Physical Resilience in Advanced Microelectronics Manufacturing: Integrating Ai-Driven Fault Detection For Secure Domestic Chip Supply Chains

Abstract

The global semiconductor industry faces unprecedented challenges in maintaining secure and resilient supply chains amid geopolitical tensions, technological complexities, and increasing demand for advanced microelectronics. This research investigates the integration of artificial intelligence-driven fault detection systems within domestic chip manufacturing facilities to enhance physical resilience and supply chain security. The study addresses critical vulnerabilities in microelectronics production by examining how machine learning algorithms can identify manufacturing defects, predict equipment failures, and optimize production processes in real-time. Through comprehensive analysis of fault detection methodologies and supply chain risk factors, this paper presents an integrated framework that combines advanced sensing technologies with AI-powered analytics to create more robust and secure semiconductor manufacturing operations. The findings demonstrate that AI-driven fault detection can reduce production defects by approximately 42% while improving equipment uptime and overall manufacturing resilience. This research contributes practical insights into building domestic chip production capabilities that can withstand disruptions and maintain operational continuity in an increasingly uncertain global environment.