Endüstri 4.0 Bağlamında Yapay Zekâ Tabanlı Kalite Kontrol Sistemlerinin Üretim Verimliliğine Etkisi: Uygulamalı Bir İnceleme

Year 2025, Volume: 5 Issue: 2, 56 - 65, 23.12.2025

Begüm Acar , Özkan Şahin

https://doi.org/10.54569/aair.1808940

Abstract

Bu çalışma, otomotiv odaklı bir üretim hattında Endüstri 4.0 ilkeleriyle tasarlanan entegre bir kalite kontrol mimarisini sunmaktadır. Mimari; mikron düzeyinde boyutsal denetim sağlayan havalı mastar, CNN tabanlı görüntü işleme ile montaj doğrulama ve DMC/QR + OCR temelli tam izlenebilirliği tek bir karar katmanında birleştirir. Üç katmanlı yazılım yapısı (veri toplama, işleme/analiz, karar/geri bildirim), mikroservis mimarisi ve MES/PLC entegrasyonuyla gerçek zamanlı çalışır. Karar füzyonu “kabul–gri alan–ayır” politikasıyla üretim akışını durdurmadan doğru müdahaleyi tetikler; SPC tabanlı çevrimiçi izleme küçük sapmaları erken aşamada görünür kılar. Uygulama, montaj doğruluğunu ve ölçüm güvenilirliğini artırırken mükerrer kimlik atamalarını süreç içinde yakalayarak izlenebilirliği güçlendirmiş, hatalı ürün sevkiyat riskini azaltmış ve manuel denetim yükünü düşürmüştür. Çalışma, ölçüm–görsel–kimlik verilerini tek bir izlenebilirlik zincirinde bütünleştirerek reaktif kontrolden proaktif/önleyici kalite güvence yaklaşımına geçiş için uygulanabilir ve ölçeklenebilir bir model önermektedir.

Keywords

endüstri 4.0 , havalı mastar , montaj doğrulama , yapay zeka , CNN , CNN , CNN , Data matrix (dmc) , izlenebilirlik , mikroservis mimarisi

The Impact of Artificial Intelligence-Based Quality Control Systems on Production Efficiency in the Context of Industry 4.0: An Empirical Study

Abstract

This study presents an integrated quality control architecture designed in line with Industry 4.0 principles for an automotive-focused production line. The architecture unifies micron-level dimensional inspection via air gauges, assembly verification through CNN-based computer vision, and full traceability based on DMC/QR + OCR within a single decision layer. A three-tier software stack (data acquisition, processing/analysis, decision/feedback) operates in real time through a microservices architecture with MES/PLC integration. Decision fusion triggers the right intervention without stopping the line through an “accept–gray zone–segregate” policy; SPC-based online monitoring makes minor drifts visible at an early stage. The implementation increased assembly accuracy and measurement reliability, strengthened traceability by catching duplicate identity assignments in process, reduced the risk of shipping defects, and lowered manual inspection burden. By integrating measurement, visual, and identity data into a single traceability chain, the study proposes a practical and scalable model for transitioning from reactive inspection to proactive/preventive quality assurance.

Keywords

Industry 4.0 , Air gauge , Assembly verification , Artificial intelligence , CNN , SPC , Data Matrix (DMC) , Traceability , Microservice architecture

