基于大语言模型与推理行为的滚动轴承设计智能体开发

钟研; 李扬; 卢泽华; 吴吉展; 刘怀举

doi:10.12382/bgxb.2025.0889

您当前的位置：

首页 >

文章列表页 >

基于大语言模型与推理行为的滚动轴承设计智能体开发

更新时间：2026-04-14

- 基于大语言模型与推理行为的滚动轴承设计智能体开发
- Study on Rolling Bearing Design Agent Based on Large Language Models with Reasoning and Acting
- 兵工学报 2026年
- 作者机构：
  
  重庆大学高端装备机械传动全国重点实验室,重庆,400044
- 作者简介：
- 基金信息：
  
  国家重点研发计划项目（2024YFB3410300）;科技创新平台项目（CXPT-2022-054）
- DOI：10.12382/bgxb.2025.0889
  中图分类号： TH133.33;TH122;TP182
- 收稿：2025-09-28，
  
  网络首发：2026-04-14，
- 稿件说明：
移动端阅览
钟研，李扬，卢泽华，等. 基于大语言模型与推理行为的滚动轴承设计智能体开发[J/OL]. 兵工学报, 2026(2026-04-14). https://doi.org/10.12382/bgxb.2025.0889.

ZHONG Y, LI Y, LU Z H, et al. Study on rolling bearing design agent based on large language models with reasoning and acting[J/OL]. Acta Armamentarii, 2026(2026-04-14). https://doi.org/10.12382/bgxb.2025.0889. (in Chinese)
钟研，李扬，卢泽华，等. 基于大语言模型与推理行为的滚动轴承设计智能体开发[J/OL]. 兵工学报, 2026(2026-04-14). https://doi.org/10.12382/bgxb.2025.0889. DOI：

ZHONG Y, LI Y, LU Z H, et al. Study on rolling bearing design agent based on large language models with reasoning and acting[J/OL]. Acta Armamentarii, 2026(2026-04-14). https://doi.org/10.12382/bgxb.2025.0889. (in Chinese) DOI：

摘要

滚动轴承是齿轮传动系统的关键基础部件，其设计和制造水平直接关系到航空发动机、风电齿轮箱等高端装备的服役性能和运行安全。当前，机械制造业正在经历从数字化、网络化向智能化发展的重要阶段，大语言模型（Large Language Models，LLM）技术的兴起为机械制造业智能化转型提供了全新可能。基于LLM语义理解和推理行为框架构建了滚动轴承设计智能体ChatBearing，实现了设计需求解析、受力分析、选型、寿命计算、强度校核、方案筛选和设计报告生成等专业任务的自主推理执行，并构建了面向生成式滚动轴承智能设计的多维度评价方法。以直升机尾部减速器、风电变桨齿轮箱和新能源汽车电驱系统中的滚动轴承为对象开展对比验证。研究结果表明：相比于常规人工设计，ChatBearing将设计时间从2~3h大幅缩短至3min以内，轴承总重量降低4%以上；相比Qwen3-235B-A22B和Gemini-2.5-Pro-0506LLM，ChatBearing在设计任务上的综合得分分别高出43.6%和21.1%。

Abstract

Rolling bearings are key components in gear transmissions

directly affecting the performance and safety of aero-engines

wind turbine gearboxes

and other advanced equipment. As mechanical manufacturing transitions toward intelligentization

large language models (LLM) offer new opportunities for this transformation. This study develops ChatBearing

an LLM-based rolling bearing design agent with reasoning and acting capabilities that autonomously performs tasks from requirement analysis to report generation

and establishes a multi-dimensional evaluation method. Validation on helicopter tail rotor gearboxes

wind turbine pitch gearboxes

and electric vehicle drivetrains demonstrates that ChatBearing reduces design time from 2~3 hours to under 3 minutes while decreasing bearing weight by over4%. ChatBearing also achieves 43.6% and 21.1% higher scores than Qwen3-235B-A22B and Gemini-2.5-Pro-0506 in design tasks

respectively.

