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

AI-based magnetic core product defect detection system and method

A product defect detection system technology, applied in the field of artificial intelligence, to achieve the effect of simple transplantation, fast detection speed, and speed improvement

Pending Publication Date: 2020-01-14
浙江华是科技股份有限公司
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to propose a universal and efficient algorithm for the complex situation of magnetic core defect detection by traditional graphics methods, and propose an AI-based magnetic core product defect detection system and method

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
  • AI-based magnetic core product defect detection system and method
  • AI-based magnetic core product defect detection system and method
  • AI-based magnetic core product defect detection system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be further described in detail below in conjunction with the accompanying drawings, and specific implementation methods will be given.

[0029] Such as figure 1 As shown, the AI-based magnetic core product defect detection method of the present invention adopts a system including a camera image acquisition and preprocessing module, a pre-trained SSD model based on Inception_v3, a comprehensive screening module and a model operation scheduling module. The image acquired by the front-end camera is transmitted to the camera image acquisition and preprocessing module through the network, and the image preprocessed by the camera image acquisition and preprocessing module is performed by the SSD model based on Inception_v3 pre-trained in the model operation scheduling module selection subprocess Detect and identify, and feed back the results to the comprehensive screening module to further screen with the results of cluster analysis performed in adv...

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 AI-based magnetic core product defect detection system and method. The system comprises a camera image acquisition and preprocessing module, a pre-trained SSD model based onInception _ v3, a comprehensive screening module and a model operation scheduling module; the camera image acquisition and preprocessing module acquires an image and preprocesses the image for the model operation scheduling module to perform subsequent operation; the pre-training model performs target detection and classification on the image and outputs a candidate box, a classification result and a confidence score; the comprehensive screening module further judges whether the product is qualified or not according to the detection result of the SSD model; and the model operation schedulingmodule allocates each process to synchronously use an SSD model for calculation. The system and method have the characteristics of simplicity in transplantation, high detection speed, wide detectabledefects and high accuracy.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to an AI-based magnetic core product defect detection system and method. Background technique [0002] Object recognition is widely used in current intelligent monitoring equipment, such as relatively mature face recognition and license plate recognition. However, compared to images such as faces and numbers with fixed features, there are multiple problems in the defect recognition of parts, such as the type of defects, the size of defects, the position and shape of parts, and the shooting conditions. In addition, for parts qualification inspection, the operation speed is required to be extremely fast, and the image algorithm of a single GPU is difficult to meet the speed requirements of the pipeline. The multi-GPU image detection algorithm based on artificial intelligence overcomes this problem well. [0003] In recent years, artificial intelligence ha...

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): G06T7/00G01N21/88
CPCG06T7/0004G01N21/8851G06T2207/20036G06T2207/20081G06T2207/20084G06T2207/10004G06T2207/30108
Inventor 俞永方叶建标
Owner 浙江华是科技股份有限公司
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