AutoML for Industrial Process Control
Analysis of its Benefits and Impact on Real Applications
DOI:
https://doi.org/10.52825/th-wildau-ensp.v2i.2933Keywords:
Machine Learning, AutoML, Industrial Process Control, BenchmarkingAbstract
Due to the growing complexity of modern manufacturing, industrial process control systems generate vast amounts of data with significant potential for machine learning applications. While ML offers immense benefits, the lack of data science expertise poses challenges for adoption. AutoML frameworks tackle these barriers by automating key ML tasks, enhancing accessibility and efficiency. This study investigates their effectiveness in a ceramic industry use case, comparing preprocessing strategies and analyzing explainability with SHAP values validated by domain experts. The findings highlight AutoML's potential to streamline ML model development but also its reliance on domain expertise for effective feature selection and explainability.
Downloads
References
G. Martíez-Arellano, and S. Ratchev, "Towards Frugal Industrial AI: a framework for the development of scalable and robust machine learning models in the shop floor", The International Journal of Advanced Manufacturing Technology, pp. 1–23, 2024.
C. Bulla, and M.N. Birje, "Anomaly detection in industrial IoT applications using deep learning approach", Artificial Intelligence in Industrial Applications: Approaches to Solve the Intrinsic Industrial Optimization Problems, pp. 127–147, 2022.
A. Tsanousa et al., "A Review of Multisensor Data Fusion Solutions in Smart Manufacturing: Systems and Trends", Sensors, vol. 22, no. 5, 2022, ISSN: 1424-8220. DOI: 10.3390/s22051734. [Online]. Available: https://www.mdpi.com/1424-8220/22/5/1734.
A. Ahuja, and M. Gupta, "Optimizing Predictive Maintenance with Machine Learning And Iot: A Business Strategy For Reducing Downtime And Operational Costs", 2024.
A. Scriven, D.J. Kedziora, K. Musial, and B. Gabrys, "The Technological Emergence of AutoML: A Survey of Performant Software and Applications in the Context of Industry", 2022. ePrint: 2211.04148. [Online]. Available: https://arxiv.org/abs/2211.04148.
F. Hutter, J. Lücke, and L. Schmidt-Thieme, "Beyond manual tuning of hyperparameters", KI-Künstliche Intelligenz, vol. 29, pp. 329–337, 2015.
M. Garouani, A. Ahmad, M. Bouneffa, M. Hamlich, G. Bourguin, and A. Lewandowski, "Towards big industrial data mining through explainable automated machine learning", vol. 120, no. 1, pp. 1169–1188, ISSN: 1433-3015. DOI: 10.1007/s00170-022-08761-9. [Online]. Available: https://doi.org/10.1007/s00170-022-08761-9.
E. LeDell, and S. Poirier, "H2o automl: Scalable automatic machine learning", in Proceedings of the AutoML Workshop at ICML, vol. 2020, 2020.
N. Erickson et al., "AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data", 2020. ePrint: 2003.06505. [Online]. Available: https://arxiv.org/abs/2003.06505.
M.A. Al Alamin, and G. Uddin, "How far are we with automated machine learning? characterization and challenges of AutoML toolkits", Empirical Software Engineering, vol. 29, no. 4, p. 91, 2024.
M.M.T. Ayyalasomayajula, S.K. Chintala, and S. Ayyalasomayajula, "A Cost-Effective Analysis of Machine Learning Workloads in Public Clouds: Is AutoML Always Worth Using", International Journal of Computer Science Trends and Technology (IJCST), vol. 7, no. 5, pp. 107–115, 2019.
A.T. Rosário, and A.C. Boechat, "How Automated Machine Learning Can Improve Business", vol. 14, no. 19, p. 8749, ISSN: 2076-3417. DOI: 10.3390/app14198749. [Online]. Available: https://www.mdpi.com/2076-3417/14/19/8749.
Y. Sun, Q. Song, X. Gui, F. Ma, and T. Wang, "AutoML in The Wild: Obstacles, Workarounds, and Expectations", in Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, ser. CHI '23, Association for Computing Machinery, pp. 1–15. DOI: 10.1145/3544548.3581082. [Online]. Available: https://dl.acm.org/doi/10.1145/3544548.3581082.
A. Crisan, and B. Fiore-Gartland, "Fits and Starts: Enterprise Use of AutoML and the Role of Humans in the Loop", in Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, ser. CHI '21, Association for Computing Machinery, pp. 1–15. DOI: 10.1145/3411764.3445775. [Online]. Available: https://dl.acm.org/doi/10.1145/3411764.3445775.
K. Azevedo, L. Quaranta, F. Calefato, and M. Kalinowski, "A Multivocal Literature Review on the Benefits and Limitations of Automated Machine Learning Tools". DOI: 10.48550/arXiv.2401.11366. ePrint: 2401.11366. [Online]. Available: http://arxiv.org/abs/2401.11366.
F. Stoica, L.F. Stoica, F. Stoica, and L.F. Stoica, "AutoML Insights: Gaining Confidence to Operationalize Predictive Models", IntechOpen, ISBN: 978-0-85466-835-9. DOI: 10.5772/intechopen.1004861. [Online]. Available: https://www.intechopen.com/online-first/1179126.
J. Drozdal et al., "Trust in AutoML: exploring information needs for establishing trust in automated machine learning systems", in Proceedings of the 25th International Conference on Intelligent User Interfaces, ser. IUI ’20, ACM, Mar. 2020, pp. 297–307. DOI: 10.1145/3377325.3377501. [Online]. Available: http://dx.doi.org/10.1145/3377325.3377501.
A. Mumuni, and F. Mumuni, "Automated data processing and feature engineering for deep learning and big data applications: A survey", Journal of Information and Intelligence, Jan. 2024, ISSN: 2949-7159. DOI: 10.1016/j.jiixd.2024.01.002. [Online]. Available: http://dx.doi.org/10.1016/j.jiixd.2024.01.002.
M. Chaabi, M. Hamlich, and M. Garouani, "Evaluation of AutoML Tools for Manufacturing Applications", in Advances in Integrated Design and Production II, Springer International Publishing, pp. 323–330. DOI: 10.1007/978-3-031-23615-0_33.
M. Naser, and A. Alavi, "Insights into performance fitness and error metrics for machine learning", arXiv preprint arXiv:2006.00887, 2020.
S.M. Lundberg, and S. Lee, "A Unified Approach to Interpreting Model Predictions", in Advances in Neural Information Processing Systems, vol. 30, Curran Associates, Inc., 2017. [Online]. Available: https://proceedings.neurips.cc/paper_files/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf.
A.G. Team, "AutoGluon Feature Engineering Documentation", 2025. [Online]. Available: https://auto.gluon.ai/stable/api/autogluon.features.html.
F. Liu, L. Chen, Y. Zheng, and Y. Feng, "A Prediction Method with Data Leakage Suppression for Time Series", Electronics, vol. 11, no. 22, 2022, ISSN: 2079-9292. DOI: 10.3390/electronics11223701. [Online]. Available: https://www.mdpi.com/2079-9292/11/22/3701.
A. Prakash, R. Tuo, and Y. Ding, "The temporal overfitting problem with applications in wind power curve modeling", 2022. ePrint: 2012.01349. [Online]. Available: https://arxiv.org/abs/2012.01349.
Downloads
Published
How to Cite
Conference Proceedings Volume
Section
License
Copyright (c) 2025 Abdelrahman Elsharkawi, Danny Krautz, Erik Rodner
This work is licensed under a Creative Commons Attribution 4.0 International License.