关键词

Keywords

references

孔亚林. 基于振动信号的滚动轴承故障诊断方法研究 [D]. 大连:大连理工大学, 2006. KONG Y L. Research on fault diagnosis method and application for rolling element bearing based on vibration signal[D]. Dalian:Dalian University of Technology, 2006. (in Chinese)

路凯屹, 刘怀举, 廖常军, 等. 基于启发式算法的附件传动系统轻量化设计[J]. 航空动力学报, 2025, 40(4): 464-474. LU K Y, LIU H J, LIAO C J, et al. Lightweight design of accessory transmission based on heuristic algorithm[J]. Journal of Aerospace Power, 2025, 40(4): 464-474. (in Chinese)

刘桂源, 王曾, 杨子艺, 等. 航空发动机附件机匣齿轮传动设计分析软件开发与应用[J]. 中国机械工程, 2024, 35(11): 1938-1947. LIU G Y, WANG Z, YANG Z Y, et al. Development and applications of aero-engine accessory gearbox gear transmission design and analysis softwares[J]. China Mechanical Engineering, 2024, 35(11): 1938-1947. (in Chinese)

李泽东, 李志农, 陶俊勇, 等. 基于特征融合的注意力增强卷积神经网络的航空发动机滚动轴承故障诊断方法[J]. 兵工学报, 2022, 43(12): 3228-3239. LI Z D, LI Z N, TAO J Y, et al. Fault diagnosis for aero-engine rolling bearings based on an attention augmented convolutional neural network with featurefusion[J]. Acta Armamentarii, 2022, 43(12): 3228 -3239. (in Chinese)

尹晓伟, 江雪峰, 王龙福. 风电机组轴承故障诊断与疲劳寿命研究综述[J]. 轴承, 2022(5): 1-8. YIN X W, JIANG X F, WANG L F. Research review on fault diagnosis and fatigue life for wind turbine bearings[J]. Bearing, 2022(5): 1-8. (in Chinese)

WU J Z, CHEN K W, ZHANG P, et al. Effects of peening velocity and coverage on peen forming [J]. Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering, 2025, 239(3): 1523-1534.

李扬, 刘怀举, 魏沛堂, 等. 基于Monte-Carlo模拟的小样本下齿轮疲劳极限计算方法及软件开发[J]. 中国机械工程, 2023, 34(2): 185-192. LI Y, LIU H J, WEI P T, et al. Calculation method and software development of gear fatigue strength under small samples based on monte-carlo simulation[J]. China Mechanical Engineering, 2023, 34(2): 185-192. (in Chinese)

王东峰, 赵翀, 李超强, 等. 滚动轴承设计技术研究现状及发展趋势[J]. 轴承, 2023(5): 1-5, 12. WANG D F, ZHAO C, LI C Q, et al. Research status and development trends of design technology for rolling bearings[J]. Bearing, 2023(5): 1-5, 12. (in Chinese)

赵玉明, 贾现召, 李济顺, 等. 滚动轴承知识库系统研究[J]. 机床与液压, 2010, 38(6): 89-91, 112. ZHAO Y M, JIA X Z, LI J S, et al. Research on the knowledge base system of rolling bearings[J]. Machine Tool & Hydraulics, 2010, 38(6): 89-91, 112. (in Chinese)

孙恒建. 轴承设计专家系统及其关键技术的分析与实现[D]. 济南:山东大学, 2007. SUN H J. Analysis and implementation of bearing design expert system and key technology[D]. Jinan:Shandong University, 2007. (in Chinese)

梁文杰吴志军, 郁鼎文, 等. 滚动轴承工艺设计自动化研究[J]. 制造技术与机床, 2004(7): 93-95. LIANG W J, WU Z J, YU D W, et al. Research on process designing automation of bearing[J]. Manufacturing Technology & Machine Tool, 2004(7): 93-95. (in Chinese)

