AI-Integrated Design-for-Manufacturing Framework for Additive Manufacturing Systems

The adoption of Additive Manufacturing (AM) is rapidly increasing across high-value manufacturing sectors; however, its industrial scalability remains limited by inadequate Design-for-Manufacturing (DfM) practices. Traditional DfM methods fail to fully capture the complex interactions between design geometry, material behavior, and process parameters inherent to AM systems, leading to increased production costs and inconsistent quality. This paper proposes an AI-integrated DfM framework that utilizes artificial intelligence to automate manufacturability assessment, optimize design features, and recommend process-specific improvements. By incorporating historical production data, machine learning models, and intelligent feedback mechanisms, the framework enables faster design validation, reduced trial-and-error, and improved production reliability. The proposed framework is highly relevant to England’s manufacturing landscape, where digital transformation, sustainability, and productivity improvement are national priorities. Its application supports the UK’s aerospace, automotive, and healthcare industries by enabling cost-effective localized production, reduced supply-chain dependency, and enhanced innovation capability, contributing to long-term industrial growth and technological leadership.