MAPPING ARTIFICIAL INTELLIGENCE RESEARCH IN COLD SPRAY ADDITIVE MANUFACTURING

Abstract

Cold Spray Additive Manufacturing (CSAM) is a solid-state process that enables high-rate fabrication and repair of metallic components with low thermal input, making it suitable for heat-sensitive materials. Its wider industrial adoption, however, is constrained by challenges in porosity control, geometric accuracy near edges and concavities, anisotropy, and costs linked to gas use and nozzle wear. Recent research increasingly integrates artificial intelligence (AI) and machine learning (ML) to address these issues. This review analyses how AI/ML is applied to CSAM-specific problems and identifies the model types most commonly used. Based on keyword co-occurrence and clustering, the literature is structured into four themes: design and inverse planning, materials analytics, in situ monitoring and defect analysis, and deposition modelling with AI-enabled optimisation. Dominant approaches include physics-informed surrogate models, active learning for difficult process regions, and uncertainty-aware optimisation. While challenges remain in data availability, transferability, and sensor integration, these methods outline a clear pathway toward robust and scalable AI/ML-enabled CSAM.