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

Anchor chain flash welding quality online detection method based on incremental learning

A technology of incremental learning and welding quality, applied in neural learning methods, instruments, biological neural network models, etc., can solve problems such as inability to adapt to new samples, sample imbalance, and insufficient detection accuracy.

Active Publication Date: 2020-07-31
JIANGSU UNIV OF SCI & TECH
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: The purpose of the invention is to provide an online inspection method for anchor chain flash welding quality based on incremental learning, which solves the problems of unbalanced samples, inability to adapt to new samples, and insufficient detection accuracy

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
  • Anchor chain flash welding quality online detection method based on incremental learning
  • Anchor chain flash welding quality online detection method based on incremental learning
  • Anchor chain flash welding quality online detection method based on incremental learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] The present invention will be further described below in conjunction with the accompanying drawings.

[0071] The present invention discloses a method for online detection of anchor chain flash welding quality based on incremental learning. The process is as follows: figure 1 As shown, the details are as follows:

[0072] (1) Collect 40 unqualified samples S={S 1 ,S 2 ,...,S i ,...,S 40} and 400 qualified samples T={T 1 , T 2 ,...,T i ,...,T 400}.

[0073] (2) Make the signal lengths of the samples consistent by piecewise linear interpolation.

[0074] The signals of 40 unqualified samples and 400 qualified samples are composed of electrode position signals and current signals. The i-th unqualified sample is denoted as S i =[A i ,B i ] (if attached figure 2 And attached image 3 shown), the lengths in the preheating stage, continuous flashing stage and upsetting stage are L i(1) , L i(2) and L i(3) . Electrode position signal A i expressed as A i =[...

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 an anchor chain flash welding quality online detection method based on incremental learning. The anchor chain flash welding quality online detection method comprises the following steps of: acquiring M unqualified samples and N qualified samples; enabling signal lengths of the samples to be consistent through piecewise linear interpolation; carrying out normalization processing on the signals; calculating the distance between the unqualified samples, and establishing a distance matrix; randomly extracting disqualified samples and then synthesizing the disqualified samples into new samples, and calculating the distance between the new samples and the existing disqualified samples; judging whether the number of the unqualified samples is the same as that of the qualified samples or not; constructing a convolutional neural network, and training the model; outputting a prediction result of the model on the test set; training the model by using the newly added sample; and outputting a prediction result of the model after incremental learning on the test set. According to the anchor chain flash welding quality online detection method, the number of unqualified samples is effectively increased, the imbalance problem of the samples is solved, the generalization ability of the model is improved, and the problem that the number of samples for anchor chain flash welding is increased day by day is solved.

Description

technical field [0001] The invention belongs to a welding quality detection method, in particular to an online detection method for anchor chain flash welding quality based on incremental learning. Background technique [0002] With the development of marine engineering and shipping, anchor chains have developed from plant ropes, forged anchor chains, and cast anchor chains to the current welded anchor chains. The anchor chain is connected by multiple links. It is a special chain used to buffer the external force of ships and marine engineering equipment. It needs to maintain good mechanical properties for a long time in the harsh seawater environment. Its quality will directly affect Safety of life and property of relevant personnel. At present, the quality inspection of the anchor chain is mainly through the tensile test before leaving the factory. For a whole anchor chain, if only one link breaks due to quality problems, the entire anchor chain will fail, and the losses ...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/24133G06F18/214Y02P90/30
Inventor 苏世杰王真心潘纬鸣陈赟唐文献付灵懿
Owner JIANGSU UNIV OF SCI & 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