Automation of defective products detection by machine learning methods.

Keywords: production automation, defect detection, CNN, Machine Learning. Deep Learning, Computer Vision, Quality Assurance.

Abstract

The basic methods of machine learning for the detection of defects in the fields of production of various products are presented. The use of deep learning and computer vision approaches to identify hardware faults, single and complex machine learning algorithms for quality control of software are discussed in detail.

References

Oren Ezra, How Machine Learning Slashes Quality Control Costs in Manufacturing [Електронний ресурс]. - Режим доступу: https://blog.seebo.com/machine-learning-quality-control/.

D. Juran, Quality 4.0: The Future of Quality? [Електронний ресурс]. - Режим доступу: https://www.juran.com/blog/quality-4-0-the-future-of-quality/.

Graham Immerman, The actual cost of downtime in the manufacturing industry [Електронний ресурс]. - Режим доступу: https://www.machinemetrics.com/blog/the-real-cost-of-downtime-in-manufacturing.

Partha Deka, Quality inspection in manufacturing using deep learning based computer vision [Електронний ресурс]. - Режим доступу: https://towardsdatascience.com/quality-inspection-in-manufacturing-using-deep-learning-based-computer-vision-daa3f8f74f45.

Convolutional Neural Network Architecture: Forging Pathways to the Future [Електронний ресурс]. - Режим доступу: https://missinglink.ai/guides/convolutional-neural-networks/convolutional-neural-network-architecture-forging-pathways-future/

International Journal of Software Engineering & Applications (IJSEA), Vol.6, No.3, May 2015

N. E. Fenton & N. Ohlsson (2000) “Quantitative analysis of faults and failures in a complex software system”, IEEE Transactions on Software Engineering, pp. 797-814.

T. Menzies, J. Greenwald, A. Frank (2007) “Data mining static code attributes to learn defect predictors”, IEEE Transaction Software Engineering, pp. 2-13.

S.V. Grynyuk, K.Ya. Bortnik, O.I. Miskevych, D.I. Palivoda An overview of tools for creating games on Android. / Computer-integrated technologies: education, science, production. No. 35, Art. 124-128, 2019.

Miskevych O.I., Sychev D.I., Khrystinets N.A. About modernization of the local area network on PJSC “Volynoblenergo” based on GRE-tunnel using IPSec encryption. / Computer-integrated technologies: education, science, production. №30-31., Art. 100-103, 2018

Miskevych O., Ilya Voytovich. Image formats and the appropriateness of their use in the modern World. / Computer-integrated technologies: education, science, production. №38., Art. 85-90, 2018

N. A. Khrystynets, A. A. Sakhnyuk, E. A. Sviridyuk, O. I. Miskevich. Use of бem-blocks when creating a site. / Computer-integrated technologies: education, science, production. №35., Art. 206-210, 2019

N. A. Khrystynets, Rud V.D Stochastic methods for modeling vibration mixing processes in bulk media./ Computer-integrated technologies: education, science, production. №7., Art. 96-98, 2011

N. A. Khrystynets, Rud V.D, Kolyadinsky M.I. Model of behavior of particles of bulk medium under the action of vibration segregation./ Computer-integrated technologies: education, science, production. №7., Art. 99-103, 2011


Abstract views: 0
PDF Downloads: 0
Published
2020-05-21
How to Cite
Miskevych О., Bahniuk , N., Khrystinets , N., & Marchevska , O. (2020). Automation of defective products detection by machine learning methods. COMPUTER-INTEGRATED TECHNOLOGIES: EDUCATION, SCIENCE, PRODUCTION, (39), 175-180. https://doi.org/10.36910/6775-2524-0560-2020-39-29
Section
Computer science and computer engineering