大语言模型支持的输变电工程BIM三维设计专家系统

齐立忠; 荣经国; 张苏; 何幸; 李翔中

PDF(832 KB)

电力建设 ›› 0

大语言模型支持的输变电工程BIM三维设计专家系统

齐立忠¹, 荣经国¹, 张苏¹, 何幸², 李翔中²

作者信息 +

Expert System for BIM 3D Design in Power Transmission and Transformation Engineering Supported by Large Language Model

QI Lizhong¹, RONG Jingguo¹, ZHANG Su¹, HE Xin², LI Xiangzhong²

Author information +

文章历史 +

摘要

【目的】针对输变电工程三维设计中传统工具规范整合不足、设计验证效率低等问题,探索建筑信息模型（building information modeling,BIM）与大语言模型协同机制,构建智能化设计辅助系统以提升规范动态映射与知识服务能力。【方法】提出大语言模型赋能的BIM三维设计专家系统：1）基于Qwen2.5模型解析输变电工程规范,提取三元组结构,构建知识图谱;2）开发混合检索框架动态映射BIM构件属性与知识实体,结合向量知识库增强语义匹配;3）集成检索增强生成(retrieval augmented generation,RAG)技术构建问答系统,通过BIMbase平台实现三维模型与规范数据的智能交互。【结果】徐州变电站应用表明：1）知识图谱三元组提取准确率达92%;2）BIM构件规范映射覆盖率达85%;3）问答系统响应时间为1.45 s,专业解答准确率达91%（较基线提升32.8%）。【结论】建立了BIM与大语言模型动态协同机制,验证了知识图谱增强检索在电力工程设计中的有效性。该系统通过规范-模型双向映射与智能问答显著提升了设计质量,为智能电网提供了可扩展技术范式。

Abstract

[Objective] To address the issues of insufficient integration of traditional tool specifications and low efficiency in design validation within 3D design for power transmission and transformation projects, this study explores the collaborative mechanism between BIM and large language models to construct an intelligent design assistance system that enhances dynamic specification mapping and knowledge service capabilities. [Methods] A large language model-powered BIM 3D design expert system is proposed: 1) The Qwen2.5 model is used to parse specifications of power transmission and transformation projects, extract triplet structures, and build a knowledge graph; 2) A hybrid retrieval framework is developed to dynamically map BIM component attributes with knowledge entities, enhanced by vector-based knowledge databases for improved semantic matching; 3) RAG technology is integrated to build a question-answering system, enabling intelligent interaction between 3D models and specification data via the BIMbase platform. [Results] Application at the Xuzhou substation demonstrates: 1) Knowledge graph triplet extraction accuracy reaches 92%; 2) Coverage rate of BIM component-to-specification mapping achieves 85%; 3) The question-answering system has a response time of 1.5 seconds, with professional answer accuracy at 94% (a 31.2% improvement over the baseline). [Conclusion] This study innovatively establishes a dynamic collaboration mechanism between BIM and large language models, validating the effectiveness of knowledge graph-enhanced retrieval in power engineering design. Through bidirectional mapping between specifications and models and intelligent question-answering, the system significantly improves design quality, providing a scalable technical paradigm for smart grids.

导出引用

齐立忠, 荣经国, 张苏, 何幸, 李翔中. 大语言模型支持的输变电工程BIM三维设计专家系统[J]. 电力建设. 0

QI Lizhong, RONG Jingguo, ZHANG Su, HE Xin, LI Xiangzhong. Expert System for BIM 3D Design in Power Transmission and Transformation Engineering Supported by Large Language Model[J]. Electric Power Construction. 0

