AutoTRIZ: Automating Engineering Innovation with TRIZ and Large Language Models

TL;DR

This work addresses the practicality gap of the Theory of Inventive Problem Solving (TRIZ) by automating its reasoning with Large Language Models (LLMs) in a controlled, interpretable framework called AutoTRIZ. It presents a four-module TRIZ workflow anchored by a fixed internal knowledge base (39 engineering parameters, 39 contradictions, 40 inventive principles) and ground-truth-like prompts to guide LLM reasoning, yielding a structured, LaTeX-formatted solution report. The authors validate AutoTRIZ with textbook cases and a Battery Thermal Management System (BTMS) case, showing AutoTRIZ can align with human reasoning while delivering multiple inventive directions and concrete design options, including a novel flat heat pipe BTMS (FHP-BTMS) with quantified performance gains. This approach reduces the entry barrier to TRIZ, enables end-to-end AI-driven ideation with interpretability, and can be extended to other knowledge-based ideation methods, potentially accelerating AI-assisted engineering design across domains.

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.

Figures (12)

• Figure 1: Four steps for problem-solving using TRIZ
• Figure 2: The framework of AutoTRIZ
• Figure 3: AutoTRIZ web-based tool
• Figure 4: Experimental results about contradiction detection
• Figure 5: The AutoTRIZ-generated solution report for the problem of metal shot transport in plastic piping