Method and system for precise coordination of crust breaking position recognition and blanking cylinder of aluminum electrolysis cell based on machine vision

By integrating machine vision and infrared temperature measurement to construct a real-time 3D model of the aluminum electrolysis cell, the problems of shell-breaking position recognition and material feeding cylinder coordination were solved, achieving precise shell-breaking and material feeding coordination, improving production efficiency and reducing energy consumption.

CN121962534BActive Publication Date: 2026-06-19HUNAN ALHUIT TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HUNAN ALHUIT TECH CO LTD
Filing Date
2026-04-03
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

In existing technologies, the positioning accuracy of the shell-forming position in aluminum electrolytic cells is insufficient, and it cannot adapt to the dynamic and irregular changes in the shell formation. This leads to frequent occurrences of off-center drilling, empty drilling, and missed drilling. The shell-forming and material feeding actions lack real-time coordination, resulting in low material feeding accuracy. Furthermore, it is impossible to optimize and adapt to the real-time status of the aluminum electrolytic cell online, causing raw material waste and production anomalies.

Method used

By employing multi-sensor information fusion based on machine vision and infrared temperature measurement, a real-time 3D model of the aluminum electrolysis cell is constructed. Through point cloud stitching algorithm and binocular vision ranging, the shell-breaking position is accurately identified. Combined with the historical records of the feeding cylinder, the shell-breaking and feeding parameters are dynamically adjusted to achieve precise coordination between shell-breaking and feeding.

Benefits of technology

It achieves millimeter-level precise identification of the shell-breaking position, improves the accuracy of material delivery, reduces the occurrence rate of anode effect, and is suitable for harsh working conditions such as high temperature, strong magnetic field and high dust, which significantly improves the production efficiency of electrolytic aluminum and reduces energy consumption.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121962534B_ABST
    Figure CN121962534B_ABST
Patent Text Reader

Abstract

This invention provides a machine vision-based method and system for precise coordination of shell-breaking position recognition and material feeding cylinder in aluminum electrolytic cells. Belonging to the field of machine vision technology, the method includes: acquiring visual images and infrared temperature data of the aluminum electrolytic cell through dual-point complementary acquisition, fusing them to construct a real-time 3D model and accurately determining the shell-breaking scheme; calculating the shell-breaking time using binocular vision ranging, generating an initial material feeding scheme based on historical material feeding data, and then dynamically correcting the material feeding parameters based on the real-time material feeding hole contour fitting results, achieving precise closed-loop coordination between shell-breaking and material feeding. This achieves millimeter-level positioning of the shell-breaking position, improves material feeding accuracy, reduces the occurrence of anode effects and production energy consumption, and is suitable for the harsh working conditions of aluminum electrolytic cells with high temperature, strong magnetism, and high dust, significantly improving the efficiency and intelligence level of electrolytic aluminum production.
Need to check novelty before this filing date? Find Prior Art