中图分类号： TM743

参考文献

[1] 周圣栋, 解蕾, 宋若晨, 等. 基于BIM的变电站数字化建设管控平台构建及应用[J]. 中国电力, 2019, 52(5): 142-147.
ZHOU Shengdong, XIE Lei, SONG Ruochen, et al.Building and application of substation digital construction management platform based on BIM[J]. Electric Power, 2019, 52(5): 142-147.
[2] 官澜, 李奥森, 韩念遐, 等. 基于数字化三维模型的架空输电线路设计[J]. 电测与仪表, 2020, 57(3): 105-109.
GUAN Lan, LI Aosen, HAN Nianxia, et al.Design of overhead transmission lines based on digital three-dimensional model[J]. Electrical Measurement & Instrumentation, 2020, 57(3): 105-109.
[3] 同嘉. 基于BIM全景可视化的架空电力线磁场三维仿真计算研究[J]. 高压电器, 2020, 56(3): 169-175.
TONG Jia.Study of overhead power line magnetic field 3D simulation caculation based on BIM panoramic visualization[J]. High Voltage Apparatus, 2020, 56(3): 169-175.
[4] 张广平, 何世洋, 任鹏飞, 等. BIM技术在750千伏变电站设计的应用[J]. 建筑结构, 2021, 51(S1): 1234-1238.
ZHANG Guangping, HE Shiyang, REN Pengfei, et al.Application of BIM technology in the design of 750 kV substation[J]. Building Structure, 2021, 51(S1): 1234-1238.
[5] MAJUMDER S, DONG L, DOUDI F, et al.Exploring the capabilities and limitations of large language models in the electric energy sector[J]. Joule, 2024, 8(6): 1544-1549.
[6] 齐立忠, 刘定, 张卓群, 等. 基于BIM技术的特高压工程数字化建设综述[J]. 电力建设, 2025, 46(2): 61-73.
QI Lizhong, LIU Ding, ZHANG Zhuoqun, et al.Review of digital construction of UHV projects based on building information modeling technology[J]. Electric Power Construction, 2025, 46(2): 61-73.
[7] 王兴华, 王彦峰, 雷翔胜, 等. 电气设备在BIM与GIS中的几何与语义一致性[J]. 南方电网技术, 2022, 16(12): 29-37.
WANG Xinghua, WANG Yanfeng, LEI Xiangsheng, et al.Congruent mapping between BIM and GIS for geometric and semantic informatiom of electrical device[J]. Southern Power System Technology, 2022, 16(12): 29-37.
[8] 周亮, 蔡钧, 丁一波, 等. 基于IFC的输变电工程三维数字化管理平台研究[J]. 电网与清洁能源, 2015, 31(11): 7-12.
ZHOU Liang, CAI Jun, DING Yibo, et al.Research on 3D digital management platform of power transmission construction project based on IFC[J]. Power System and Clean Energy, 2015, 31(11): 7-12.
[9] 李燕, 郭嘉成, 冯笑峰, 等. 智慧基建背景下基于BIM技术的输变电工程全生命周期造价管理研究[J]. 建筑经济, 2022, 43(10): 58-65.
LI Yan, GUO Jiacheng, FENG Xiaofeng, et al.Research on life cycle cost management of power transmission and transformation projects based on BIM technology under the background of smart infrastructure[J]. Construction Economy, 2022, 43(10): 58-65.
[10] 杜春宇, 周亮, 陈培智, 等. 基于BIM的输变电工程自动算量分析研究[J]. 建筑经济, 2020, 41(10): 64-68.
DU Chunyu, ZHOU Liang, CHEN Peizhi, et al.Research on BIM based automatic statistics analysis of engineering quantity of power transmission and transformation project[J]. Construction Economy, 2020, 41(10): 64-68.
[11] 任春光, 孟长虹, 史卓鹏, 等. 智能变电站施工控制的三维可视化系统研究和设计[J]. 制造业自动化, 2023, 45(9): 79-83.
REN Chunguang, MENG Changhong, SHI Zhuopeng, et al.Research and implementation of 3D visualization system based on intelligent power station construction control[J]. Manufacturing Automation, 2023, 45(9): 79-83.