王黎钦, 崔立, 郑德志, 等. 球轴承-转子系统动特性的整体分析方法[J]. 哈尔滨工业大学学报, 2009, 41(5): 37-42. WANG L Q, CUI L, ZHENG D Z, et al. Integral analysis on dynamic characteristics of high-speed ball bearings and rotor system[J]. Journal of Harbin Institute of Technology, 2009, 41(5): 37-42. (in Chinese)

张建. 基于CATIA通用滚动轴承数字化设计系统开发[D]. 西安:西安工业大学, 2024. ZHANG J. Development of a digital design system for universal rolling bearings based on CATIA[D]. Xi'an: Xi'an Technological University, 2024. (in Chinese)

徐月梅, 胡玲, 赵佳艺, 等. 大语言模型的技术应用前景与风险挑战[J]. 计算机应用, 2024, 44(6): 1655-1662. XU Y M, HU L, ZHAO J Y, et al. Technology application prospects and risk challenges of large language models[J]. Journal of Computer Applications, 2024, 44(6): 1655-1662. (in Chinese)

何哲, 曾润喜, 秦维, 等. ChatGPT等新一代人工智能技术的社会影响及其治理[J]. 电子政务, 2023(4): 2-24. HE Z, ZENG R X, QIN W, et al. Social impacts of new generation AI technologies such as ChatGPT and their governance[J]. E-Government, 2023(4): 2-24. (in Chinese)

沈晨晨, 岳圣斌, 刘书隽, 等. 面向法律领域的大模型微调与应用[J]. 大数据, 2024, 10(5): 12-27. SHEN C C, YUE S B, LIU S J, et al. Fine-tuning and application of large language model in law domain[J]. Big Data Research, 2024, 10(5): 12-27. (in Chinese)

陈子佳, 彭文茜, 张德政, 等. 大语言模型在中医药领域的应用、挑战与前景[J]. 协和医学杂志, 2025, 16(1): 83-89. CHEN Z J, PENG W X, ZHANG D Z, et al. Application,challenges,and prospects of large language model in the field of traditional chinese medicine[J]. Medical Journal of Peking Union Medical College Hospital, 2025, 16(1): 83-89. (in Chinese)

贾鹏. 基于大语言模型的农业知识问答系统的研究与设计[D]. 秦皇岛:河北科技师范学院, 2024. JIA P. Research and design of agricultural knowledge Q&A system based on large language model[D]. Qinhuangdao:Hebei Normal University of Science and Technology, 2024. (in Chinese)

贾学法, 贾康, 陈恭. 光明大模型推动电力创新迸发新活力[J]. 河南电力, 2025(5): 60-63. JIA X F, JIA K, CHEN G. Bright large model to promote power innovation bursting with new vitality[J]. Henan Electric Power, 2025(5): 60-63. (in Chinese)

TAO L F, LIU H F, NING G A, et al. LLM-based framework for bearing fault diagnosis[J]. Mechanical Systems and Signal Processing, 2025, 224: 112127.

孔庆华, 徐世河, 李宗, 等. 滚动轴承选型专家系统的设计与实现[J]. 工程机械, 2003(11): 17-19, 85. KONG Q H, XU S H, LI Z, et al. Design and implementation of rolling bearing selection expert system[J]. Construction Machinery and Equipment, 2003(11): 17-19, 85. (in Chinese)

郭连湘, 何频, 李党索. 滚动轴承专家系统设计[J]. 机械设计与制造, 2005(8): 141-142. GUO L X, HE P, LI D S. Rolling-bearing expert system design[J]. Machinery Design & Manufacture, 2005(8): 141-142. (in Chinese)

张晓冬, 何频. 集成化圆锥滚子轴承 CAD 系统[J]. 机械与电子, 1997(5): 41-43. ZHANG X D, HE P. Integrated CAD system for tapered roller bearings[J]. Machinery & Electronics, 1997(5): 41-43. (in Chinese)

张鹤译, 王鑫, 韩立帆, 等. 大语言模型融合知识图谱的问答系统研究[J]. 计算机科学与探索, 2023, 17(10): 2377-2388. ZHANG H Y, WANG X, HAN L F, et al. Research on question answering system on joint of knowledge graph and large language models[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(10): 2377-2388. (in Chinese)

WANG L, MA C, FENG X Y, et al. A survey on large language model based autonomous agents[J]. Frontiers of Computer Science, 2024, 18(6): 186345.

