Real-Time ML-Driven Quality Control in Fully Automated Manufacturing Lines
-
DOI:
https://doi.org/10.67228/3142788X/IJMLPA-2021PII5N1MPublished 07-02-2021
Real-Time Quality Control, Machine Learning, Automated Manufacturing, Industrial Automation, Defect Detection, Anomaly Detection, Sensor Data Analytics, Industry 4.0, Smart Manufacturing, Predictive Maintenance Issue
Section
ArticlesHow to Cite
[1]A. Krishnan and R. Agarwal, “Real-Time ML-Driven Quality Control in Fully Automated Manufacturing Lines”, IJMLPA, vol. 4, no. 2, pp. 01–13, Jul. 2021, doi: 10.67228/3142788X/IJMLPA-2021PII5N1M.Abstract
In fully automated manufacturing lines, ensuring product quality in real-time is critical to maintaining efficiency, reducing waste, and minimizing production costs. Traditional quality control methods often rely on periodic inspections and static rule-based systems, which can be inadequate for dynamic, high-speed manufacturing environments. This paper presents a novel framework for real-time quality control driven by machine learning (ML) techniques integrated directly into automated production lines. Leveraging continuous sensor data streams and advanced ML models, the system detects defects and anomalies with high accuracy and low latency, enabling immediate corrective actions. We describe the system architecture, ML model development, and implementation details, followed by experimental evaluation on an industrial case study. The results demonstrate significant improvements in defect detection rates and response times compared to conventional approaches. This work highlights the potential of ML-driven real-time quality control as a key enabler of Industry 4.0 and smart manufacturing.
References
[1] Zhang, Y., & Jiang, J. (2020). Real-time defect detection in manufacturing based on deep learning: A review. IEEE Transactions on Industrial Informatics, 16(3), 1951-1962.
[2] 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.
[3] Zhou, K., Liu, T., & Zhou, L. (2016). Industry 4.0: Towards future industrial opportunities and challenges. 12th International Conference on Fuzzy Systems and Knowledge Discovery, 2147-2152.
[4] Kusiak, A. (2018). Smart manufacturing. International Journal of Production Research, 56(1-2), 508-517.
[5] Lu, Y., Liu, C., Wang, K. I. K., Huang, H., & Xu, X. (2020). Digital twin-driven smart manufacturing: Connotation, reference model, applications and research issues. Robotics and Computer-Integrated Manufacturing, 61, 101837.
[6] Qin, S. J. (2012). Survey on data-driven industrial process monitoring and diagnosis. Annual Reviews in Control, 36(2), 220-234.
[7] Graves, A., Mohamed, A.-r., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. ICASSP, 6645-6649.
[8] Hwang, S., Park, C., & Yoon, S. (2019). Real-time anomaly detection for industrial sensor data based on a generative adversarial network. Sensors, 19(19), 4221.
[9] Bousdekis, A., Magoutas, B., Apostolou, D., & Mentzas, G. (2019). Intelligent manufacturing decision support systems: A review. Computers & Industrial Engineering, 138, 106065.
[10] Sun, Y., & Huang, Y. (2021). Machine learning applications in manufacturing quality control: A review. Journal of Manufacturing Systems, 58, 206-218.
[11] Wang, L., Törngren, M., & Onori, M. (2015). Current status and advancement of cyber-physical systems in manufacturing. Journal of Manufacturing Systems, 37, 517-527.
[12] Karthik, P., & Arvind, M. (2020). Edge computing for real-time data analytics in Industry 4.0. Procedia Computer Science, 171, 1568-1577.
[13] Zolanvari, M., et al. (2020). Machine learning-based intrusion detection for IoT devices in smart manufacturing. IEEE Transactions on Industrial Informatics, 16(8), 5542-5552.
[14] Liu, Y., et al. (2021). Adaptive machine learning for predictive maintenance in manufacturing. IEEE Transactions on Industrial Electronics, 68(2), 1695-1704.
[15] Ma, Y., et al. (2018). Anomaly detection and diagnosis in industrial processes using deep learning. Journal of Process Control, 67, 106-117.
Downloads
How to Cite
[1]A. Krishnan and R. Agarwal, “Real-Time ML-Driven Quality Control in Fully Automated Manufacturing Lines”, IJMLPA, vol. 4, no. 2, pp. 01–13, Jul. 2021, doi: 10.67228/3142788X/IJMLPA-2021PII5N1M.