Flat glass as an important foundational material in various industries such as construction, automotive, and electronics has a significant importance in promoting the development of related industries through its production efficiency and product quality. With the development of the global economy and the continuous growth of demand for flat glass in various applications, the size of the global flat glass market is still expanding. However, the conventional flat glass industry faces some challenges in production, testing, logistics, and other aspects due to its low production efficiency, unstable product quality, high energy consumption, and high logistics costs. The rapid development of artificial intelligence technology brings some opportunities for transformation to the flat glass industry. It can play an important role in material and performance prediction, intelligent control of production processes, precise quality inspection, and efficient logistics management, effectively improving production efficiency, product quality, and market competitiveness, reducing production costs and energy consumption, and promoting the sustainable development of the industry.

This review mainly discusses the current development status and existing problems of artificial intelligence in the field of flat glass production, revealing the practical effects and challenges faced by artificial intelligence technology in promoting the intelligent development of the flat glass industry. In terms of component design and performance prediction, machine learning algorithms establish accurate prediction models via mining inherent patterns in a large amount of experimental data. For instance, the research and development cycle of new materials shortens and research and development costs reduce via combining neural networks and genetic algorithms to design new glass materials with specific optical properties and using random forest models to design components for lightweight and low expansion curtain wall glass. In terms of production process control, artificial intelligence technology plays an important role in core processes such as raw material processing, melting, forming, annealing, defect detection, cutting and sorting. Fuzzy modeling and genetic algorithm based on layered architecture are used for furnace operation optimization, and computer vision models are used for float glass melting furnace liquid level detection and control, thus improving production efficiency and product quality. In terms of identifying and diagnosing product defects, deep learning technology improves recognition accuracy and practicality through innovative model architecture, multimodal data fusion, and optimized computational efficiency. Object detection and segmentation models based on convolutional neural networks are widely used in glass defect detection. In terms of transportation, warehousing, and scheduling of flat glass raw materials, intelligent warehousing management systems and intelligent scheduling systems are gradually applied to flat glass enterprises, effectively improving the efficiency and accuracy of warehousing management and reducing transportation costs.