AutoTRIZ: Automating engineering innovation with TRIZ and large language models
Year: 2025
Type: article
Abstract: Various engineering design ideation methods, such as morphological analysis and design-by-analogy, have been developed to aid creative problem-solving and innovation. Among these, the Theory of Inventive Problem Solving (TRIZ) stands out as one of the best-known innovation methods. However, the complexity of TRIZ and reliance on users' knowledge, experience, and reasoning capabilities limit its practicality. Therefore, we adopt Large Language Models (LLMs) to bridge this gap. This paper proposes AutoTRIZ, an artificial ideation system that uses LLMs to automate and enhance the TRIZ methodology. By leveraging LLMs’ extensive pre-trained knowledge and advanced reasoning capabilities, AutoTRIZ offers a novel approach to generative and interpretable engineering innovation. AutoTRIZ takes a problem statement from the user as its initial input and automatically generates a TRIZ solution report after the automatic reasoning process. This paper demonstrates and evaluates the effectiveness of AutoTRIZ through comparative experiments with textbook cases and a detailed real-world application to designing Battery Thermal Management System (BTMS). Moreover, the proposed LLM-based framework holds the potential for extension to automate other knowledge-based ideation methods, including SCAMPER, Design Heuristics, and Design-by-Analogy, paving the way for a new era of knowledge-based systems for design innovation.
Source: Advanced Engineering Informatics
Institutions: City University of Hong Kong, Tsinghua University
Language: English
Subfield: Mechanical Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $3,560
OpenAlex ID: W4409156407