基于大数据的反应堆系统全生命周期智能检修方案研究  

Solution of Full-Life-Cycle Intelligent Maintenance of Nuclear Reactor System Based on Big Data

作　　者：万浩 王炳炎[1] 陈相羽 殷琪 蒲耀洲 李豪 WAN Hao;WANG Bingyan;CHEN Xiangyu;YIN Qi;PU Yaozhou;LI Hao(Science and Technology on Reactor System Design Technology Laboratory,Nuclear Power Institute of China,Chengdu 610041,China)

机构地区：[1]中国核动力研究设计院、核反应堆系统设计技术重点实验室,四川成都610041

出　　处：《机械》2023年第4期1-8,共8页Machinery

基　　金：国家自然科学基金(52175241)。

摘　　要：目前核反应堆换料检修耗时长,基于维修人员经验判断,存在缺陷识别不精确、数据零散、可追溯性低等不足,并且受个人主观影响较大。随着新一代技术的发展,如大数据、人工智能等,智能维护能够有效提高维护质量和效率。本文阐述分析了反应堆系统检修的现状和工业检修技术的进展,提出了基于大数据的反应堆系统全生命周期智能检修思路,研究了全生命周期检修数据标准、数据库构建、施工检修过程管理和智能检修方案等关键技术。以反应堆压力容器的主螺栓螺纹检修为例,提出了主螺栓螺纹检修的数据挖掘与智能决策支持技术路线、实施路径及其寿命预测,从而提高主螺栓螺纹检修过程的服务能力,有利于进一步保障核反应堆结构服役的安全性与可靠性。最后,针对智能检修技术在反应堆系统的加快推进提出了一些建议。Nuclear reactor refueling maintenance takes a long time at present.It is mostly based on experience,which causes problems such as inaccurate identification of defects,scattered data,and poor traceability,and it is greatly affected by subjective factors.With the development of new generation technologies,such as big data and artificial intelligence,the quality and efficiency of maintenance can be effectively improved.This paper described and analyzed the research status of reactor system maintenance and the progress of industrial maintenance technology.The solution of full-life-cycle intelligent maintenance of reactor system based on big data was put forward,and the key technologies,such as data standardization,database construction,maintenance progress management,and intelligent maintenance scheme,were studied.Taking the thread maintenance of the main bolt as an example,a data mining and intelligent decision support technology roadmap were proposed to improve the serviceability of the maintenance process,and to ensure the safety and reliability of the nuclear reactor in service.Finally,some suggestions were put forward for the promotion of intelligent maintenance in reactor system.

关 键 词：智能检修 大数据 全生命周期 决策支持 反应堆换料 

分 类 号：TL387[核科学技术—核技术及应用]