Е-Публикации
Технически университет - София

Abstract: 2025.A manufacturing process, including in the field of electronics, must be organized in such a way as to ensure the production of quality items. This can be achieved by using and following certain quality control procedures and methods. Quality control is usually carried out at several stages of manufacturing to check that there are no deviations in product parameters, thus to ensure compliance with the production specification. Recently, in the scope of concepts related to industry 4.0, techniques from machine learning and artificial intelligence have also been applied, making quality control systems increasingly intelligent, thereby greatly assisting quality experts. The aim of the paper is to map the current scientific achievements regarding the application of machine learning in the field of quality control through bibliometric analysis and to present the results of performed experiments with data from a real manufacturing process. At the created predictive models that solve a classification task with two classes pass or fail the quality check, the following learning methods are applied: (a) artificial neural network with optimization of parameters, (b) principal component analysis and deep learning, (c) Random Forest. Performance of the three learning methods is high as the second method is particularly suitable.

References

1. Aria M, Cuccurullo C (2017) Bibliometrix: an R-tool for comprehensive science mapping analysis. J Informet 11(4):959–975. https://doi.org/10.1016/j.joi.2017.08.007
2. Ching NT, Ghobakhloo M, Iranmanesh M, Maroufkhani P, Asadi S (2022) Industry 4.0 applications for sustainable manufacturing: a systematic literature review and a roadmap to sustainable development. J Clean Prod 334:130133. https://doi.org/10.1016/j.jclepro.2021.130133
3. Czerwińska K, Pacana A (2024) Method of analyzing technological data in metric space in the context of industry 4.0. Processes 12(2):401. https://doi.org/10.3390/pr12020401
4. Escobar A, McGovern ME, Morales-Menendez R (2021) Quality 4.0: a review of big data challenges in manufacturing. J Intell Manuf 32:2319–2334. https://doi.org/10.1007/s10845-021-01765-4
5. Kehayov M, Holder L, Koch V (2022) Application of artificial intelligence technology in the manufacturing process and purchasing and supply management. Procedia Comput Sci 200:1209–1217. https://doi.org/10.1016/j.procs.2022.01.321
6. McCann M, Johnston A (2008) SECOM. UCI Machine learning repository. https://doi.org/10. 24432/C54305
7. Md QA, Jha K, Haneef S, Sivaraman AK, Tee KF (2022) A review on data-driven quality prediction in the production process with machine learning for industry 4.0. Processes 10(10):1966. https://doi.org/10.3390/pr10101966
8. Medina JG, Giancontieri G, Presti DL (2020) Quality control of manufacturing and hot storage of crumb rubber modified binders. Constr Build Mater 233:117351. https://doi.org/10.1016/j.con buildmat.2019.117351
9. Memon IA, Ali A, Memon MA, Rajput UA, Abro SAK, Memon AA (2019) Controlling the defects of paint shop using seven quality control tools in an automotive factory. Eng Technol Appl Sci Res 9(6):5062–5065. https://doi.org/10.48084/etasr.3160
10. Neural Net, rapid miner studio operator reference guide. https://docs.rapidminer.com/2024.1/studio/operators/modeling/predictive/neural_nets/neural_net.html
11. Yang T, Yi X, Lu S, Johansson KH, Chai T (2021) Intelligent manufacturing for the process industry driven by industrial artificial intelligence. Engineering 7(9):1224–1230. https://doi.org/10.1016/j.eng.2021.04.023

Issue

Copyright Springer, Singapore