AI审图技术在核电工业消防审查中的应用

张轩铭; 彭科夫; 张荷花

doi:10.16670/j.cnki.cn11-5823/tu.2023.03.02

2023, 15(3): 7-12. doi: 10.16670/j.cnki.cn11-5823/tu.2023.03.02

AI审图技术在核电工业消防审查中的应用

1.	清华大学软件学院, 北京 100084
2.	中核国电漳州能源有限公司, 漳州 363300
3.	北京信息科学与技术国家研究中心, 北京 100084

通讯作者: 彭科夫,

网络出版日期: 2023-06-30

作者简介: 张轩铭(1996-)，男，在读硕士研究生，主要研究方向：AI审图、深度学习技术

基金项目: 国家重点研发计划项目 2018YFB1700400

Application of AI Drawing Review Technology in Nuclear Power Industry Fire Protection Review

Xuanming Zhang ^1,, Kefu Peng ^2,,, Hehua Zhang ^1,3,

1.	School of Software, Tsinghua University, Beijing 100084, China
2.	CNNP Guodian Zhangzhou Energy Co., Ltd., Zhangzhou 363300, China
3.	BNRist, Beijing 100084, China

Corresponding author: Kefu Peng,

Available Online: 2023-06-30

引用本文: 张轩铭, 彭科夫, 张荷花. AI审图技术在核电工业消防审查中的应用[J]. 土木建筑工程信息技术, 2023, 15(3): 7-12. doi: 10.16670/j.cnki.cn11-5823/tu.2023.03.02

Citation: Xuanming Zhang, Kefu Peng, Hehua Zhang. Application of AI Drawing Review Technology in Nuclear Power Industry Fire Protection Review[J]. Journal of Information Technologyin Civil Engineering and Architecture, 2023, 15(3): 7-12. doi: 10.16670/j.cnki.cn11-5823/tu.2023.03.02

摘要:本文结合清华大学与中核集团在AI审图技术赋能核电消防安全方面的研究成果，阐述“图智”系统及其在核电工业消防审查中的应用实践。实践表明，AI审图技术能够有效应用于工业厂房、仓库等现实PDF施工图，帮助发现违反国家防火规范强条的消防安全问题。AI审图技术在审查全面性、客观性、一致性和行业知识固化重用等方面具有显著优势。本文介绍的AI审图技术及在核电工业的创新应用能够为后续更多智能产业应用提供一些参考借鉴。

关键词: AI审图, 智能审核, 核电消防, 工业建筑

Abstract: With the rapid development of artificial intelligence technology in recent years, AI drawing review technology has received extensive attention in the industry. This paper combines the research results of Tsinghua University and China National Nuclear Corporation on AI drawing review technology to empower nuclear power fire safety, and expounds the "TuZhi" system and its application practice in fire protection review in nuclear power industry. Practice in this paper has shown that AI drawing review technology can be effectively applied to actual PDF construction drawings such as industrial plants and warehouses, which helps find fire safety problems that violate the provisions of national fire protection regulations. AI drawing review technology has significant advantages in comprehensive, objective, and consistent reviewing, as well as its solidification and reuse of industry knowledge. The AI drawing review technology and its innovative application in the nuclear power industry introduced in this paper would provide a reference for the subsequent applications in smart industry.

Key words: AI Drawing Review, Intelligent Review, Nuclear Power Fire Protection, Industrial Buildings

[1]	蔡雨玺. 核电厂防火设计进展分析[J]. 今日消防, 2020, 5(12): 34-35.
[2]	张荷花, 顾明. BIM模型智能检查工具研究与应用[J]. 土木建筑工程信息技术, 2018, 10(2): 1-6.
[3]	张荷花, 顾明. BIM模型智能检查工具在审查平台及消防审查中的应用[J]. 土木建筑工程信息技术, 2021, 13(1): 1-7.
[4]	Ren S, He K, Girshick R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6): 1137-1149.
[5]	Han J, Ding J, Xue N, et al. Redet: A rotation-equivariant detector for aerial object detection[C]//In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2021: 2786-2795.
[6]	Xiao B, Wu H, Wei Y. Simple baselines for human pose estimation and tracking[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 466-481.
[7]	高铭, 张荷花, 张庭瑞, 等. 基于深度学习的公共建筑像素施工图空间识别[J]. 图学学报, 2022, 43(2): 189- 196.
[8]	Du Y, Li C, Guo R, et al. Pp-ocr: A practical ultra lightweight ocr system[J]. arXiv preprint arXiv: 2009.09941, 2020.
[9]	中华人民共和国住房和城乡建设部. 住房城乡建设部关于发布国家标准《建筑设计防火规范》局部修订的公告[EB/OL]. (2018-05-09)[2022-04-12]. https://www.mohurd.gov.cn/gongkai/zhengce/zhengcefilelib/201805/20180509_235971.html
[10]	孙家广, 顾明, 刘玉身, 等. GB/T 36456.3-2018面向工程领域的共享信息模型第3部分: 测试方法[S]. 北京: 中国国家标准化管理委员会, 2018.

AI审图技术在核电工业消防审查中的应用

Application of AI Drawing Review Technology in Nuclear Power Industry Fire Protection Review

计量

作者相关

关键词相关

Figures And Tables