References

• Lasi, H., Fettke, P., Kemper, H.-G., Feld, T., & Hoffmann, M. (2014). Industry 4.0. Business & Information Systems Engineering, 6(4), 239–242.
• Kagermann, H., Wahlster, W., & Helbig, J. (2013). Recommendations for implementing the strategic initiative INDUSTRIE 4.0. Final report of the Industrie 4.0 Working Group.
• Wang, S., Wan, J., Li, D., & Zhang, C. (2016). Implementing Smart Factory of Industrie 4.0: An Outlook. International Journal of Distributed Sensor Networks, 12(1).
• Qin, J., Liu, Y., & Grosvenor, R. (2016). A Categorical Framework of Manufacturing for Industry 4.0 and beyond. Procedia CIRP, 52, 173–178.
• Bokrantz, J., Skoogh, A., Berlin, C., & Stahre, J. (2017). Maintenance in digitalized manufacturing: Delphi-based scenarios for 2030. International Journal of Production Economics, 191, 154–169.
• Zhang, Y., Ren, S., Liu, Y., Sakao, T., Huisingh, D., & Dou, Y. (2017). A framework for Big Data-driven product lifecycle management. Journal of Cleaner Production, 159, 229–244.
• Lee, J., Bagheri, B., & Kao, H. A. (2015). A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems, Manufacturing Letters, 3, 18–23.
• Wamba, S. F., Akter, S., Edwards, A., Chopin, G., & Gnanzou, D. (2015). How ‘big data’ can make big impact: Findings from a systematic review and a longitudinal case study. International Journal of Production Economics, 165, 234–248.
• Wang, S., Wan, J., Zhang, D., Li, D., & Zhang, C. (2016). Towards smart factory for Industry 4.0: a self-organized multi-agent system with big data-based feedback and coordination, Computer Networks, 101, 158–168.
• Jayaraman, P. P., Yavari, A., Georgakopoulos, D., Morshed, A., & Zaslavsky, A. (2016). Internet of Things platform for smart farming: Experiences and lessons learnt, Sensors, 16(11), 1884.
• Zhong, R. Y., Xu, X., Klotz, E., & Newman, S. T. (2017). Intelligent Manufacturing in the Context of Industry 4.0: A Review, Engineering, 3(5), 616–630.
• Alkan, B., & Kaynak, O. (2020). Industry 4.0 and Application Examples in Turkey, Mühendis ve Makina Dergisi, 61(694), 75–88.
• Dombrowski, U., Mielke, T., & Engel, C. (2014). Smart Factory – Sustainable production processes based on cyber-physical systems in the context of Industry 4.0. Procedia CIRP, 17, 645–650.
• Hawkins, D. M., & Wu, N. (2014). The CUSUM and the EWMA head-to-head. University of Minnesota Lecture Notes.
• Lawson, J. (2020). Time-Weighted Control Charts in Phase II. Online Lecture Notes.
• Okano, M. T., et al. (2025). Edge AI for Industrial Visual Inspection: YOLOv8-Based Visual Conformity Detection Using Raspberry Pi. Algorithms, 18(8), 510.
• Deep Object Detection Framework for Automated Quality Inspection. (2022). Journal of Manufacturing Systems, Elsevier.
• Calabrese, M., et al. (2025). Application of Mask R-CNN and YOLOv8 for AOI in PCB Manufacturing. SN Applied Sciences.
• Liao, L., et al. (2022). Data Extraction Method for Industrial Data Matrix Codes Based on Local Adjacent Modules Structure. Applied Sciences, 12(5), 2291.
• Karrach, L., et al. (2020). Recognition of Data Matrix Codes in Images and Industrial Conditions. Management Systems in Production Engineering.
• Sporici, D., Cușnir, E., & Boiangiu, C.-A. (2020). Improving the Accuracy of Tesseract 4.0 OCR Engine Using Convolution-Based Preprocessing. Symmetry, 12(5), 715.
• Tsai, D.-M., et al. (2021). Autoencoder-Based Anomaly Detection for Surface Defect Inspection. IFAC-PapersOnLine.
• Saeedi, J., et al. (2022). Anomaly Detection for Industrial Inspection Using Convolutional Autoencoder and Deep Feature-Based One-Class Classification. VISIGRAPP 2022.
• Mehta, D., et al. (2023). Autoencoder-Based Visual Anomaly Localization for Industrial Inspection. arXiv:2309.06884.
• Hu, L., et al. (2025). DataMatrix Code Recognition Based on Coarse-to-Fine and Transformer Methods. Electronics, 14(12), 2395.