| Home | My Account | Post Article | Upload Showcase | Site Shortcuts | Feedback | About us |

  Home > Smart Manufacturing technology >  

Seven Tech
Pat. Warn
Pat. Level2
Prj cases
Model Sys
New L2
Ind. Softw.
Key Prjs
Smart Equip
Model Prjs
Li Batt Ind.
Steel Ind.


Defect Warn

Equip Intelli

Domain Sale


- Class Time
- Classes
- Resources
- Lrn Method
- Status Need
- Metaverse
- Li Batt Tech
- Equip Softw.
- Intelli System

Metal Pass Defective Product Detection Based on Similarity Model

Online Defect Detection System Based on Optical Photography and Model Judgment

Current defect detection: in China, it is mainly through the identification of human eyes, which requires the participation of a large number of inspectors. Each factory usually needs dozens to hundreds of people to detect defective products. The current automatic detection system is usually based on the training system of existing open source software, using the existing defect library. This kind of system has a serious problem that is difficult to solve: because the defective samples in the defect library can never include all defects, it is difficult to ensure that no defective products are misjudged as genuine products, so many manufacturers do not accept this kind of system.

Metal Pass Online Defect Detection System: our team has developed a successful knife notch online detection system, which can become an online defect detection system with a little customization and development. The detection system adopts a step-by-step method. The first step is to take high-speed continuous photos of the parts to be measured; The second step is to convert the photos into digital according to a certain algorithm, and use digital image processing technology; The third step is to model the defect according to the logic and data, describe the defect degree of the part to be tested, and then detect the defect according to this model. Relevant defect models have been trained and debugged by a large number of defects in the defect library, including the defect degree of each defect in the defect Library (such as 60-100 points, rather than only qualified and unqualified). We have eight self-learning optimization technologies to ensure accuracy.

The team's main technical advantages: mainly lies in the accurate modeling of defects. Accurate modeling technology is first reflected in the definition of defect pictures at the stage of converting pictures into numbers, and then more importantly in the defect description based on the converted numbers.

Development Example of Defect Online Detection System: Automobile Parts Processing

Traditional defect detection is carried out through image comparison: the product images taken on site are compared with the photos in the gallery. If the similarity is high, it is a defective product. Because the pictures of defective products can never be collected comprehensively, there are always defective products that leak the net and are wrongly placed in the genuine products. Metal Pass system adopts similarity model and 8 self-study, which solves this common problem. For auto parts processing, Metal Pass system has a high leading position through technical development in 12 fields.

Internet Platform Provides Robot "Brain" For Defective Product Identification

The logic of identifying defective products of different products is different; The defective identification logic of each product can be downloaded from the Internet platform; The defective product identification logic of new products will be continuously added on the platform for download for use by the defective product screening robot.

Tech & Products

   Situation, Metauniverse, 4.0 brains, Smart manug, Equipment Softw.
Defect warning, Defect detection, Li-battery, Level 2 platform


Contact us: Please contact Linkedin in www.Linkedin.com/in/intelli, OR scan the figure below to add Wechat (e.g. myQQfriend); Tel: (+1) 858 898 1288 or (+1) 858 6090468; E-mail BLiMetaverse@Gmail.com. See Profile of the key consultant.


  | Private Policy | Terms & Conditions | About Us | AdvertisePartnerInvestorSponsorlistings |  
Copyright: 2022 Metal Data LLC. All right reserved