RESEARCH ON METHODS OF UNIFICATION AND PREPROCESSING OF EXPERIMENTAL DATA TO IMPROVE THE QUALITY OF INTEGRATION INTO AI MODELS FOR ROLL ECCENTRICITY COMPENSATION
DOI:
https://doi.org/10.34185/1991-7848.itmm.2026.01.016Keywords:
experimental data, data unification, data preprocessing, artificial intelligence, roll eccentricity, sheet rolling, adaptive control, time series, feature engineeringAbstract
The paper addresses the issues of unification and preprocessing of experimental data for their effective use in AI models for roll eccentricity compensation in sheet rolling processes. It is substantiated that the performance quality of intelligent models largely depends on the consistency, completeness, and informativeness of the input data. Approaches to time-series synchronization, data cleaning, noise filtering, normalization, and feature engineering are analyzed. It is shown that the application of data unification and preprocessing procedures improves the quality of data integration into AI models and creates prerequisites for more accurate roll eccentricity compensation.
References
Edwards W. J., Thomas P. J., Goodwin G. C. Roll Eccentricity Control for Strip Rolling Mills // IFAC Proceedings Volumes. 1987. Vol. 20, Issue 5. P. 187–198. DOI: 10.1016/S1474-6670(17)55438-5.
Chen Z.-M., Luo F., Xu Y.-G., Yu W. Roll Eccentricity Compensation Based on Anti-Aliasing Wavelet Analysis Method // Journal of Iron and Steel Research International. 2009. Vol. 16. P. 35–39. DOI: 10.1016/S1006-706X(09)60024-8.
Hameed W. I., Mohamad K. A. Strip Thickness Control of Cold Rolling Mill with Roll Eccentricity Compensation by Using Fuzzy Neural Network // Engineering. 2014. Vol. 6. P. 27–33. DOI: 10.4236/eng.2014.61005.
Tawakuli A., Havers B., Gulisano V., Kaiser D., Engel T. Survey: Time-Series Data Preprocessing: A Survey and an Empirical Analysis // Journal of Engineering Research. 2025. Vol. 13, No. 2. P. 674–711. DOI: 10.1016/j.jer.2024.02.018.
Li X., Cheng Y., Møller C., Lee J. Data Issues in Industrial AI Systems: A Meta-Review and Research Strategy // Computers in Industry. 2025. Vol. 173. Article 104361. DOI: 10.1016/j.compind.2025.104361.