[12] JIANG Q, LIU Y D, YAN Y J, et al.BIM-based 3-D multimodal reconstruction for substation equipment inspection images[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 5031714.
[13] LOGGIA R, FLAMINI A.Electrical safety enhanced with BIM, SCADA and digital twin integration: a case study of a MV-LV substation[J]. IEEE Transactions on Industry Applications, 2024, 60(2): 2725-2731.
[14] 徐涛, 邹泽华, 胡仁焱, 等. 基于BiGRU+CRF深度学习模型的水电站调度运行知识图谱构建方法[J]. 电力科学与技术学报, 2025, 40(1): 180-189.
XU Tao, ZOU Zehua, HU Renyan, et al.A construction method of dispatching operation knowledge graph of hydro power stations based on BiGRU + CRF deep learning model[J]. Journal of Electric Power Science and Technology, 2025, 40(1): 180-189.
[15] LEE J, AHN S, KIM D, et al.Performance comparison of retrieval-augmented generation and fine-tuned large language models for construction safety management knowledge retrieval[J]. Automation in Construction, 2024, 168: 105846.
[16] 覃思中, 郑哲, 顾燚, 等. 大语言模型在建筑工程中的应用测试与讨论[J]. 工业建筑, 2023, 53(9): 162-169.
QIN Sizhong, ZHENG Zhe, GU Yi, et al.Exploring and discussion on the application of large language models in construction engineering[J]. Industrial Construction, 2023, 53(9): 162-169.
[17] 姜文明, 齐立忠, 张苏, 等. 基于知识图谱的电网工程建筑信息模型质量检查方法[J]. 吉林大学学报(工学版), 2024, 54(3): 807-814.
JIANG Wenming, QI Lizhong, ZHANG Su, et al.Quality inspection method of electric power engineering building information model based on knowledge graph[J]. Journal of Jilin University (Engineering and Technology Edition), 2024, 54(3): 807-814.
[18] 肖发龙, 吴岳忠, 沈雪豪, 等. 基于深度学习和知识图谱的变电站设备故障智能诊断[J]. 电力建设, 2022, 43(3): 66-74.
XIAO Falong, WU Yuezhong, SHEN Xuehao, et al.Intelligent fault diagnosis of substation equipment on the basis of deep learning and knowledge graph[J]. Electric Power Construction, 2022, 43(3): 66-74.
[19] 田雪涵, 董坤, 赵剑锋, 等. 基于增强优化预训练语言模型的电力数据实体识别方法[J]. 智慧电力, 2024, 52(6): 100-107.
TIAN Xuehan, DONG Kun, ZHAO Jianfeng, et al.Entity recognition method for power data based on enhanced optimization pre-trained language model[J]. Smart Power, 2024, 52(6): 100-107.
[20] 王合庆, 魏杰, 景红雨, 等. Meta-RAG: 基于元数据驱动的电力领域检索增强生成框架[J/OL]. 计算机工程, 2024: 1-11. 2024.(2024-12-25)[2025-04-23]. https://doi.org/10.19678/j.issn.1000-3428.0070415.
WANG Heqing, WEI Jie, JING Hongyu, et al. Meta-RAG: metadata-driven enhanced generation framework for power domain retrieval[J/OL]. Computer Engineering, 2024:1-11.(2024-12-25)[2025-04-23]. https://doi.org/10.19678/j.issn.1000-3428.0070415.
[21] 马超, 李武峰, 陈羽飞, 等. Chat GPT类大语言模型赋能电力标准数字化转型的核心技术、技术特征及应用展望[J]. 高电压技术, 2025, 51(4): 1727-1746.
MA Chao, LI Wufeng, CHEN Yufei, et al.Core technologies, technical characteristics, and application prospects of ChatGPT class big language models on the digital transformation of standards in electric power field[J]. High Voltage Engineering, 2025, 51(4): 1727-1746.
[22] 李莉, 时榕良, 郭旭, 等. 融合大模型与图神经网络的电力设备缺陷诊断[J]. 计算机科学与探索, 2024, 18(10): 2643-2655.
LI Li, SHI Rongliang, GUO Xu, et al.Diagnosis of power system defects by large language models and graph neural networks[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(10): 2643-2655.
