Using Neural Network Algorithms and Machine Vision to Analyze the Dynamics of Product Quality Changes

In the article, modern technologies of automation and digitalization of production require effective methods of product quality control. One of the promising areas is the use of neural network algorithms and machine vision, which make it possible to analyze the dynamics of product quality changes in...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Wave Electronics and Its Application in Information and Telecommunication Systems (Online) S. 1 - 8
Hauptverfasser: Chabanenko, Aleksandr, Kurlov, Victor, Rassykhaeva, Maria, Puzyreva, Victoria, Daniele, Casadio
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 12.05.2025
Schlagworte:
Automation
dynamics analysis
Heuristic algorithms
Machine vision
neural network algorithms
Neural networks
Product design
Production
production automation
Quality assessment
Quality control
Real-time systems
Telecommunications
ISSN:2769-3538
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In the article, modern technologies of automation and digitalization of production require effective methods of product quality control. One of the promising areas is the use of neural network algorithms and machine vision, which make it possible to analyze the dynamics of product quality changes in real time. These technologies ensure high accuracy, minimize the impact of the human factor, and allow for rapid response to identified inconsistencies. Additionally, the introduction of machine vision and neural networks helps to increase the efficiency of big data analysis, which makes it possible to identify patterns of product degradation and predict potential defects. The use of cloud computing and integration with industrial IoT systems makes it possible to continuously monitor product quality in real time. A comparative analysis of traditional quality control methods and modern neural network algorithms shows that the use of artificial intelligence makes it possible to reduce the cost of manual product verification and improve its quality through adaptive learning and self-correction of models. This article discusses machine vision methods and neural network approaches used to analyze product quality, as well as their advantages and prospects for implementation. Examples of real-world implementations of these technologies in various industries, their economic impact and possible challenges arising during the transition to automated quality control are also given.
ISSN:2769-3538
DOI:10.1109/WECONF65186.2025.11017223