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

An aluminum electrolysis superheat degree identification method based on a semi-supervised extreme learning machine

A technology of extreme learning machine and recognition method, which is applied in the field of aluminum electrolytic superheat recognition based on semi-supervised extreme learning machine, can solve the problems of fast training speed and weak inference power, and achieve the effect of fast training speed and overcoming weak inference power

Active Publication Date: 2019-04-09
CENT SOUTH UNIV
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] The purpose of the present invention is to overcome the defects in the prior art and provide a method for identifying the superheat of aluminum electrolysis based on a semi-supervised extreme learning machine, which can fully explore the hidden information in unlabeled data and overcome the traditional Laplacian regularization The problem of weak inference power, and the training speed is faster than traditional methods, which can realize accurate real-time monitoring of the superheat state of industrial systems

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 superheat degree identification method based on a semi-supervised extreme learning machine
  • An aluminum electrolysis superheat degree identification method based on a semi-supervised extreme learning machine
  • An aluminum electrolysis superheat degree identification method based on a semi-supervised extreme learning machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] Such as figure 1 As shown, the present invention provides a kind of aluminum electrolysis superheat identification method based on semi-supervised extreme learning machine, and described method comprises:

[0065] S1. Collect real-time production data of aluminum electrolysis, and normalize and standardize the collected data;

[0066] S2. Construct a Hessian regularization operator;

[0067] S3, calculating the hidden layer output of the extreme learning machine ELM model;

[0068] S4. Construct the loss function of the ELM model, and solve the output weight matrix.

[0069] The method of the present invention is described in further detail below.

[0070] 1. Extreme Learning Machine

[0071] Extreme learning machine is a training algorithm to effectively determine the parameters of single hidden layer feedforward neural network. When performing hierarchical extreme learning machine training, it is assumed that there are input variables X∈R N×m and the output vari...

Embodiment 2

[0120] Efficient aluminum electrolysis process has always been a challenging industrial problem. However, due to various external conditions and complex physical and chemical reactions and interferences of manual operations, the aluminum electrolysis process often works in many different working conditions, which increases the difficulty of monitoring the aluminum electrolysis process. In the process of aluminum electrolysis, the degree of superheat is mainly identified by manual observation of the electrolyte, fire eyes, etc. The online identification method of the superheat of the electrolytic cell has not yet been solved. Therefore, 12 process variables are selected for soft sensor modeling. The data set comes from the real-time production data of two 400KA electrolytic cells of Shandong Weiqiao Aluminum Co., Ltd., and 1200 daily data samples of each of the two electrolytic cells are selected as training data, of which 500 are labeled data for training models, and the other ...

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 identification method based on a semi-supervised extreme learning machine, and the method comprises the steps: collecting aluminum electrolysis real-time production data, and carrying out the normalization processing and standardization processing of the collected data; Constructing a Hessian regularization operator; Calculating hidden layer output of the extreme learning machine ELM model; And constructing a loss function of the ELM model, and solving an output weight matrix. According to the method, hidden information in the label-free data can be fully explored, the problem of weak inference force of traditional Laplacian regularization is solved, the training speed is higher than that of a traditional method, and the superheat state of an industrial system can be accurately monitored in real time.

Description

technical field [0001] The invention relates to the field of industrial control, in particular to a method for identifying superheat of aluminum electrolysis based on a semi-supervised extreme learning machine. Background technique [0002] In modern industry, how to ensure production safety and improve product quality has important research value, and it is against this background that process monitoring technology emerges. For the process industry, accurate mathematical mechanism models and complete expert knowledge are often difficult to obtain, resulting in difficulties in online detection and high costs. [0003] Process monitoring methods based on mathematical models and knowledge are usually difficult to apply in practice. With the widespread use of distributed control systems (DCS) and various intelligent instruments in the process industry, a large amount of process data is collected and stored. Therefore, The data-driven process monitoring method has been greatly ...

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): G06K9/62
CPCG06F18/2155
Inventor 陈晓方雷勇祥谢永芳岳伟超杨焕万晓雪
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