Flat enameled electromagnetic wire surface defect detection method based on deep learning

A surface defect and deep learning technology, applied in the direction of optical test defects/defects, measuring devices, scientific instruments, etc., can solve the problems of low detection accuracy and low degree of automation, and achieve high recognition accuracy, reduce production costs, and recognition speed fast effect

Active Publication Date: 2020-07-10
南通远景电工器材有限公司
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing quality parameter detection of precision flat enamelled electromagnetic wire is generally manual inspection, which has the disadvantages of low detection accuracy and low degree of automation. Therefore, it is urgent to develop a quality inspection device for flat enamelled electromagnetic wire

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
  • Flat enameled electromagnetic wire surface defect detection method based on deep learning
  • Flat enameled electromagnetic wire surface defect detection method based on deep learning
  • Flat enameled electromagnetic wire surface defect detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to make the technical means, creative features, goals and effects achieved by the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.

[0026] Such as Figure 1-4 Shown, the flat enamelled magnetic wire surface flaw detection method based on deep learning, it comprises the following steps:

[0027] Step 1: Flat enamelled magnet wire image acquisition: use a camera and surface light source installed in a specified way to collect flat enameled magnet wire images in a dark field environment;

[0028] Step 2: flat enamelled magnet wire image preprocessing: utilize the K-means clustering method to remove the part that does not contain flat enameled magnet wire in the image;

[0029] Step 3: Flaw recognition of flat enamelled magnet wire: use label data to train convolutional neural network to recognize the defect of enameled wire, and the training model is called by the inspection sys...

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
greyscaleaaaaaaaaaa
Login to view more

Abstract

The invention discloses a flat enameled electromagnetic wire surface defect machine vision detection method based on deep learning. The method comprises the following steps: 1, acquiring flat enameledelectromagnetic wire images: establishing a dark field environment, and acquiring a flat enameled electromagnetic wire image by using an area light source and a camera which are installed in a specified mode; 2, preprocessing the flat enameled electromagnetic wire image: segmenting an image of an area where the enameled wire is located by using a clustering algorithm; 3, identifying flaws of theflat enameled electromagnetic wire: training a convolutional neural network by using label data, and training a model to be called by a detection system to realize surface defect detection of the flatenameled electromagnetic wire. According to the method, the flat enameled electromagnetic wire image is acquired and preprocessed through a machine vision method, and the surface defects of the flatenameled electromagnetic wire are accurately identified through the convolutional neural network, so that the manpower input can be reduced, the detection cost is reduced, and the identification accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of surface defect detection of electromagnetic wires, in particular to a method for detecting surface defects of flat enameled electromagnetic wires based on deep learning. Background technique [0002] Product surface quality has always been a major concern in industrial production, and product surface quality will affect the commercial value and use value of the product. Electromagnetic wire, also known as winding wire, is an insulated wire used to manufacture coils or windings in electrical products. Magnet wires are generally divided into enameled wires, wrapped wires, enameled wrapped wires and inorganic insulated wires. Among them, the enamelled electromagnetic wire is made by coating the corresponding paint solution on the outside of the conductor, and then volatilizing the solvent, curing the paint film, and cooling. Problems such as unevenness and protruding defects lead to unqualified electromagn...

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 Applications(China)
IPC IPC(8): G01N21/88G06T7/00G06T7/11G06T7/194G06K9/62
CPCG01N21/8851G06T7/0008G06T7/11G06T7/194G01N2021/888G01N2021/8887G06T2207/10004G06T2207/20081G06T2207/20084G06T2207/30108G06F18/23213G06F18/24
Inventor 董桂香
Owner 南通远景电工器材有限公司
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