THE USE OF CONVOLUTIONAL NEURAL NETWORKS IN THE MANUFACTURE OF GUITARS TO IDENTIFY PRODUCT DEFECTS AND AUTOMATED SELECTION OF PAIRS OF BLANKS

D.M. Logunova, A.M. Volodina, E.V. Kurnasov, S.K. Kirillov, N.D. Tonkonozhenko

About the authors

D.M. Logunova, A.M. Volodina, E.V. Kurnasov, S.K. Kirillov, N.D. Tonkonozhenko

MIREA – Russian Technological University, 119454, Vernadsky ave. bld. 78, Moscow, Russia

Download PDF

UDC: 004.896:681.518.5+65.011.56
DOI: 10.24412/2413-7383-2025-4-39-137-148
Language: Russian

Abstract: The article presents an information and analytical system that provides automated quality control of wooden blanks in the manufacture of guitars using machine vision technologies and neural networks. The key components of the system focused on the detection of defective products and the automated selection of pairs of blanks with a matching wood pattern are considered. The results of the image analysis module, which uses neural networks with YOLO and EfficientNet architectures to dete ct product defects, are presented. It is shown that the proposed method of product quality control will significantly eliminate the subjective human factor in identifying defects and selecting guitar blanks. Algorithms and fragments of the software implementation of the system are presented, which can be integrated with SCADA and MRP systems operating in production.

Keywords: neural networks, information and analytical systems, production automation, woodworking industry, machine vision, product quality control.

References

1. Pansombut T. Wikaisuksakul S. Khongkraphan K. Aniruth P. Convolutional Neural Networks for Recognition of Lymphoblast Cell Images // Computational Intelligence and Neuroscience. 2019. Vol. 20. P. 1-12. DOI: 10.1155/2019/7519603.
2. Belovodsky V.N. On the use of neural networks to construct areas of attraction for periodic modes of nonlinear dynamic systems // Problems of artificial intelligence. 2023. No. 4 (31). P. 56-67. DOI: 10.34757/2413-7383.2023.31.4.006
3. Pikalev Ya.S. Ermolenko T.V. On neural architectures for feature extraction for the task of object recognition on devices with limited computing power // Problems of artificial Intelligence. 2023. No. 3 (30). P. 44-54. DOI: 10.34757/2413-7383.2023.30.3.004.
4. Zuev V. M. Comparison of object detection by means of artificial intelligence in comparison with classical methods // Problems of artificial intelligence. 2024. No. 3(34). P. 30-35. DOI: 10.24412/2413 -7383-2024-3-30-35.
5. Babicheva M.V. Tretyakov I.A. Automation of the procedure for recognizing fake images using neural networks // Problems of artificial intelligence. 2025. No. 1 (36). P. 94-105. DOI: 10.24412/2413 -7383-94-105.
6. Andrianov N.A. Dementyev V.E. Tashlinsky A.G. Object detection in an image: from Bayes and Neiman- Pearson criteria to detectors based on EfficientDet neural networks // Computer Optics. 2022. Vol. 46. No.
7. P. 139-159. DOI: 10.18287/2412-6179-CO-92.
8. Volodin I.V. Putyato M.M. Makaryan A.S. Evgenevsky V.Yu. Classification of attack mechanisms and research of system protection methods using machine learning and artificial intelligence algorithms // Caspian Journal: Management and High Technologies. 2021. No. 2(54). P. 91-98. DOI: 10.21672/2074- 1707.2021.53.1.090-098.
9. Belovodskiy V.N. On interpolation and approximation of functions using neural networks // Problems of artificial intelligence. 2024. No. 3 (34). P. 6-19. DOI: 10.24412/2413-7383-2024-3-4-19.
10. Kharlamov A. Samaev E. Kuznetsov D. and others. Semantic text analysis using artificial neural networks based on neural-like elements with temporal summation of signals // Problems of artificial intelligence. 2023. No. 3 (30). P. 4-27. DOI: 10.34757/2413-7383.2023.30.3.001.
11. Guitar for Nerds / Neale Morison – [Electronic resource] // Music archive of Christian music: [website]. – Access mode: https://noty.propovednik.com/Public/_УЧЕБНИКИ/ГИТАРА/Guitar%20For%20Nerds.pdf, free. – Caption from the screen. Date of request: 10-11-2025.
12. How Maton guitars are made. Factory Tour | gitaraclub.ru / Guitar Club – [Electronic resource] // YouTube.com: [video hosting]. – Access mode: https://www.youtube.com/live/lHReR19aEzI, free. – Caption from the screen. Date of request: 15-01-2023.
13. Redmon J. Divvala S.K. Girshick R.B. Farhadi A. You Only Look Once: Unified, Real-Time Object Detection // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2015. P. 779-
14. DOI:10.1109/CVPR.2016.91. – URL: https://www.cv-

Issue: 4(39)'2025
Section: AUTOMATION AND CONTROL OF TECHNOLOGICAL PROCESSES AND PRODUCTION
How to cite: D.M. Logunova, A.M. Volodina, E.V. Kurnasov, S.K. Kirillov, N.D. Tonkonozhenko. THE USE OF CONVOLUTIONAL NEURAL NETWORKS IN THE MANUFACTURE OF GUITARS TO IDENTIFY PRODUCT DEFECTS AND AUTOMATED SELECTION OF PAIRS OF BLANKS // Problems of Artificial Intelligence. - 2025. - № 4 (39). - P. 137-148. - https://paijournal.guiaidn.ru/en/2025/4(39)-12.html

Back to issue 4(39)'2025