Investigation of Intelligent Control Methods for Minimizing Production Risks in the Glass Industry
Eltun Safarli
*
Department of Instrument Engineering, Azerbaijan State Oil and Industrial University, Baku, Azerbaijan.
Stanislav Aghamatov
Department of Instrument Engineering, Azerbaijan State Oil and Industrial University, Baku, Azerbaijan.
*Author to whom correspondence should be addressed.
Abstract
Aims: This article aims to analyze the strategic significance of glass production and identify primary challenges regarding energy efficiency and environmental impact. It explores the potential of Industry 4.0 technologies, specifically Fuzzy logic and smart sensors, to enhance production quality and minimize operational losses.
Study Design: This is an analytical study focusing on intellectual measurement and control systems. It involves the systematic modeling of production stages to optimize energy usage and quality, incorporating autonomous defect detection frameworks.
Place and Duration of Study: Department of "Instrumentation Engineering" (Intellectual Measurement and Control Systems), Azerbaijan State Oil and Industry University (ASOIU), between 15 January 2026 - 15 February 2026.
Methodology: The research involved a systematic analysis of glass production stages, focusing on thermal efficiency at 1500°C. Precision batching logic was developed using high-precision gravimetric scales synchronized via PROFINET/Modbus TCP protocols. Closed-loop simulations modeled temperature stability and real-time defect detection through AI-driven image processing. Additionally, a theoretical evaluation of hydrogen-natural gas blends was conducted to assess potential emission reductions.
Results: Integration of intellectual control systems significantly enhances thermal stability by reducing furnace temperature fluctuations. The implementation of an intelligent Predictive Efficiency Trim model yields a measurable reduction in fuel consumption by 3–5%. The application of Convolutional Neural Networks (CNN) for quality inspection effectively distinguishes genuine material flaws (seeds, stones) from superficial contaminants, significantly increasing production yield compared to traditional methods. Furthermore, the use of hydrogen-natural gas blends contributes to lower carbon emissions while maintaining combustion efficiency.
Conclusion: Implementation of intellectual measurement and autonomous control systems offers an efficient approach to optimizing glass production, reducing both energy consumption and financial burden. These systems provide a robust solution for minimizing production risks and facilitating the transition to sustainable energy alternatives through digital precision.
Keywords: Glass manufacturing, intellectual measurement, autonomous control systems, CNN, thermal stability, industry 4.0, defect detection, sustainable energy