Scholarlink

Abstract <p>A program developed for increasing the efficiency of keeping track of the production process by automating parts identification in production containers and using QR codes is described. To detect tags and objects in containers, a cascade algorithm is developed that uses trained convolutional neural networks YOLO and VGG19, increasing the accuracy of recognition while significantly reducing the size of the training sample for neural networks. The developed program is tested using production equipment at Samara University. The experimental results show 93% accuracy in identifying parts when using the algorithm developed.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Development of a Program for Process Monitoring in Production Systems

  • 期刊论文

  • 发表日期：

    2025年12月22日

查看全文
  • V. A. Pechenin,
  • A. M. Kovaleva,
  • P. I. Kiseleva,
  • A. I. Khaimovich

摘要

Abstract

A program developed for increasing the efficiency of keeping track of the production process by automating parts identification in production containers and using QR codes is described. To detect tags and objects in containers, a cascade algorithm is developed that uses trained convolutional neural networks YOLO and VGG19, increasing the accuracy of recognition while significantly reducing the size of the training sample for neural networks. The developed program is tested using production equipment at Samara University. The experimental results show 93% accuracy in identifying parts when using the algorithm developed.