Digitalization and optimization of dual-use goods production using artificial intelligence

This study aims to develop a methodology for optimizing the production of dual use goods and technologies through the application of artificial intelligence. The proposed approach combines proven management methods with cutting edge technologies – from machine learning to shop floor automation and robotics. Particular attention is paid to the use of AI in the manufacture and quality control of optical components such as sensors, cameras, and laser systems intended for dual use applications. We demonstrate that reinforcement learning techniques can minimize costs and improve a system’s responsiveness to external changes. Key aspects of machine learning deployment are presented: demand forecasting, inventory level optimization, real time data analysis, risk mitigation, and supply chain resilience. Mathematical models designed to quantify the effectiveness of the proposed solutions are considered, with a special focus on statistical and probabilistic methods that account for environmental uncertainty and variability. A system of indicators enabling ongoing monitoring of AI performance under sanctions pressure is proposed. The paper also introduces an algorithm for forecasting production volumes of dual use technologies that accounts for political, economic, and technological factors. Its implementation supports resource allocation optimization, cost reduction, and enhancement of national defense capability. The findings can be used both theoretically and practically when formulating long term development strategies for high tech enterprises.