A Methodological Framework for Cognitive AI Integration in Marine CAD Environments for Ship Design: Application to Pipe Routing

The increasing complexity of contemporary ship design, driven by multidisciplinary integration, dense spatial constraints, and stringent regulatory frameworks, poses significant limitations to traditional Computer-Aided Design (CAD)-based engineering workflows. While Artificial Intelligence (AI) techniques have been applied to isolated marine optimization problems, their systematic and governance-compliant integration into regulated CAD environments remains underdeveloped. This paper proposes a governance-aware methodological framework for the integration of Cognitive AI into marine CAD systems. The framework defines a layered architecture that combines structured data management, engineering corpus modeling, hybrid reasoning mechanisms (rule-based systems, machine learning models, and multi-objective optimization), and real-time CAD interaction. A human-in-the-loop cognitive cycle is embedded to ensure traceability, regulatory compliance, decision transparency, and professional accountability. To quantitatively assess engineering impact, a normalized performance evaluation model is introduced, incorporating indicators for design cycle time reduction, iteration convergence, compliance enhancement, and rework minimization. The framework is validated through a scenario-based application to pipe routing, demonstrating its analytical consistency and integration feasibility within operational design workflows. The proposed methodology establishes a reproducible and certification-aligned foundation for AI-augmented ship design, contributing to the structured digital transformation of Shipyard 4.0 environments.