ZHAO A, HUANG D, XU Q, et al. ExpeL: LLM agents are experiential learners[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(17): 19632-19642.

YUAN S, SONG K, CHEN J, et al. Easytool: enhancing llm-based agents with concise tool instruction[C]//Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies. Albuquerque, NM, US: Association for Computational Linguistics, 2024: 951–972.

李述兴. 大语言模型驱动的智能体应用与挑战[J]. 科技视界, 2024, 14(22): 67-70. LI S X. Applications and challenges of intelligentsia driven by large language models[J]. Science & Technology Vision, 2024, 14(22): 67-70. (in Chinese)

WU H Y, HE Z L, ZHANG X Y, et al. Chateda: a large language model powered autonomous agent for EDA[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2024, 43(10): 3184-3197.

QIN S Z, GUAN H, LIAO W J, et al. Intelligent design and optimization system for shear wall structures based on large language models and generative artificial intelligence[J]. Journal of Building Engineering, 2024, 95: 109996.

LI Y C, WEN H, WANG W J, et al. Personal LLM agents: insights and survey about the capability, efficiency and security: arXiv: 2401.05459 [R/OL]. Ithaca, NY, US:Cornell University, 2024. https://arxiv.org/abs/2401.05459.

王灵玉. 军用直升机战勤席位人机工效综合评价[J]. 直升机技术, 2024(1): 42-47,52.

WANG L Y. Ergonomics Comprehensive Evaluation of Military Helicopter Logistic Personnel Seat[J]. Helicopter Technique, 2024(1): 42-47, 52. (in Chinese)

于朋涛, 卓宏明, 施鑫煜. 航空应急救援目标区域需求权重优化研究[J]. 民航学报, 2024, 8(6):32-36, 138.

YU P T, ZHUO H M, SHI X Y. Research on optimization of demand weight of target area for aviation emergency rescue[J]. Journal of Civil Aviation, 2024, 8(6): 32-36, 138. (in Chinese)

刘胜新, 周超. 模拟训练系统中量化评估的重要性与实现方法[J]. 科技创新与应用, 2021, 11(35): 56-58, 62.

LIU S X, ZHOU C. Importance and implementation method of quantitative evaluation in simulation training system[J]. Technology Innovation and Application, 2021, 11(35): 56-58, 62. (in Chinese)

李丹丹, 王军见, 赵钦志, 等. 数控机床加工一致性评价方法研究[J]. 制造技术与机床, 2023(11): 116-122.

LI D D, WANG J J, ZHAO Q Z, et al. Research on Evaluation Method of Machining Consistency of CNC Machine Tools[J]. Manufacturing Technology & Machine Tool, 2023(11): 116-122. (in Chinese)

范岩旻, 车爱兰, 冯少孔. 基于模式匹配的网格扫描法在高铁线下结构检测中的应用[J]. 振动与冲击, 2019, 38(16): 159-165.

FAN Y M, CHE A L, FENG S K. Application of Grid scanning method based on pattern matching in detection of high-speed railway substructure[J]. Journal of Vibration and Shock, 2019, 38(16): 159-165. (in Chinese)

赵泓荀, 杨兆军, 陈传海, 等.考虑参数权重的数控机床电主轴加速试验优化设计[J]. 吉林大学学报（工学版）, 2022, 52(2): 409-416.

ZHAO H X, YANG Z J, CHEN C H, et al. Optimal design of accelerated test for CNC machine tool motorized spindle considering parameter weight[J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(2): 409-416. (in Chinese)

浏览量

下载量

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

MSCNN LSTM与改进注意力机制的轴承故障声发射识别

基于频域TCAE-Informer的滚动轴承剩余使用寿命预测方法

MSCNN_LSTM与改进注意力机制的轴承故障声发射识别