AutoTRIZ: Automating Engineering Innovation with TRIZ and Large Language Models

2024-03-13

AI Summary

TRIZ adoption in engineering practice is hindered by its procedural complexity and heavy reliance on expert experience. Method: This paper introduces the first large language model (LLM)-driven automated TRIZ system, enabling end-to-end generation of structured solution reports from problem inputs. It integrates prompt engineering, multi-step reasoning chains, and structured encoding—along with dynamic invocation—of TRIZ tools (e.g., the contradiction matrix and the 40 Inventive Principles). Contribution/Results: The work pioneers deep coupling between TRIZ’s systematic methodology and LLMs, establishing an interpretable, generative, and extensible AI-augmented innovation paradigm. Crucially, it supports methodological transfer to other creativity frameworks (e.g., SCAMPER). Evaluated on textbook cases and a real-world battery thermal management system (BTMS) design task, the system outperforms baseline approaches, producing technically feasible, interpretable solutions—thereby validating an effective AI-enabled pathway for engineering innovation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Knowledge Representation and Reasoning: Automated Reasoning and Theorem Proving
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Various ideation methods, such as morphological analysis and design-by-analogy, have been developed to aid creative problem-solving and innovation. Among them, the Theory of Inventive Problem Solving (TRIZ) stands out as one of the best-known methods. However, the complexity of TRIZ and its reliance on users' knowledge, experience, and reasoning capabilities limit its practicality. To address this, we introduce AutoTRIZ, an artificial ideation system that integrates Large Language Models (LLMs) to automate and enhance the TRIZ methodology. By leveraging LLMs' vast pre-trained knowledge and advanced reasoning capabilities, AutoTRIZ offers a novel, generative, and interpretable approach to engineering innovation. AutoTRIZ takes a problem statement from the user as its initial input, automatically conduct the TRIZ reasoning process and generates a structured solution report. We demonstrate and evaluate the effectiveness of AutoTRIZ through comparative experiments with textbook cases and a real-world application in the design of a Battery Thermal Management System (BTMS). Moreover, the proposed LLM-based framework holds the potential for extension to automate other knowledge-based ideation methods, such as SCAMPER, Design Heuristics, and Design-by-Analogy, paving the way for a new era of AI-driven innovation tools.

Problem

• Automating TRIZ to overcome complexity and user dependency
• Enhancing engineering innovation with LLM-powered generative solutions
• Extending AI framework to automate knowledge-based ideation methods

Innovation

• Integrates LLMs to automate TRIZ methodology
• Generates structured solution reports from problem statements
• Extends framework to automate other ideation methods