MODELING A SYSTEM FOR REAL-TIME MONITORING OF TECHNOLOGICAL PROCESSES
Authors/Creators
- 1. Researcher at Bukhara State Technical University
Description
This paper presents a comprehensive study on modeling systems for real-time monitoring of technological processes. The research focuses on integrating mathematical modeling, data-driven techniques, and hybrid approaches to improve accuracy, reliability, and responsiveness in industrial monitoring systems. The study examines how sensor data acquisition, state estimation, and anomaly detection can be combined with modern computational frameworks such as edge computing and digital twin technology. The results indicate that hybrid models provide superior performance compared to purely physical or purely data-driven approaches, particularly in nonlinear and uncertain environments. The paper also highlights key challenges including data quality, computational latency, and system scalability. Overall, the proposed modeling perspective supports the development of intelligent, adaptive, and efficient real-time monitoring systems for modern industrial applications.
Files
92-98.pdf
Additional details
References
- 1.Basseville, M., & Nikiforov, I. V. (2020). Detection of abrupt changes: Theory and application. Springer.
- 2.Chai, T., & Draxler, R. R. (2021). Root mean square error (RMSE) or mean absolute error (MAE)?—Arguments against avoiding RMSE in the literature. Atmospheric Environment, 264, 118.
- 3.Chen, T., & Guestrin, C. (2019). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
- 4.Goodfellow, I., Bengio, Y., & Courville, A. (2021). Deep learning. MIT Press.
- 5.Grieves, M., & Vickers, J. (2022). Digital twin: Mitigating unpredictable, undesirable emergent behavior in complex systems. Transdisciplinary Perspectives on Complex Systems.