Intelligent Decision Optimization System for Enterprise Electronic Product Manufacturing Based on Cloud Computing

Abstract

With the rapid growth of electronic product manufacturing, enterprises increasingly face challenges in balancing product quality and cost control across multi-stage production processes. Key decisions—such as whether to inspect or disassemble spare parts, semi-finished, and finished goods—are interrelated and significantly influence efficiency and quality. To address this, we propose an Intelligent Decision Optimization System for Electronic Product Manufacturing Based on Cloud Computing. Leveraging the scalability and processing power of cloud platforms, the system integrates simulation-based machine learning to optimize inspection and disassembly strategies. Using real production data from a Shenzhen-based electronics manufacturer (2011–2014), which includes detailed records of defect rates, production volumes, costs, and inspection actions, we simulate workflows and construct a cost analysis model. Results reveal that the optimal strategy is to inspect all spare parts while omitting inspection and disassembly for later stages, minimizing overall cost while maintaining stability. This research highlights the value of intelligent information systems in modern manufacturing and offers a foundation for future exploration of deep learning and multi-objective optimization in quality-cost decision-making.