Design and implementation of an AI-based web monitoring platform for real-time analysis and forecasting of industrial technological processes

Abstract

In this study, an artificial intelligence-based web monitoring platform is proposed for real-time analysis and forecasting of industrial technological processes. The relevance of the research is determined by the increasing need for digital tools that can collect heterogeneous production data, process them continuously, identify deviations in process parameters, and support timely decision-making in industrial environments. The developed platform is designed as a modular web system that integrates data acquisition, preprocessing, analytical processing, forecasting, visualization, and notification components within a unified digital environment. The methodological basis of the study includes machine learning algorithms, time-series analysis, database management, and dashboard-based visual analytics. The system architecture allows technological parameters such as temperature, humidity, pressure, energy consumption, production speed, and equipment state to be monitored in real time. Forecasting models are used to estimate future changes in process indicators and to detect potential risk situations before they lead to technological failures or efficiency losses. The proposed approach improves the transparency of industrial process control by transforming raw sensor data into interpretable analytical information. The practical significance of the work lies in the possibility of applying the platform to various production systems where continuous monitoring, predictive analysis, and rapid response mechanisms are required. The results show that the integration of artificial intelligence methods with web-based monitoring technologies can increase the reliability, adaptability, and operational efficiency of industrial digital control systems.