Electrochemical noise corrosion type distinguishing method based on support vector machine

A technology of electrochemical noise and support vector machine, applied in the fields of weather resistance/light resistance/corrosion resistance, measuring devices, scientific instruments, etc., can solve problems that have not yet been applied, and achieve the effect of high prediction accuracy

Inactive Publication Date: 2015-04-08
TIANJIN UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it has not been applied to the field

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
  • Electrochemical noise corrosion type distinguishing method based on support vector machine
  • Electrochemical noise corrosion type distinguishing method based on support vector machine
  • Electrochemical noise corrosion type distinguishing method based on support vector machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The method for discriminating electrochemical noise corrosion types based on support vector machines provided by the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0023] Such as figure 2 As shown, the electrochemical noise corrosion type discrimination method based on the support vector machine provided by the invention comprises the following steps carried out in order:

[0024] Step 1) Establishing an input feature vector: sorting out the electrochemical noise signal data obtained from the electrochemical noise corrosion experiment, and thus establishing an input feature vector;

[0025] Step 2) diversity processing: the input feature vector is divided into 80% of the training set and 20% of the test set;

[0026] Step 3) Find the best SVM parameters: Since SVM uses the cross-validation method, different penalty parameters c and kernel function parameters g are taken during the training ...

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 relates to an electrochemical noise corrosion type distinguishing method based on a support vector machine. The method comprises the following steps: establishing an input feature vector; performing diversity processing; finding the best SVM parameter; training to obtain the best SVM model by a training set; and predicting the electrochemical noise corrosion type by using the SVM model. According to the electrochemical noise corrosion type distinguishing method based on the support vector machine, provided by the invention, the corrosion type can be distinguished by data obtained from an electrochemical noise corrosion experiment, the method can well complete a corrosion type distinguishing task, and the accuracy of a test set can be up to 100%; in a stability aspect, since the support vector machine adopts a structural risk minimization principle, the support vector machine is stable; the training results are very close, and the fitting and under-fitting conditions do not appear, so that the prediction accuracy is high.

Description

technical field [0001] The invention belongs to the technical field of material corrosion detection, in particular to a method for discriminating electrochemical noise corrosion types based on a support vector machine. Background technique [0002] In recent years, new electrochemical noise processing methods have emerged in an endless stream. The main idea is to apply new mathematical methods to the processing of electrochemical noise data. The specific methods are as follows: cluster analysis, using clustering methods to divide corrosion stages; Chaos theory, using chaotic parameters to distinguish corrosion types; neural network, using trained neural networks to distinguish corrosion types and predictions, etc.; these new methods have many new parameters, but the correspondence with the principle of corrosion process is slightly weak and takes longer Therefore, how to find a new processing method for electrochemical noise data and combine it with the principle of corrosio...

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): G01N17/02
Inventor 李健张宇孔伟康陈冠任郑焕军
Owner TIANJIN 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
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