Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method for recognizing slag variety by combining with laser-induced breakdown spectroscopy based on least squares support vector machine

A laser-induced breakdown and support vector machine technology, applied in the field of spectral analysis, can solve problems such as time-consuming, limited real-time rapid analysis, and inability to quickly obtain steel product quality information, so as to overcome interference, improve prediction accuracy, and tolerate degree of effect

Inactive Publication Date: 2015-06-10
NORTHWEST UNIV
View PDF2 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the conventional methods for slag analysis include chemical analysis, atomic fluorescence spectrometry (XRF), atomic emission spectrometry (AES), inductively coupled plasma-optical emission spectrometry (ICP-OES) and mass spectrometry (MS). Complicated sample pretreatment and time-consuming, unable to quickly obtain steel product quality information, limiting its application in real-time rapid analysis

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
  • Method for recognizing slag variety by combining with laser-induced breakdown spectroscopy based on least squares support vector machine
  • Method for recognizing slag variety by combining with laser-induced breakdown spectroscopy based on least squares support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0020] The LIBS system used in this example includes a dual-wavelength Q-switched single-pulse Nd:YAG laser, an optical system, an adjustable three-dimensional sample stage, an echelle spectrometer (ARYELLE-UV-VIS, LTB400, German) and a computer. The laser energy is 80mJ, the fundamental frequency light wavelength is 1064 nm, the pulse width is 10 ns, the delay time is 1.5 μs, the repetition frequency is 5 Hz, and the spectral range is 220nm-800nm.

[0021] Three kinds of slags (blast furnace slag, converter slag, and flat furnace slag) were selected, and a total of 30 slag samples were used. For the convenience of testing, each slag sample was ground to 200 mesh with a ball mill, and then each sample was pressed into a thin sheet about 2mm thick, with a pressure of 400MPa and last for 5min.

[0022] The LIBS signals of different slag samples were collected by laser-induced breakdown spectroscopy. Randomly select 50 measurement points for each slag sample, obtain a measuremen...

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 provides a method for recognizing slag variety by combining with a laser-induced breakdown spectroscopy (LIBS) analysis technology based on a least squares support vector machine. The method comprises the following steps: optimizing the least squares support vector machine parameter (radical basis kernel function-gamma and rho2) by adopting grid global optimization and half-off cross validation; building a least squares support vector machine classification model; and realizing reorganization of the slag variety by combining the classification model with the LIBS technology. A research shows that a least squares support vector machine modeling approach has a good prediction effect; a novel modeling method is provided for mode recognition of the LIBS technology; and the method can be applied to recognition, recovery and reutilization of metallurgical waste materials.

Description

technical field [0001] The invention relates to a method for identifying slag types based on a least square support vector machine combined with a laser-induced breakdown spectrum, and belongs to the technical field of spectral analysis. Background technique [0002] In the steelmaking industry, a large number of by-products exist in the form of slag and deposits. The slag produced by the world slag industry amounts to almost 50 million tons per year. As an important by-product of the slag industry, slag plays a decisive role in ensuring the smooth progress of steelmaking operations, steel quality and metal recovery. Different types of steelmaking furnaces produce different slags. Each type of slag has its own unique chemical, mineral and physical properties, however its main components include calcium oxide, silicon dioxide, aluminum oxide, magnesium oxide, iron oxide, etc. Sorting of slag facilitates recycling and reuse of metallurgical waste. The reuse of slag is main...

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): G01N21/63
Inventor 李华张天龙汤宏胜
Owner NORTHWEST 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
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