Research

This research area focuses on optimizing the design of components to fully leverage the capabilities of additive manufacturing technologies. 

Part decomposition involves breaking down complex assemblies into smaller, more manufacturable sub-parts, enabling improved printability, reduced support structures, and enhanced post-processing efficiency. 

It aims to maximize the benefits of AM by considering structural integrity, assembly feasibility, and cost-effectiveness

This field addresses the efficient planning, scheduling, and control of large-scale additive manufacturing facilities, commonly referred to as 3D printing farms. 

Research focuses on optimizing machine utilization, workflow automation, inventory management, and order fulfillment strategies to improve throughput and reduce operational costs. 

It plays a crucial role in scaling up production for mass customization and on-demand manufacturing.

This research area investigates the application of deep reinforcement learning algorithms to optimize complex decision-making processes in industrial environments. 

It involves training intelligent agents to autonomously manage tasks such as production scheduling, quality control, and energy optimization. 

The goal is to enable adaptive and data-driven decision-making that enhances operational efficiency and system resilience. 

A digital twin is a virtual replica of a physical industrial system that enables real-time monitoring, simulation, and predictive analysis. 

Research in this area explores how to create accurate and dynamic digital models to optimize system performance, anticipate failures, and support decision-making processes.