Keywords
LLM-based Chatbot
(1)
(2)
Keyword #1
Generative Design
Keyword #2
(3)
(4)
In the field of engineering design, many students and beginners face barriers when using simulation tools like Ansys Discovery.
They often struggle to select appropriate materials, set boundary conditions, and interpret simulation results without expert guidance.
Despite the growing importance of simulation-based design, the steep learning curve and lack of intuitive support limit broader adoption.
To address this, we propose a chatbot-powered system that integrates LLMs (such as GPT-4) to assist users in understanding, analyzing, and improving their designs
Background
Prototype
The prototype focused on intuitiveness and guidance.
We designed the chatbot interface to provide step-by-step assistance, especially in material selection and simulation interpretation, where users often feel lost.
The UI was kept minimal and context-aware, helping users focus on decision-making without overwhelming technical details.
01
Starting the Conversation with Ansys Chatbot
The chatbot initiates the conversation by offering multiple assistance options, such as material suggestions, simulation guidance, and design review support.
02
Simulation Feedback Support
The chatbot analyzes simulation results and provides design feedback, such as material alternatives or structural improvements.
03
AI-Guided Design Alternatives
The chatbot suggests alternative design options by analyzing the user’s feedback and performance requirements.
Visual candidates are presented to help the user explore more ergonomic or aesthetically diverse forms.
System Flow
Analysis support using a
GPT-4-powered chatbot
Request clarification
on analysis results
Collect specific
requirements
Identify areas for improvement
and suggest questions
1
2
3
Generative design
using GAN
Modeling
STEP 1
Feasibility Check
STEP 2
Evaluation
STEP 3
Decision Making
STEP 4
CODA grow up in bilingual environments sign language at home and spoken language in society.
Navigating between two different languages and cultures, they often struggle to have deep conversations with their parents.
COM-US was designed to address this communication gap and the emotional challenges that come with it.
Design system
CODA grow up in bilingual environments sign language at home and spoken language in society.
Navigating between two different languages and cultures, they often struggle to have deep conversations with their parents.
COM-US was designed to address this communication gap and the emotional challenges that come with it.
Future Agenda
The system can be extended to cover the full design cycle from AI assisted shape generation and material selection to structural evaluation and topology optimization within Ansys Discovery.
Design Generation
step 1
Design Evaluation
step 2
Design Optimization
step 3
Design Recommendation
step 4
Design
Engineering
Recommend materials suitable for purpose
Support structural analysis
Shape suggestions
Generation of similar form models
GPT-4 -> OpenSCAD[6]
-> sf-GDT[7] -> Selection
Selected Design -> Discovery
Additional thermal and
structural analysis using
Applied Topology Optimization
in Ansys Discovery [8]
User Selection
discovery Chatbot
LLM-based Generative Engineering Design
Suggestion using Ansys Discovery
Period
Type
role
Oct. 2024
LLM-based chatbot suggesting engineering designs
Designed user flows and UI/UX prototypes
Team member
YeaJong Kang
-
Frontend Developer
Hayeon Song
-
Backend Developer
YeongHwan Shin
-
Researcher
Eunnarae Song
-
UX ∙ Product Designer
EunnaraeSong © 2025
UI/UX designer