita, Jean Paul .

IEEE TRANSACTIONS ON CYBERNETICS, 2021, 51 (02) :839-852

[15] TCvBsISM: Texture Classification via B-Splines-Based Image Statistical Modeling [J].

Liu, Jinping ;

He, Jiezhou ;

Zhang, Wuxia ;

Xu, Pengfei ;

Tang, Zhaohui .

IEEE ACCESS, 2018, 6 :44876-44893

[16] Impact of Power Grid Strength and PLL Parameters on Stability of Grid-Connected DFIG Wind Farm [J].

Liu, Ju ;

Yao, Wei ;

Wen, Jinyu ;

Fang, Jiakun ;

Jiang, Lin ;

He, Haibo ;

Cheng, Shijie .

IEEE TRANSACTIONS ON SUSTAINABLE ENERGY, 2020, 11 (01) :545-557

[17] Energy-Efficient Train Driving Strategy with Considering the Steep Downhill Segment [J].

Liu, Wentao ;

Tang, Tao ;

Su, Shuai ;

Yin, Jiateng ;

Cao, Yuan ;

Wang, Cheng .

PROCESSES, 2019, 7 (02)

[18]

Peters M. E., 2018, P 2018 C N AM CHAPT, V1, P2227, DOI [10.18653/V1/N18-1202, DOI 10.18653/V1/N18-1202]

[19] Real-time monitoring of entrainment using fundamental models and froth images [J].

Popli, Khushaal ;

Afacan, Artin ;

Liu, Qi ;

Prasad, Vinay .

MINERALS ENGINEERING, 2018, 124 :44-62

[20] Predictive control of the bubble size distribution in a two-phase pilot flotation column [J].

Riquelme, A. ;

Desbiens, A. ;

del Villar, R. ;

Maldonado, M. .

MINERALS ENGINEERING, 2016, 89 :71-76

← 1 2 3 →