A quantitative method for steel samples combined with laser-induced breakdown spectroscopy

A laser-induced breakdown and spectroscopy technology, applied in the field of spectral analysis, can solve the problems of difficulty in correctly judging different types of steel samples, unsuitable for on-site real-time analysis requirements, and differences in the components of the manufacturing process, so as to extend the linear range. , the effect of improving robustness test and reducing computational cost

Active Publication Date: 2020-09-18
段忆翔 +1
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is difficult to correctly judge different types of steel samples only by the naked eye, especially in steel companies, sales markets, and major port warehouses. This kind of place where a large number of steel gathers is prone to mislabeling and misjudgment of steel samples. Case
Moreover, for the same batch of national steel samples, the difference in the manufacturing process of different manufacturers will also lead to differences in their composition
The traditional steel sample quality inspection and analysis method takes a long time and is complicated to operate, which is not suitable for on-site real-time analysis requirements. Therefore, the emergence of LIBS analysis technology provides a solution to this dilemma

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
  • A quantitative method for steel samples combined with laser-induced breakdown spectroscopy
  • A quantitative method for steel samples combined with laser-induced breakdown spectroscopy
  • A quantitative method for steel samples combined with laser-induced breakdown spectroscopy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] A quantitative method for steel samples combined with laser-induced breakdown spectroscopy, through wavelet packet transform and an improved correlation vector machine kernel function quantitative analysis method combined with laser-induced breakdown spectroscopy to achieve rapid quantitative detection of steel samples, including the following steps :

[0050] 1) Collect spectral data to form two sets of data sets;

[0051] 2) Use the wavelet packet transform method to extract the features of the data set, convert the spectral peak intensity into wavelet energy for representation, and apply the wavelet packet energy as an input to the vector machine regression model;

[0052] 3) Establish a vector machine regression model, and perform modeling to predict the content.

Embodiment 2

[0054] The present embodiment is further optimized on the basis of the above-described embodiments, and further to better realize the present invention, the following setting mode is adopted in particular: the step 1) specifically includes the following steps:

[0055] 1.1) The laser-induced breakdown spectroscopy device is used to collect spectral data of steel samples of different steel grades at different measurement points;

[0056] 1.2) Randomly and evenly divide the collected spectral data into two groups, one group is used as a training set, and the other group is used as a test set; the selected training set data includes the maximum and minimum changes in the content of the entire steel sample, and the test set data Does not include the steel content involved in the training set.

Embodiment 3

[0058] This embodiment is further optimized on the basis of any of the above-mentioned embodiments. Further, in order to better realize the present invention, the following setting mode is adopted in particular: said step 2) includes the following specific steps:

[0059] 2.1) Perform data normalization preprocessing on the characteristic spectral lines of the training set and the characteristic spectral lines of the test set respectively with wavelet packet transform;

[0060] 2.2) The wavelet packet transform uses dB4 as the wavelet basis function, and performs three-layer decomposition on the characteristic spectral lines of the training set and the characteristic spectral lines of the test set;

[0061] 2.3) After step 2.2), the three-layer wavelet packet coefficients of the training set and the three-layer wavelet packet coefficients of the test set are respectively obtained; wherein the third layer includes 8 nodes, and each node represents a corresponding section of freq...

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 a method used for quantification of steel samples via combination with laser-induced breakdown spectroscopy. The method comprises following steps: 1, spectrum data is collectedso as to obtain two data sets; 2, the data sets are subjected to wavelet packet transformation, and spectrum peak intensity feature extraction so as to obtain wavelet packet energy, and the wavelet packet energy is adopted in a vector machine regression model as an input end; and 3, the vector machine regression model is established, and modeling prediction of content is carried out. According tothe method, wavelet packet transformation and an improved related vector machine kernel function quantitative analysis method are combined with laser-induced breakdown spectroscopy to realize rapid quantitative determination of steel samples.

Description

technical field [0001] The present invention relates to the field of spectral analysis technology and other fields, covering the extraction of original data by wavelet packet transform, and the quantitative analysis of steel samples through improved correlation vector machine based on laser-induced breakdown spectrum. Specifically, it is a method based on wavelet packet transform and correlation Quantitative method of steel samples based on vector machine combined with laser-induced breakdown spectroscopy. Background technique [0002] Laser Induced Breakdown Spectroscopy (Laser Induced Breakdown Spectroscopy, LIBS) is a technology based on atomic emission spectroscopy for rapid detection of the types and contents of elements contained in substances. It is widely used in metallurgical analysis, environmental monitoring, geological exploration, Medical monitoring, materials and other fields. The principle is to realize the qualitative or quantitative analysis of the chemical...

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 Patents(China)
IPC IPC(8): G01N21/71G06K9/62G06F17/14
Inventor 段忆翔谢世陈
Owner 段忆翔
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap