Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

An aluminum electrolysis cell superheat degree state recognition method and system based on a 3D convolutional neural network

A convolutional neural network and state recognition technology, applied in the field of aluminum electrolysis, to achieve the effect of improving accuracy, improving production efficiency, and improving comprehensiveness

Inactive Publication Date: 2019-04-30
CENT SOUTH UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the shortcomings of the existing method for identifying the superheat state of aluminum electrolytic cells, and proposes a method and system for identifying the superheat state of aluminum electrolytic cells based on a 3D convolutional neural network. The method and system include a video acquisition module, A data processing module and a superheat state identification module, the data processing module includes a sample data processing module and an online data processing module, and the superheat state identification module includes an offline learning module and an online prediction module

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
  • An aluminum electrolysis cell superheat degree state recognition method and system based on a 3D convolutional neural network
  • An aluminum electrolysis cell superheat degree state recognition method and system based on a 3D convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The specific implementation of the present invention will be described below in conjunction with the accompanying drawings, and the superheat state of the aluminum electrolytic cell is divided into three categories: large, normal, and small according to the actual operating conditions.

[0032] 1. Video capture module

[0033] From an aluminum electrolysis factory, a hand-held industrial camera was used to shoot 22 videos of different superheating states. The size of each frame of the video is 1920*1080, and the average duration of each group of videos is 80s, and then the collected videos are saved to the image acquisition stuck.

[0034] 2. Data processing module

[0035] Read the collected video data from the image acquisition card, decompose the read video data into multiple frames of RGB images, select the red channel in each frame of RGB images, and perform threshold segmentation on the red channel. The threshold value is 230, and after segmentation The binarize...

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

The invention aims to overcome the defects of an existing aluminum electrolysis cell superheat degree state recognition method. The invention provides an aluminum electrolysis cell superheat degree state recognition method and system based on a 3D convolutional neural network. The system comprises a video acquisition module, a data processing module and a superheat degree state recognition module,the data processing module comprises a sample data processing module and an online data processing module, and the superheat degree state recognition module comprises an offline learning module and an online prediction module. According to the aluminum electrolysis cell superheat degree state recognition method based on the 3D convolutional neural network, the applicability of the aluminum electrolysis cell superheat degree state recognition method is ensured, and meanwhile the superheat degree recognition accuracy is improved.

Description

technical field [0001] The invention relates to a method and system for identifying the superheat state of an aluminum electrolytic cell based on a 3D convolutional neural network, which can be applied to the identification of the superheat state in the production process of aluminum electrolysis, and belongs to the technical field of aluminum electrolysis. Background technique [0002] After decades of development, the aluminum electrolysis industry has gradually become an important basic industry in my country. However, due to the high power consumption in the production process, it has become one of the key industries regulated by the state. The degree of superheat (the difference between the electrolyte temperature and the primary crystal temperature) can well reflect the state of the aluminum electrolytic cell. Specifically, when the degree of superheat is high, the current efficiency is low, otherwise the current efficiency is high. Therefore, many experts have studied ...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V20/41G06F18/214
Inventor 赵士伟谢永芳陈晓方
Owner CENT SOUTH UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com