A method for non-destructive determination of steel corrosion product characteristics based on bp neural network

A BP neural network and neural network technology, applied in the field of predicting actual steel corrosion products, to achieve the effect of convenient data collection, reduced test cost and operation difficulty, and strong reliability

Inactive Publication Date: 2017-07-14
TIANJIN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the selection of the number of neurons in each layer, there is currently no mature theory for reference. The number of commonly used neurons in the hidden layer is 3-5, and the number of neurons in the output layer is 1.

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 method for non-destructive determination of steel corrosion product characteristics based on bp neural network
  • A method for non-destructive determination of steel corrosion product characteristics based on bp neural network
  • A method for non-destructive determination of steel corrosion product characteristics based on bp neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The electrochemical experimental device includes a sample table, a three-electrode system: a sample (working electrode), a reference electrode (SCE electrode), an auxiliary electrode (platinum electrode) and an electrochemical workstation. When the electrochemical test device is connected to the sample section, the traditional three-electrode system is used. The preparation of the working electrode includes the following steps: take a 1cm*1cm stainless steel mesh, stick it on one side with a double-sided conductive adhesive, and put a certain mass of mixed powder Press it in from the other side, and finally seal the edge with resin, so that the working surface is a sample plane of 1cm*1cm, and finally solder the wires on the conductive glue, and seal the welding place with resin. The auxiliary electrode is a platinum electrode, the reference electrode is a saturated calomel electrode (SCE); connect the workstation, apply a constant current of 2.5mA / g-7.5mA / g, the electro...

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

PropertyMeasurementUnit
areaaaaaaaaaaa
Login to view more

Abstract

The invention relates to a BP-neural-network-based non-destructive determination method for characteristics of a steel corrosion product. The method comprises the following steps: (1) preparing pure-phase alpha-FeOOH and gamma-FeOOH; (2) preparing five or more samples of the mixtures prepared from alpha-FeOOH and gamma-FeOOH at different ratios; (3) manufacturing a working electrode used for electrochemical test; (4) mounting a three-electrode system comprising the working electrode, a counter electrode and a reference electrode, charging the working electrode with a constant current and detecting potential signals to obtain a chronopotentiometry V-T curve I; (5) drawing a standard curve to obtain two parameters Etau / 2 and Qtau; and (6) determining a chronopotentiometry V-T curve II for a rusted sample, comparing the chronopotentiometry V-T curve II with the standard curve to obtain the rust layer characteristics of the rusted sample. By virtue of the method, the in-situ detection of the characteristics of the corrosion product is carried out without breaking the rust layers; the dependence on large-scale analysis and test instruments is avoided; the method can be applied to on-site detection of the corrosion product, research on the protection performance of the rust layers and research on the influence factors of atmospheric corrosion.

Description

technical field [0001] The invention belongs to the field of material science and electrochemistry, and specifically relates to a method for non-destructively measuring the characteristics of steel corrosion products based on BP neural network. A method for predicting actual steel corrosion products. Background technique [0002] The traditional methods for determining the composition of corrosion products mainly include: X-ray powder diffraction method, Fourier transform infrared transform spectroscopy, Raman spectroscopy, etc. Diffraction characteristics of rays - the position, intensity and quantity of diffraction lines are used to identify the phase of crystalline substances, so this method is mainly for crystalline substances, that is, the crystal substances in corrosion products can only be analyzed according to the position, intensity and quantity of diffraction lines phase, and cannot be analyzed for the amorphous phase. Fourier transform infrared spectroscopy and ...

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): G01N27/26
Inventor 高志明卢丽花夏大海修妍胡文彬刘永长
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