Integrating Generative Design and Cloud-Edge Intelligence for Autonomous Production Systems

The autonomous production systems need to be optimized in design within a few seconds, have real-time intelligence, and resilience decision-making to work in dynamic industrial conditions. The present paper introduces an empirical machine learning-based system that combines Generative Design (GD) and Cloud-Edge Intelligence (CEI) to allow adaptive and self-optimizing manufacturing systems. Generative design algorithms are used to create optimal production layouts and component structures automatically subject to multi-objective requirements including cost, energy usage, and structural performance. Cloud intelligence is used in large-scale model training, global optimization, and historical analytics and edge intelligence in low-latency inference and local adaptation on the shop floor. Simulated smart factory data is carried out through an empirical assessment that considers production logs, sensor streams and design constraints. Findings indicate that the suggested integrated framework is more effective in increasing production efficiency, cutting down design cycle time, and decreasing system latency than cloud-only and rule-based baselines. The paper presents how combined use of generative models with distributed intelligence can be beneficial to the next-generation autonomous manufacturing. Based on experimental results, the mean increase in prediction accuracy was 12%, the robustness of the system with respect to adversarial conditions improved by 20%, and the time taken for the system to make decisions and resource utilization by 17% compared to using only a cloud-based server and non-adversarial learning methods.