Определение качества изделий из алюминиевых сплавов, полученных методом литья с последующей механической обработкой с помощью методов машинного зрения

Ivan V. Chufarov

Authors

Ivan V. Chufarov Ulyanovsk State Technical University

How to cite

GOST Chufarov I. V. Determination of the quality of aluminum alloy products obtained by casting followed by mechanical processing using machine vision methods // STROITEL'NYE I DOROZHNYE MASHINY. 2025. Vol. 69. No. 2. P. 53-59.

APA Chufarov, I. V. (2025). Determination of the quality of aluminum alloy products obtained by casting followed by mechanical processing using machine vision methods. STROITEL'NYE I DOROZHNYE MASHINY, 69(2), 53-59.

Abstract

The paper provides a brief overview of the use in the automotive industry of aluminum alloy parts obtained by high-pressure casting with subsequent machining. The most common defect in the production of these parts is briefly described. The necessity of solving the problem of defect control of products made of this material using machine vision using neural networks is substantiated. The defect search was analyzed using the YOLOv8 neural network

Keywords

machine vision neural networks deep learning YOLO casting machining defects

Funding

The authors did not declare any external funding for this research.

References

Андриянов Н.А., Дементьев В.Е., Ташлинский А.Г. Обнаружение объектов на изображении: от критериев Байеса и Неймана – Пирсона к детекторам на базе нейронных сетей EfficientDet // Компьютерная оптика. 2022. Т. 46. № 1. С. 139-159.

Дементьев В.Е., Савинов Р.А., Суетин М.Н., Подлобошников А.Г. Система распознавания повреждений металлических конструкций // Автоматизация процессов управления. 2021. № 2. C. 40-45.

Казанцев С.П., Фурман Л.Е. Дефекты отливок при литье по выплавляемым моделям. Екатеринбург: Информационный портал Уральского федерального университета, 2019. 109 с.

Карунин А.Л., Бузник Е.Н., Дащенко О.А. Технология автомобилестроения: учеб. для вузов. М: Академический проект: Трикста, 2005.

Коновалов Д.Н., Хольшев Н.В., Глазков Ю.Е., Милованов А.В., Прохоров А.В., Ведищев С.М. Технологические процессы изготовления деталей двигателей внутреннего сгорания: уч. электр. изд. Тамбов: ИЦ ТГТУ. 2023. 98 с.

Сеничев А.В., Новикова А.И., Васильев П.В. Сравнение глубокого обучения с традиционными методами компьютерного зрения в задачах идентификации дефектов // Молодой исследователь Дона. №4(25). 2020. С. 64-67.

Хамидов Э.Х. Глубокое обучение: понятие и применение // Молодой ученый. 2020. № 37(327). С. 8-11.

ChenYa., Ding Yu., Zhao F., Zhang E., WuZh, Shao L. Surface defect detection methods for industrial products: a review // Applied science. 2021. Vol. 9. MDPI AG. рр. 35-98.

Deep Learning vs Traditional Computer Vision. 2024. https://www.researchgate.net/publication/331586553_Deep_Learning_vs_Traditional_Computer_Vision

Determination of the quality of aluminum alloy products obtained by casting followed by mechanical processing using machine vision methods

Authors

How to cite

Abstract

Keywords

Funding

References

Published

Issue

Section

Metrics

Rights and terms of use

Similar Articles

Similar Articles

Neural network optimization of routes and logistics of construction equipment at large facilities: from planning to autonomous management

Intelligent systems for recognizing dangerous areas and preventing accidents on construction sites: neural networks in machine safety management

Intelligent predictive quality control systems in construction: analyzing the effectiveness of machine learning for automated inspection of construction defects

quantum sensors, autonomous robotic platforms, offshore hydrocarbon deposits, geophysical modeling Adaptive machine learning algorithms for self-regulating earthmoving equipment control systems in difficult ground conditions, predictive analytics, neural

Development of intelligent control systems for construction robots based on machine learning algorithms to improve the accuracy of installation operations

Methods of protection against radio frequency attacks of wireless networks

Predictive maintenance of construction machinery based on neural network analysis of sensor data: reduced downtime and increased service life

Development of a machine learning model for automatic detection of SQL injections in web applications of the construction industry

Ecology and the use of regression analyses to estimate the biomass of forest stands, as well as methods for mapping and visualizing carbon stocks in a machine learning environment

A web-based design automation platform in construction based on the integration of BIM technologies and digital twins