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

Method for identifying cracks in laser cladding process

A technology of laser cladding and cracks, which is applied in the field of infrared images and image recognition, can solve problems such as cracks are difficult to identify, difficult to control, and cannot be monitored in real time, and achieve the effect of overcoming the lack of eigenvalues ​​and high recognition accuracy

Active Publication Date: 2020-10-30
DALIAN UNIV OF TECH
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The invention provides a method and system for identifying cracks in the laser cladding process of nickel-based alloys, which are used to overcome defects such as difficult identification, difficult control, and real-time monitoring of crack defects in the processing process in the existing technology, and realize the reduction of laser The number of cladding cracks, improving real-time monitoring capabilities

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
  • Method for identifying cracks in laser cladding process
  • Method for identifying cracks in laser cladding process
  • Method for identifying cracks in laser cladding process

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The specific implementation manners of the present invention will be further described below in conjunction with the accompanying drawings and technical solutions.

[0041] A method for identifying cracks in the laser cladding process, the implementation steps are as follows figure 1 ,Proceed as follows:

[0042] Step 1: Use an infrared thermal imager to collect infrared images of the nickel-based alloy laser cladding process processed with different processing parameters, and extract the image ROI from the infrared images;

[0043] Step 2: Further process the extracted infrared image ROI, and use the residual convolutional autoencoder structure to denoise the infrared image; the residual convolutional autoencoder is an improvement on the basis of the convolutional autoencoder, The structure of convolutional autoencoder is divided into input layer, convolution layer, pooling layer, deconvolution layer and output layer, such as figure 2 shown. The residual convolutio...

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 belongs to the technical field of infrared image and image recognition, and provides a method for identifying cracks in a laser cladding process. An infrared thermal imager is used for collecting infrared images of the nickel-based alloy laser cladding process under different machining parameter conditions, and image ROI extraction is conducted on the infrared images; noise reductionprocessing is performed on the extracted infrared image by using a residual convolution auto-encoder; the surfaces of the workpieces processed under different processing parameters are processed by using a dye penetrant inspection method, the crack conditions of the surfaces of the workpieces are observed, the crack conditions are divided into seriousness and non-seriousness, and the reconstructed images are classified according to the crack severity; a multi-scale convolutional neural network is used to process the de-noised reconstructed image; a reconstructed image is divided into multiplegroups of data according to different crack degrees, each group of data is divided into training data and test data in proportion, the training data is input into a multi-scale convolutional neural network for training, and the test data is used for testing the accuracy of the network after training, so that the accuracy of the network is ensured.

Description

technical field [0001] The invention belongs to the technical field of infrared images and image recognition, in particular to a method and system for identifying the degree of crack generation in a nickel-based alloy laser cladding process. Background technique [0002] Laser cladding forming (LCF) technology is a multidisciplinary emerging advanced manufacturing technology. This technology combines rapid prototyping technology and laser cladding surface strengthening technology, using high-energy laser beams to form a molten pool on the metal substrate, and the metal powder delivered to the molten pool through the powder feeding device and powder nozzle or pre-placed on the substrate The coating on the surface is melted, and after rapid solidification, it forms a metallurgical bond with the substrate on the substrate, and the material is accumulated layer by layer to form a three-dimensional near-net shape metal part. However, due to the rapid cooling and rapid heating of...

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): G06K9/00G06K9/32G06K9/40G01N21/88G06N3/04G06N3/08
CPCG01N21/8851G06N3/08G01N2021/8887G06V20/20G06V10/30G06V10/25G06N3/045
Inventor 李涛马敏李凯强杨征宇王灏孙慧刘伟嵬王奉涛
Owner DALIAN UNIV OF TECH
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