A Soft Sensing Method for Zinc Ore Grade Based on Process Size Features

A dimensional feature, soft measurement technology, applied in the direction of instrument, calculation, character and pattern recognition, etc., can solve the problems of difficulty, high cost and large delay in online detection of concentrate grade.

Active Publication Date: 2021-11-23
CENT SOUTH UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the difficulty of online detection of concentrate grade in the process of zinc flotation, high cost, large delay and insufficient prediction of zinc flotation concentrate grade, this invention proposes a lead-zinc A construction method for the process characteristics of the flotation foam image, and a prediction method for the concentrate grade, which has good prediction accuracy, anti-interference ability and fast operation speed

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Soft Sensing Method for Zinc Ore Grade Based on Process Size Features
  • A Soft Sensing Method for Zinc Ore Grade Based on Process Size Features
  • A Soft Sensing Method for Zinc Ore Grade Based on Process Size Features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The following is a more detailed and clear description and explanation of the technical solution adopted in the present invention in conjunction with the accompanying drawings of the present invention. Aiming at the limitation that the traditional method cannot accurately reflect the foam state only by relying on a single frame picture, the invention proposes a time-related process size feature extraction method, and realizes the online detection of zinc concentrate grade by using an improved lifting decision tree model. Apparently, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the relevant art without making creative efforts shall fall within the protection scope of the present invention.

[0034] Such as figure 1As shown, it is a flow chart of a soft-sensing method for lead-zinc ore grade based ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

A method of soft measurement of zinc flotation concentrate grade based on process characteristics. This invention combines expert knowledge and data modeling methods. First, the bubble size distribution in the image is used to characterize the foam according to the observation focus of the on-site workers when watching the bubbles. Image, according to the characteristics that on-site workers need to observe the foam state for a period of time to judge the current production state, it is proposed to use the size distribution sequence to mathematicize the current production state, and a modeling method for the foam size sequence is proposed, which reduces the dimension of the feature vector number. In the prediction algorithm, a large amount of accumulated data is used to adopt the improved lifting decision tree algorithm, which can effectively suppress the over-fitting problem caused by too fast learning and improve the generalization ability. Experiments have proved that the method of the invention is simple in calculation, fast in execution speed, high in prediction accuracy, convenient for on-site actual operation, can guide on-site operation in real time, optimize the production process, and solve the problem of difficulty in online detection of existing zinc ore grades.

Description

technical field [0001] The invention belongs to the technical field of froth flotation, and in particular relates to a method for predicting the grade of zinc flotation concentrate. Background technique [0002] Foam flotation is one of the most important beneficiation methods in zinc smelting today. Flotation is a method of sorting according to the difference in physical and chemical properties of the surface of mineral particles and according to the difference in mineral floatability. The separation process of useful minerals and their symbiotic gangues, through continuous stirring and blowing during the flotation process, a large number of air bubbles with different sizes, shapes, textures and other characteristics are formed in the slurry, and the air bubbles carry mineral particles up to the floating A foam layer is formed on the surface of the groove to realize the separation of minerals and gangue. For such a complex industrial process as froth flotation, due to the ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62
CPCG06F18/213G06F18/24323
Inventor 唐朝晖牛亚辉曾思迪史伟东高小亮
Owner CENT SOUTH UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products