APPLICATION OF NEURAL NETWORKS FOR QUALITY IMPROVEMENT OF MANUFACTURING PROCESSES IN MECHANICAL ENGINEERING
DOI:
https://doi.org/10.34185/1991-7848.itmm.2026.01.098Keywords:
neural networks, mechanical engineering, quality assurance, deep learning, CNN-LSTM, manufacturing process monitoring, defect prediction, Industry 4.0Abstract
The rapid development of machine learning and artificial intelligence methods opens new opportunities for improving the quality of manufacturing processes in mechanical engineering. This paper examines the application of artificial neural networks (ANN) for quality assurance in machining, welding, casting and metal forming processes. The advantages of neural network approaches over traditional analytical methods are analyzed: the ability to model nonlinear relationships between process parameters and quality indicators, adaptability to variable production conditions and the possibility of integration into real-time control systems. CNN, MLP and hybrid CNN-LSTM architectures for defect prediction and tool condition monitoring tasks are considered. It is shown that the implementation of neural network systems contributes to reducing the defect rate, improving process stability and reducing quality control costs.
References
Wang J. et al. Deep learning for smart manufacturing: Methods and applications // Journal of Manufacturing Systems. – 2018. – Vol. 48. – P. 144–156. – DOI: 10.1016/j.jmsy.2018.01.003
Kumar S. et al. Application of ANN in machining processes: A review // International Journal of Advanced Manufacturing Technology. – 2012.
Zhang Y. et al. Tool wear condition monitoring method based on deep learning with force signals // Sensors. – 2023. – Vol. 23, No. 10. – P. 4595. – DOI: 10.3390/s23104595
Lin W.-C. et al. Prediction and analysis of the surface roughness in CNC end milling using neural networks // Applied Sciences. – 2022. – Vol. 12, No. 1. – P. 393. DOI: 10.3390/app12010393
Teti R. et al. Advanced monitoring of machining operations // CIRP Annals. – 2010. – Vol. 59, No. 2. – P. 717–739.
Uyan T.Ç. et al. Industry 4.0 foundry data management and supervised machine learning in low-pressure die casting quality improvement // International Journal of Metalcasting. – 2023. – Vol. 17. – P. 414–429. – DOI: 10.1007/s40962-022-00783-z
Zhang Z. et al. Deep learning for intelligent manufacturing // Journal of Manufacturing Systems. – 2019.
Kumaresan S. et al. Deep learning-based weld defect classification using VGG16 transfer learning adaptive fine-tuning // International Journal of Interactive Design and Manufacturing. – 2023. – DOI: 10.1007/s12008-023-01327-3
Madhvacharyula A.S. et al. In situ detection of welding defects: A review // Welding in the World. – 2022. – Vol. 66. – P. 611–628. – DOI: 10.1007/s40194-021-01229-6
Lee J. et al. Predictive manufacturing systems // Manufacturing Letters. – 2014.
Kusiak A. Smart manufacturing // International Journal of Production Research. – 2018. – Vol. 56, No. 1–2. – P. 508–517.
