Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
121 tokens/sec
GPT-4o
9 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

AutoTRIZ: Automating Engineering Innovation with TRIZ and Large Language Models (2403.13002v4)

Published 13 Mar 2024 in cs.HC, cs.AI, and cs.CL

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 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. F Zwicky. The morphological approach to discovery, invention, research and construction. New Methods of Thought and Procedure, pages 273–297, 1967.
  2. From brainstorming to c-sketch to principles of historical innovators: ideation techniques to enhance student creativity. Journal of STEM Education: Innovations and Research, 13, 2012.
  3. Computer-aided mind map generation via crowdsourcing and machine learning. Research in Engineering Design, 31:383–409, 2020.
  4. Genrikh Saulovich Altshuller. The innovation algorithm: TRIZ, systematic innovation and technical creativity. Technical innovation center Inc., 1999.
  5. Computer-aided analysis of patents and search for triz contradictions. International Journal of Product Development, 4:52–67, 2007.
  6. Triz mapping and novelty detection of engineering design patents using machine learning. International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, 86267:V006T06A044, 2022.
  7. Patriz: A framework for mining triz contradictions in patents. Expert Systems with Applications, 207:117942, 2022.
  8. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023.
  9. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023.
  10. Emergent abilities of large language models. Transactions on Machine Learning Research, 2022.
  11. Large language models encode clinical knowledge. Nature, pages 1–9, 2023.
  12. Autonomous chemical research with large language models. Nature, 624:570–578, 2023.
  13. Mathematical discoveries from program search with large language models. Nature, 625:468–475, 2024.
  14. How can large language models help humans in design and manufacturing? arXiv preprint arXiv:2307.14377, 2023.
  15. From concept to manufacturing: Evaluating vision-language models for engineering design. arXiv preprint arXiv:2311.12668, 2023.
  16. A task-decomposed ai-aided approach for generative conceptual design. International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, 87349:V006T06A009, 2023a.
  17. Attribute-sentiment-guided summarization of user opinions from online reviews. Journal of Mechanical Design, 145:41402, 2023.
  18. Biologically inspired design concept generation using generative pre-trained transformers. Journal of Mechanical Design, 145:41409, 2023.
  19. Generative transformers for design concept generation. Journal of Computing and Information Science in Engineering, 23:41003, 2023.
  20. Triz industrial case studies: a critical survey. Procedia Cirp, 39:51–56, 2016.
  21. How to achieve competitive excellence using triz. NW: Taylor&Francis Group, 2008.
  22. A framework for automatic triz level of invention estimation of patents using natural language processing, knowledge-transfer and patent citation metrics. Computer-aided design, 44:987–1010, 2012.
  23. Automatic extraction of inventive information out of patent texts in support of manufacturing design studies using natural languages processing. Journal of Intelligent Manufacturing, 34:2495–2509, 2023.
  24. Jianxi Luo. Data-driven innovation : What is it ? IEEE Transactions on Engineering Management, pages 1–19, 2022.
  25. Patent data for engineering design: A critical review and future directions. Journal of Computing and Information Science in Engineering, 22:060902, 2022a.
  26. Utilizing chatgpt to assist cad design for microfluidic devices. Lab on a Chip, 23:3778–3784, 2023.
  27. How can llms transform the robotic design process? Nature Machine Intelligence, pages 1–4, 2023.
  28. Using llms to customize the ui of webpages. Adjunct Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–3, 2023.
  29. Document understanding-based design support: Application of language model for design knowledge extraction. Journal of Mechanical Design, 145:121401, 2023.
  30. Fluid transformers and creative analogies: Exploring large language models’ capacity for augmenting cross-domain analogical creativity. Proceedings of the 15th Conference on Creativity and Cognition, pages 489–505, 2023.
  31. Causalmapper: Challenging designers to think in systems with causal maps and large language model. Proceedings of the 15th Conference on Creativity and Cognition, pages 325–329, 2023.
  32. Struc-bench: Are large language models really good at generating complex structured data? arXiv preprint arXiv:2309.08963, 2023.
  33. Peter Childs. Mechanical design engineering handbook. Butterworth-Heinemann, 2013.
  34. Michael A Orloff. Inventive thinking through TRIZ: a practical guide. Springer Berlin, Heidelberg, 2006.
  35. Michael A Orloff. Modern TRIZ: A practical course with easytriz technology. Springer Science & Business Media, 2012.
  36. Semyon D Savransky. Engineering of creativity: Introduction to TRIZ methodology of inventive problem solving. CRC press, 2000.
  37. Innovation on demand: new product development using TRIZ. Cambridge University Press, 2005.
  38. Self-consistency improves chain of thought reasoning in language models. The Eleventh International Conference on Learning Representations, 5 2023b.
  39. A review of triz, and its benefits and challenges in practice. Technovation, 33:30–37, 2013.
  40. Evidence-based design heuristics for idea generation. Design Studies, 46:95–124, 2016. ISSN 0142694X. doi:10.1016/j.destud.2016.05.001.
  41. Design heuristics in engineering concept generation. Journal of Engineering Education, 101:602–628, 2012.
  42. Bob Eberle. Scamper on: Games for imagination development. Prufrock Press Inc., 1996.
  43. IDEO. IDEO method cards: 51 ways to inspire design. William Stout, 2003.
  44. Bio-inspired design: An overview investigating open questions from the broader field of design-by-analogy. ASME Journal of Mechanical Design, 136:111102, 11 2014. ISSN 1050-0472. doi:10.1115/1.4028289.
  45. Data-driven design-by-analogy: State-of-the-art and future directions. ASME Journal of Mechanical Design, 144:020801, 2022b.
  46. Function based design-by-analogy: a functional vector approach to analogical search. ASME Journal of Mechanical Design, 136(10):101102, 2014.
  47. Analogies and metaphors in creative design. International Journal of Engineering Education, 24(2):283, 2008.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now