Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A fast and accurate identification method for aeroengine blade defects based on artificial intelligence

An aero-engine and recognition method technology, applied in character and pattern recognition, computer parts, image analysis, etc., can solve problems such as low detection accuracy, overcome differences in experience, improve training speed and accuracy, and improve detection efficiency and accuracy. sexual effect

Active Publication Date: 2022-05-20
NORTHWESTERN POLYTECHNICAL UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the missed detection and false detection caused by human factors such as human factors such as human factors such as eye fatigue and standard understanding caused by manual evaluation of blade CT images, and to avoid the problem of low detection accuracy in the past, the present invention proposes a The rapid and accurate identification method of aero-engine blade defects based on artificial intelligence, the application of artificial intelligence deep learning algorithm to construct and optimize the identification model, constructs an efficient and intelligent turbine blade defect identification model, realizes automatic identification of defects, improves the quality and efficiency of radiographic inspection, Ensure the reliability of turbine blade detection

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 fast and accurate identification method for aeroengine blade defects based on artificial intelligence
  • A fast and accurate identification method for aeroengine blade defects based on artificial intelligence
  • A fast and accurate identification method for aeroengine blade defects based on artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043]In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, not to limit the present application.

[0044] In one embodiment, such as figure 1 As shown, a fast and accurate identification method for aero-engine blade defects based on artificial intelligence is proposed, including:

[0045] Step 1: Establish the turbine blade radiographic inspection image database, including the intact blade image database and the defective blade image database; the defect type and position in the digital image of each defective blade are calibrated in the defective blade image database.

[0046] In step 1, the digital images in the turbine blade radiography image database include digital images obtained ...

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 present invention proposes a fast and accurate identification method for aeroengine blade defects based on artificial intelligence, and uses manual calibration and data enhancement technology to build a turbine blade detection image database, which effectively solves the problem of small sample size and is conducive to improving the generalization of the model ability. Based on the artificial intelligence deep learning method, a turbine blade defect detection and recognition network is constructed, and technologies such as the maximum entropy principle acceleration strategy are used to solve the problem of "authentic" defect recognition, which greatly improves the training speed and accuracy of the model. This detection method effectively overcomes the influence of human factors such as experience differences, manual evaluation eye fatigue, and standard understanding, so that the radiation detection of blades can be standardized and intelligent, greatly improving the detection efficiency and accuracy, and ensuring the production of turbine blades. reliability.

Description

technical field [0001] The invention belongs to the field of processing, manufacturing and quality inspection of aero-engine blades, and in particular relates to an artificial intelligence-based method for quickly and accurately identifying defects of aero-engine blades. Background technique [0002] Turbine blades are one of the core components of aero-engines. With the continuous improvement of aircraft performance, the requirements for reliability testing are becoming more and more stringent. Turbine blade defect detection has gradually developed from traditional film detection to current computerized ray tomography detection. At the same time, the requirements for objectivity, accuracy and reliability of ray detection are getting higher and higher. [0003] Due to the complex internal structure, the existing engine blades are generally formed by precision casting without margin. During the molding process, defects such as cracks, cold shuts, pores, slag inclusions, 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): G06T7/00G06K9/62G06V10/774G06V10/764
CPCG06T7/0006G06T2207/10081G06F18/214G06F18/241
Inventor 肖洪王栋欢
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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