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

Aluminum electrolysis superheat degree recognition method based on CNN-LapsELM

A technology of aluminum electrolysis and superheating, applied in neural learning methods, character and pattern recognition, image data processing, etc., can solve the problems of human error, waste of manpower and material resources, etc.

Inactive Publication Date: 2020-01-10
CENT SOUTH UNIV
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the collected Huoyan images are unlabeled, and manually labeling all Huoyan images will not only cause a waste of manpower and material resources, but also cause human errors

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
  • Aluminum electrolysis superheat degree recognition method based on CNN-LapsELM
  • Aluminum electrolysis superheat degree recognition method based on CNN-LapsELM
  • Aluminum electrolysis superheat degree recognition method based on CNN-LapsELM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] 1. Dataset description and preprocessing

[0051] During the aluminum electrolysis industrial process, fire eye images are collected by operators using industrial camera equipment. Affected by the industrial environment and physical equipment, there are some noises and interferences in the collected fire eye images. Therefore, it is crucial to preprocess the Huoyan image. Here, the adaptive mean filtering algorithm is used to remove the noise points on the original fire eye image, so as to exclude the influence of noise on the classification of superheat state. In addition, because not all of the collected Huoyan images are Huoyan parts, in order to avoid other parts from interfering with the recognition results, improve the processing efficiency of Huoyan images, and reduce the memory burden of CNN when extracting features, it is necessary to preprocess the Huoyan images, from Extract the edge of the fire hole in the whole image.

[0052] The experiment uses 1200 im...

Embodiment 2

[0063] 1. Laplacian regularization:

[0064] Usually, the recognition accuracy of the model trained with a small number of labeled training sample sets does not meet the expected value. In order to solve the problem of few labeled training samples and improve the performance of the model, a semi-supervised learning method is proposed. Given a labeled data set and the unlabeled dataset Then the method based on Laplacian semi-supervised learning can fully extract the geometric information distribution contained in all available data. The semi-supervised learning method is based on the following two basic assumptions:

[0065] (1) All with label X l and unlabeled data X u are drawn from the same marginal distribution.

[0066] (2) If two sample points x 1 and x 2 , the distributions are very close to each other, then the corresponding conditional probability P(y|x 1 ) and P(y|x 2 ) should be very similar.

[0067] Using these two assumptions, the target regularization ...

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 discloses an aluminum electrolysis superheat degree recognition method based on CNN feature fusion and a semi-supervised Laplace extreme learning machine, and the method comprises the steps: 1, collecting aluminum electrolysis real-time production data, and carrying out the normalization and standardization of the collected data; 2, utilizing a convolutional neural network (CNN) to extract depth features of a fire eye image in the aluminum electrolysis industrial process; 3, fusing the depth features of the fire eye image extracted in the step 2 with other features of the fire eye image; and 4, constructing a semi-supervised extreme learning machine (LapsELM) as a classifier by using LapsELM regularization, and judging the current state of the superheat degree of the electrolytic cell according to the fire eye image.

Description

technical field [0001] The invention relates to the field of industrial control, in particular to an aluminum electrolytic superheat recognition method based on CNN feature fusion and a semi-supervised Laplacian extreme learning machine (CNN-LapsELM). Background technique [0002] In the process of aluminum electrolysis industry, the degree of superheat is one of the important indicators to evaluate the performance of the electrolytic cell, which can reflect the current working condition of the electrolytic cell. However, how to accurately measure superheat is an unsolved challenge. Traditional manual measurement methods are easily affected by many factors, such as manual reading errors, and the accuracy of measuring instruments. The aluminum electrolysis industrial site is an environment with high temperature, high humidity, and high concentration of corrosive gases. This harsh environment will also affect the accuracy of manual measurement and cause damage to measuring in...

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 Applications(China)
IPC IPC(8): G06T7/00G06K9/62G06N3/04G06N3/08
CPCG06T7/0004G06N3/08G06T2207/10004G06T2207/10024G06T2207/20081G06T2207/20084G06T2207/30136G06N3/048G06N3/045G06F18/241
Inventor 闵梦灿陈晓方雷永祥谢永芳
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