INTEGRATION OF ARTIFICIAL INTELLIGENCE AND DIGITAL TECHNOLOGIES IN DRONE MANUFACTURING: INNOVATIVE APPROACHES TO ENHANCING EFFICIENCY

Abstract

The article explores a modern approach to drone manufacturing automation through the integration of cuttingedge technologies, particularly artificial intelligence (AI) and flexible manufacturing systems. The importance of AI in automation is highlighted by its ability to adapt production lines and reduce costs through predictive failure analysis and process optimization based on big data analytics. The examined automation methods, such as neural network learning rules (Hebb's rule, delta rule, competition, and gradient descent), are utilized to enhance processes at various stages of production. Reinforcement learning approaches, particularly the Deep Q-Learning algorithm, are applied to optimize complex manufacturing systems, providing dynamic adaptation to unpredictable conditions. Simulation modeling plays a key role in optimizing manufacturing processes, allowing for testing responses to changing conditions without real-world intervention. The use of physical models and intelligent control systems for monitoring and quality control helps increase efficiency and reduce the number of defects. The focus is on the application of deep learning algorithms that model the principles of neural networks to improve production efficiency and reduce equipment failures. Automation systems such as SCADA, DCS, PLC, MES, ERP, and robotic manufacturing systems demonstrate advantages in improving productivity and product quality. This new approach to drone manufacturing automation provides significant benefits, including cost reduction, increased flexibility and adaptability, and improved quality of end products through the integration of advanced technologies and management methods.