[23] 曹祎, 张莉, 郭静, 等. 基于大语言模型的低碳电力市场发展应用前景[J]. 智慧电力, 2024, 52(2): 8-16.
CAO Yi, ZHANG Li, GUO Jing, et al.Prospects for development of low-carbon electricity markets based on large language models[J]. Smart Power, 2024, 52(2): 8-16.
[24] 牛泽原, 李嘉媚, 艾芊. 大语言模型在电力系统中的应用初探[J]. 电网技术, 2025, 49(4): 1327-1336.
NIU Zeyuan, LI Jiamei, AI Qian.Preliminary exploration of the application of large language models in power systems[J]. Power System Technology, 2025, 49(4): 1327-1336.
[25] 贾震江, 刘宇穗. 协同、三维设计技术在数字化电厂建设中的应用[J]. 电力建设, 2011, 32(4): 83-86.
JIA Zhenjiang, LIU Yusui.Application of collaborative 3D design in digitalized power plant[J]. Electric Power Construction, 2011, 32(4): 83-86.
[26] 胡君慧, 盛大凯, 郄鑫, 等. 构建数字化设计体系, 引领电网建设发展方向[J]. 电力建设, 2012, 33(12): 1-5.
HU Junhui, SHENG Dakai, QIE Xin, et al.Establishment of digital design system of power transmission & transformation project for power grid construction and development[J]. Electric Power Construction, 2012, 33(12): 1-5.
[27] 韩文军, 王庭华, 彭晶, 等. 输变电工程数据管理技术标准体系框架研究[J]. 科技管理研究, 2018, 38(22): 224-229.
HAN Wenjun, WANG Tinghua, PENG Jing, et al.Research on standard system framework of power transmission and distribution project data management technology[J]. Science and Technology Management Research, 2018, 38(22): 224-229.
[28] 输变电工程数据移交规范: GB/T 38436—2019[S]. 北京: 中国标准出版社, 2019.
Engineering data handover specification for power transmission and transformation: GB/T 38436—2019[S]. Beijing: Standards Press of China, 2019.
[29] 任海玉, 刘建平, 王健, 等. 基于大语言模型的智能问答系统研究综述[J]. 计算机工程与应用, 2025, 61(7): 1-24.
REN Haiyu, LIU Jianping, WANG Jian, et al.Research on intelligent question answering system based on large language model[J]. Computer Engineering and Applications, 2025, 61(7): 1-24.
[30] 王思丽, 李慧佳, 孟庆洪, 等. 基于深度学习模型的领域知识库语义检索服务实现研究[J]. 图书馆学研究, 2024(10): 40-49.
WANG Sili, LI Huijia, MENG Qinghong, et al.Research on the implementation of semantic retrieval service for domain knowledge base based on deep learning model[J]. Research on Library Science, 2024(10): 40-49.
[31] 王帅, 何文春, 王甫棣, 等. 大语言模型融合知识图谱与向量检索的问答系统[J]. 科学技术与工程, 2024, 24(32): 13902-13910.
WANG Shuai, HE Wenchun, WANG Fudi, et al.Question answering system based on large language model integrating knowledge graph and vector retrieval[J]. Science Technology and Engineering, 2024, 24(32): 13902-13910.
[32] 黄立新, 马恩成, 张晓龙, 等. PKPM的“BIM数据中心及协同设计平台”[J]. 建筑科学, 2018, 34(9): 42-49, 129.
HUANG Lixin, MA Encheng, ZHANG Xiaolong, et al.PKPM BIM data center and collaborative design platform[J]. Building Science, 2018, 34(9): 42-49, 129.
[33] YANG A, YANG B S, ZHANG B C, et al. Qwen2.5 technical report[DB/OL]. (2024-12-09)[2025-04-29]. http://arxiv.org/abs/2412.15115.
[34] 电力规划设计总院. 输变电工程三维设计模型交互及建模规范: NB/T 11199—2023[S/OL]. (2023-05-26)[2025-01-29]. https://hbba.sacinfo.org.cn/stdDetail/4fd5f719c3fe7d98ff5a904344b104a4f06c6991f1e3cee101d33cb52a9d2a6c.