Electronic Component AVL and Life Cycle Prediction Based on AI

Electronic component obsolescence presents a growing challenge to product sustainability, supply chain resilience, and lifecycle cost management, particularly in industries with long product lifetimes. Traditional Approved Vendor List (AVL) management relies heavily on reactive monitoring and manual expertise, making it difficult to anticipate supply risks in advance. This paper proposes an AI-driven framework for electronic component life cycle prediction that integrates machine learning models with multi-source data, including historical procurement records, market availability, manufacturer lifecycle notices, and supply chain indicators. The proposed approach predicts component life cycle stages and obsolescence risk, enabling proactive AVL optimization and early identification of high-risk components and vendors. By automating risk assessment and decision support, the framework enhances supply chain visibility, reduces redesign and procurement disruptions, and supports more resilient and data-driven AVL management. Experimental results demonstrate that the AI-based model improves prediction accuracy and significantly reduces obsolescence-related risks compared to traditional rule-based methods.