A digital twin dosing system for iron reverse flotation. (April 2022)

• Record Type: Journal Article
• Authors: Zhang, Dingsen; Gao, Xianwen
• Is Part Of: Journal of manufacturing systems. Volume 63(2022)
• Page Start: 238
• Page End: 249
• Publication Date: 2022-04
• Subjects: Digital twin -- Dosage of reagent -- Iron reverse flotation -- Soft sensor; Manufacturing processes -- Periodicals; Production engineering -- Data processing -- Periodicals; Robots, Industrial -- Periodicals; Production, Technique de la -- Informatique -- Périodiques; Robots industriels -- Périodiques; Electronic journals; 670.42
• DOI: 10.1016/j.jmsy.2022.03.006
• Languages: English
• ISSNs: 0278-6125

Abstract

Abstract: Flotation is an essential process in beneficiation production. The amount of flotation reagent has a significant influence on the quality of the product. An inappropriate dosing system will lead to metal loss and reagent waste, especially when the nature of the raw ore changes frequently. If the dosing system is not updated in time, it will cause economic losses. Based on digital twin technology and machine learning algorithms, this research designed a digital twin system for iron reverse flotation reagents. Based on the flotation froth image and transformer algorithm, a soft sensor model of tailings grade is established to monitor the product quality in real-time. The flotation dosing model established based on the ELM algorithm automatically updates the reagent system and intelligently assigns the controller. On the basis of stabilizing product quality, this research avoids the waste of reagents and improves the economic benefits of production efficiency. The system was applied in an iron flotation plant, and industrial operation effect verified the method. Highlights: An iron reverse flotation digital twin dosing system was developed. A production digital twin framework was established. A soft sensor model of tailings grade was established based on froth image and ViT. An automatic update dosing system was developed based on ELM. A human-computer interaction interface was designed for the digital twin system.