新一代人工智能在电力系统故障分析及定位中的研究综述  

A Research Review on Application of Artificial Intelligence in Power System Fault Analysis and Location

作　　者：和敬涵[1] 罗国敏[1] 程梦晓 刘艳梅 谭颖婕 李猛 HE Jinghan;LUO Guomin;CHENG Mengxiao;LIU Yanmei;TAN Yingjie;LI Meng(School of Electrical Engineering,Beijing Jiaotong University,Haidian District,Beijing 100044,China)

机构地区：[1]北京交通大学电气工程学院,北京市海淀区100044

出　　处：《中国电机工程学报》2020年第17期5506-5515,共10页Proceedings of the CSEE

基　　金：国家重点研发计划项目(2018YFB0904600);国家自然科学基金项目(51507008);国家电网公司科技项目(5200-201956113A-0-0-00)。

摘　　要：随着电力系统的不断发展,电力系统故障分析及定位面临数据规模庞大、故障机理复杂、建模需求多样化等问题。新一代人工智能技术在数据处理方面有较强的优势,如特征自学习、强非线性拟合、端到端建模等,为电力系统故障分析及定位的问题提供新思路。该文首先分析了电力系统新态势下,故障分析及定位面临的挑战和新一代人工智能技术应用的可行性。随后,对新一代人工智能技术在故障分析及定位中不同方面的应用情况进行了详细的综述,探讨了新一代人工智能技术在故障分析及定位的优势和存在问题的解决方式,并对未来发展进行了展望。With the development of the power grid,the fault analysis and location of power system has to face new challenges such as huge data,complicate fault characteristics,and difficult system design.The new generation of artificial intelligence(AI)which is good at feature learning,non-linear fitting and end-to-end modeling could provide alternative solutions for fault analysis and location.Based on the analysis of needs and rationalities of applying new generation AI in fault analysis and location,the application of new generation AI techniques was reviewed.Finally,their advantages and solutions for existing problems were discussed,and the possible development of new generation AI techniques in fault analysis and location was discussed.

关 键 词：故障分析及定位 新一代人工智能 故障识别 故障测距 故障定位 

分 类 号：TM77[电气工程—电力系统及自动化]