Published October 18, 2024 | Version v1
Conference paper Open

IMAGE CLASSIFICATION OF AUTOMOTIVE PARTS: HELICAL GEAR, BEARING, AND WHEEL

Description

This work addresses the classification of three automotive components - wheels, bearings, and helical gears - using computer vision algorithms and deep learning. The dataset, composed of high-quality images, was obtained and reviewed to ensure the model's accuracy, which reached 90%. The system enables precise identification of the parts, contributing to the effective monitoring of components in industrial systems. 

Files

WMO-24-086_R1.pdf

Files (309.4 kB)

Name Size Download all
md5:f76e6b032ac8b7cd40b594591c7c9d9e
309.4 kB Preview Download

Additional details

References

  • RAHMAN, Md Sazzadur et al. Machine learning and internet of things in industry 4.0: A review. Measurement: Sensors, v. 28, p. 100822, 2023.
  • CHANG, Z.; LIU, S.; XIONG, X; CAI, Z.; and TU, G., "A Survey of Recent Advances in Edge-Computing Powered Artificial Intelligence of Things," IEEE Internet of Things Journal, vol. 8, no. 18, pp. 13849- 13875, 2021. DOI: 10.1109/JIOT.2021.3088875.
  • PENUMURU, Durga Prasad; MUTHUSWAMY, Sreekumar; KARUMBU, Premkumar. Identification and classification of materials using machine vision and machine learning in the context of industry 4.0. Journal of Intelligent Manufacturing, v. 31, n. 5, p. 1229-1241, 2020.
  • KAGGLE. "Your Machine Learning and Data Science Community" Kaggle. 2023. Available at: <http://www.kaggle.com/>. Accessed on: 09/12/2023.
  • BANACHEWICZ, Konrad; MASSARON, Luca. The Kaggle Book: Data analysis and machine learning for competitive data science. Packt Publishing Ltd, 2022.
  • EDGE IMPULSE. "Teach edge machine learning using Edge Impulse". Edge Impulse. 2023. Available at: <http://edgeimpulse.com/university>. Accessed on: 09/12/2023.
  • ANAPA REDDI, V.; et al. Edge Impulse: An MLOps Platform for Tiny Machine Learning. Proceedings of Machine Learning and Systems, v. 5, 2023.
  • WAQUAR, Automobile-parts-classification, Kaggle, 2022. DOI: 10.34740/KAGGLE/DSV/4064828. Available at: <https://www.kaggle.com/dsv/4064828>. Accessed on: 08/10/2024.