Materials & Design · 2024 · 14 citations · 20 references
ArchitectureComputer ScienceDesignHeat TransferProcess DesignSimulation-based DesignDialogue SystemsExpert SystemsKnowledge-based DesignKnowledge-based EngineeringProcess EngineeringProcess SimulationChatbotsComputer-aided EngineeringComputer-aided Engineering IntegrationHeat Treatment ModelingHeat Treatment OptimizationKnowledge-driven CadRetrieval-augmented GenerationSteel Heat Treatment
• Proposed a full-process paradigm for heat treatment process design based on LLMs. • Design a LLM integrating heat treatment knowledge, enabling knowledge transfer and process recommendation. • Proposed a framework using LLMs to simplify interactions between humans and finite element analysis software. • Proposed a evaluation system named SHTKU to evaluate the knowledge mastery capabilities of the heat treatment expert system. Heat treatment of steel is a multi-physics coupled process. Designing programs that meet the desired results is challenging. The current design of processes relies on experience and experimentation, leading to high costs in developing processes and challenges in training practitioners. To reduce research and development costs in the industry and enable novices to reach expert levels, we propose an intelligent heat treatment process design and simulation assistant system based on large language models (LLMs), named Chat-IMSHT. Chat-IMSHT can impart knowledge and recommend processes. Additionally, Chat-IMSHT optimizes the interaction between humans and Computer Aided Engineering (CAE) software. To achieve knowledge impartation and process recommendation, a dialogue model based on Retrieval Augmented Generation (RAG) and LLMs was designed. It characterizes and compresses a massive amount of heat treatment knowledge and process data. The system designs a new CAE software interaction paradigm, using LLMs to map parameters from natural language into formatted text for the CAE software COSMAP. A Steel Heat Treatment Knowledge Understanding (SHTKU) evaluation method was designed. The improved model significantly increased the accuracy of knowledge responses, with a maximum accuracy of 94.54 %. Experimental results show that Chat-IMSHT effectively imparts knowledge and generates formatted text, completing the task of process recommendation.
20
Training language models to follow instructions with human feedback
Long Ouyang, Jeff Wu, Xu Jiang et al. · arXiv (Cornell University) · 2022 · 4.3K citations · Full text
Materials discovery and design using machine learning
Yue Liu, Tianlu Zhao, Wangwei Ju et al. · Journal of Materiomics · 2017 · 1.2K citations · Full text
Natural Sciences, Materials Engineering, Materials Science +16
Autonomous chemical research with large language models
Daniil A. Boiko, Robert MacKnight, Ben Kline · Nature · 2023 · 810 citations · Full text
An autonomous laboratory for the accelerated synthesis of inorganic materials
Nathan J. Szymanski, Bernardus Rendy, Yuxing Fei et al. · Nature · 2023 · 806 citations · Full text
Natural Sciences, Materials Engineering, Materials Science +17
A GPT‐4 Reticular Chemist for Guiding MOF Discovery**
Zhiling Zheng, Zichao Rong, Nakul Rampal et al. · Angewandte Chemie International Edition · 2023 · 151 citations · Full text