LLMs enhance TRIZ for automated engineering innovation

Why It Matters

This approach offers a more accessible and efficient way for designers and engineers to explore inventive solutions, overcoming the traditional barriers of TRIZ's complexity and knowledge dependency. It opens doors for AI-assisted ideation, potentially accelerating product development cycles and fostering novel design outcomes.

Key Finding

An AI system called AutoTRIZ successfully automates the TRIZ innovation methodology using LLMs, providing structured solutions for engineering challenges and proving effective in case studies.

Key Findings

• AutoTRIZ, an LLM-integrated TRIZ system, can automate the TRIZ reasoning process.
• The system generates structured solution reports for engineering problems.
• Comparative experiments and a real-world case study demonstrated the effectiveness of AutoTRIZ.

Research Evidence

Aim: Can Large Language Models be effectively integrated with TRIZ to automate and enhance the process of engineering innovation?

Method: Comparative experimental evaluation and real-world case study.

Procedure: An AI system, AutoTRIZ, was developed by integrating LLMs with TRIZ. Its effectiveness was demonstrated through comparative experiments using textbook cases and a real-world application in designing a Battery Thermal Management System (BTMS).

Context: Engineering innovation and product design.

Design Principle

Leverage AI to automate and enhance structured innovation methodologies for more efficient and comprehensive ideation.

How to Apply

Explore and experiment with AI platforms that offer integrated TRIZ or other ideation frameworks to assist in your design challenges. Consider how LLMs can help in analyzing problem statements and generating initial solution concepts.

Limitations

The effectiveness and interpretability of LLM-generated solutions may vary depending on the LLM's capabilities and the complexity of the problem. The 'black box' nature of some LLMs might also pose challenges for full transparency.

Student Guide (IB Design Technology)

Simple Explanation: Using AI like ChatGPT (which is an LLM) can help you use methods like TRIZ more easily for your design projects, making it faster to come up with creative ideas.

Why This Matters: This research shows how technology can help designers be more innovative by making complex problem-solving tools more accessible and efficient.

Critical Thinking: To what extent does relying on AI for ideation methods like TRIZ impact a designer's own creative development and critical thinking skills?

IA-Ready Paragraph: The integration of Large Language Models (LLMs) with established innovation methodologies, such as TRIZ, presents a significant advancement in design practice. Research by Jiang et al. (2025) demonstrates how systems like AutoTRIZ can automate the complex TRIZ process, making inventive problem-solving more accessible and efficient for designers. This AI-driven approach has the potential to accelerate the generation of novel solutions and broaden the scope of ideation by leveraging the vast knowledge and reasoning capabilities of LLMs.

Project Tips

• Consider using AI tools to help you understand and apply complex design methodologies like TRIZ.
• Document how the AI assisted in your ideation process and critically evaluate its suggestions.

How to Use in IA

• Reference this study when discussing the use of AI tools to support ideation or the application of innovation methodologies in your design project.

Examiner Tips

• When discussing ideation, consider the role of AI tools in augmenting human creativity and the potential benefits and drawbacks.

Independent Variable: Integration of LLMs with TRIZ.

Dependent Variable: Effectiveness and efficiency of engineering innovation (e.g., quality of solutions, time taken).

Controlled Variables: Complexity of the problem statement, specific TRIZ principles applied, LLM used.

Strengths

• Novel integration of LLMs with a well-established innovation methodology.
• Demonstrated effectiveness through comparative experiments and a real-world case study.

Critical Questions

• How can the interpretability of LLM-generated solutions be improved?
• What are the long-term implications of AI-driven innovation on the role of human designers?

Extended Essay Application

• An Extended Essay could explore the comparative effectiveness of different LLMs in automating specific TRIZ tools or investigate the potential for AI to automate other complex design methodologies.

Source

AutoTRIZ: Automating engineering innovation with TRIZ and large language models · Advanced Engineering Informatics · 2025 · 10.1016/j.aei.2025.103312