JavaScript is Disabled
Your browser's JavaScript functionality is disabled. It has to be enabled to use this function of ConfTool.
Here you can find information on how to enable JavaScript
If you have any problems, please contact the organisers at design2026@fsb.unizg.hr.

Conference Agenda

Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).

Please note that all times are shown in the time zone of the conference. The current conference time is: 18th Apr 2026, 04:05:11pm CEST

Agenda Overview

Session

D326: AI-DRIVEN DESIGN AND PERFORMANCE ANALYSIS IN ADDITIVE MANUFACTURING

Time:

Wednesday, 20/May/2026:

10:15am - 11:15am

Session Chair: Jonathan Cagan, Carnegie Mellon University, United States of America

Location: Conference Hall Šipun

Presentations

A concept for AI supported knowledge extraction in design for additive manufacturing

Pascal Schmitt, Stefan Zorn, Kilian Gericke

University of Rostock, Germany

This paper presents a concept for an AI-supported DfAM framework aimed at supporting knowledge extraction, focusing on early design phases. The concept is derived from a set of objectives and integrates, in addition to the user, an agile DfAM process model, an AI copilot based on a large language model, and a structured knowledge base. A configured GPT is used as a prototype to demonstrate the feasibility of selected required functions. With regard to a full-scale framework, findings from this prototyping process and remaining open questions are discussed.

Generative AI in the design for additive manufacturing of orthotic devices – a literature review

Abdul Monim^1,2, Didunoluwa Obilanade², Peter Törlind²

¹Politecnico di Milano, Italy; ²Luleå University of Technology, Sweden

Generative AI and additive manufacturing (AM) are shifting orthotic design from generic devices to data-driven, patient-specific solutions. This paper presents a systematic review of Generative AI in Design for AM (DfAM) for orthotic devices. It examines how AI-driven methods generate customised, lightweight orthoses via 3D printing, improving both design efficiency and anatomical fit. The review identifies biomechanical and workflow challenges that hinder adoption and outlines how Generative AI can advance orthotic DfAM, providing a conceptual workflow and suggestions for future research.

Mechanical performance of generative design structures for material extrusion: solid vs shells across mass targets

Sindre W. Eikevåg, Håvard Revheim Martinsen, Christer W. Elverum

Norwegian University of Science and Technology, Norway

This study compares solid and shell generatively designed PLA components for material extrusion (MEX) at matched mass targets (100, 150, 200 g). Geometries were generated Generative Design (GD) and manufactured by MEX, then tested in a 30° quasi-static compression rig representing prosthetic heel strike. Solid designs achieved up to 92% higher peak load, but failed abruptly, whereas shells exhibited lower strength but progressive, energy-dissipating failure. Results show that simple shelling of GD outcomes cannot replace iterative GD refinement for weight-critical, load-bearing parts.

Learning impact of CAD geometry change on finite element analysis results

Gaurav Devdikar¹, Thorsten Pohl¹, Daniel Strang¹, Benjamin Schleich²

¹Stellantis, Germany; ²Technical University of Darmstadt, Germany

This study examines how CAD geometry variations affect finite element (FE) crash simulations for automotive front rail assembly and motivate the use of combined impact measures that better reflect the physical response. Based on these insights, we outline a machine learning formulation that links geometric modifications to their simulation effects. The study centers on geometric representation, employing UV‑based graph encodings to capture local shape changes and provide the basis for advancing and validating the full prediction pipeline.