Unlock instant, AI-driven research and patent intelligence for your innovation.

A Machine Learning-Based Microstructure Image Recognition Method for Titanium Alloy Forgings

A technology of microstructure and machine learning, applied in the field of image recognition, can solve problems such as insufficient accuracy, low efficiency, and low efficiency of evaluation, and achieve the effect of ensuring classification accuracy, ensuring processing efficiency, and streamlining image data

Active Publication Date: 2021-04-27
CHENGDU AIRCRAFT INDUSTRY GROUP
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] There are great limitations in comparing the microstructure of titanium alloy forgings with the standard atlas manually. First of all, "evaluation by comparing the standard atlas" must be done by professionals, and the number of professionals is rare, which greatly affects the forgings. The universality of the identification work; secondly, the results of the evaluation are still subjective. For the microstructure of the same titanium alloy forging, different professionals may have different evaluation results, that is, the accuracy of the evaluation is subject to subjective influence. very inefficient
[0004] Therefore, in view of the defects of difficult popularization, insufficient accuracy and low efficiency in the identification and judgment of the microstructure image of titanium alloy forgings in the traditional material performance evaluation of titanium alloy forgings, the present invention discloses a titanium alloy based on machine learning Image Recognition Method for Forging Microstructure

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 Machine Learning-Based Microstructure Image Recognition Method for Titanium Alloy Forgings

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] A method for identifying microstructure images of titanium alloy forgings based on machine learning in this embodiment, such as figure 1 shown, including the following steps:

[0036] Step 1. Obtain microstructure images of titanium alloy forgings of different materials, and classify the microstructure images of titanium alloy forgings based on material property levels to form a data set;

[0037] Select titanium alloy forgings corresponding to different material performance grades and obtain the corresponding microstructure images of titanium alloy forgings, and store the microstructure images of titanium alloy forgings according to material performance grades. The material performance grades of titanium alloy forgings can be divided into 1-11 There are 11 grades in total, and 11 material performance grade folders are established corresponding to 11 material performance grades, and then the microstructure images of titanium alloy forgings are stored in the correspondin...

Embodiment 2

[0045] This embodiment is further optimized on the basis of Embodiment 1, and the step 3 includes the following sub-steps:

[0046] Step 3.1, segment the feature vector obtained in step 2 to obtain several feature vector segments;

[0047] According to step 2, each titanium alloy forging microstructure image can be represented as a 324-dimensional feature vector. First, the 324-dimensional feature vector is segmented, and every 6-dimensional vector is taken as a segment, that is, the 324-dimensional feature vector can be Divided into 54 feature vector segments.

[0048] Step 3.2, perform pooling processing on the feature vector segment, select the one-dimensional vector with the largest value in the current feature vector segment, and use the one-dimensional vector to represent the current feature vector segment;

[0049] Then perform the pooling operation on the segmented feature vector segments, select the feature vector with the largest value in the vector segment as a one...

Embodiment 3

[0053] This embodiment is further optimized on the basis of the above-mentioned embodiment 1 or 2, and the step 4 includes the following sub-steps:

[0054] Step 4.1. Use the support vector machine to construct a corresponding number of classifiers corresponding to the material performance levels, that is, to construct 11 classifiers corresponding to 11 material performance levels through the support vector machine;

[0055] Step 4.2. Each classifier corresponds to a titanium alloy forging microstructure image of one material property level and performs two classifications to obtain classifier models corresponding to different material property levels;

[0056] Through the established classifier, the feature vector of the titanium alloy forging microstructure image is classified into the corresponding material property level for classification training. For one type, the microstructure images of titanium alloy forgings of other material performance grades are divided into anot...

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 for recognizing the microstructure image of a titanium alloy forging based on machine learning. Classify and form a data set; step 2, extract the feature vector of the microstructure image of the titanium alloy forging in the data set; step 3, select the microstructure image of the titanium alloy forging from the data set to construct a training set, and then display the titanium alloy forging in the training set The feature vector of the microstructure image is segmented, pooled, and normalized; step 4, based on the training set, the support vector machine is used to classify the classifier to obtain a classifier model, and the titanium alloy forging is displayed through the classifier model. Recognition of microstructure images; the invention greatly improves the accuracy and efficiency of judging the material performance grade of titanium alloy forgings, so that the judgment of material performance grades of titanium alloy forgings can be generally and quickly carried out.

Description

technical field [0001] The invention belongs to the technical field of image recognition, in particular to a method for recognizing microstructure images of titanium alloy forgings based on machine learning. Background technique [0002] The material properties of titanium alloy forgings, such as tensile properties, fracture toughness, fatigue properties, impact toughness, etc., are factors that must be considered in the manufacturing process. If the material properties of titanium alloy forgings are not qualified, it will seriously affect the quality of parts manufacturing. Traditionally, the identification of the material properties of titanium alloy forgings is judged by manually identifying the microstructure of the forgings. Professionals first observe the microstructure of the titanium alloy forgings, and then compare it with the standard map. The similarity between the microstructure and the standard map, the microstructure of the titanium alloy forging is most simila...

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): G06T7/00G06K9/62
CPCG06T7/0004G06T2207/10056G06T2207/20081G06T2207/30116G06F18/2411
Inventor 汪迢迪卢大伟段作衡陈向东朱国仁王平
Owner CHENGDU AIRCRAFT INDUSTRY GROUP
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com