摘要
准确评估电力变压器运行状态并及时发现电力变压器潜在故障,对于电力系统稳定运行具有十分重要的意义。随着人工智能、数据挖掘等前沿技术与电网的深度结合,对现有电力变压器状态评估中关键技术和问题进行归纳和讨论,着重探讨了现阶段变压器状态评估指标体系建立、数据处理方法和状态评估方法应用,有助于后续设备管理智能化、数字化等科研工作的开展。最后,从数据体量与质量、数据增强、小样本非均衡样本处理方法、多维数据应用、多源信息融合几方面展望了未来值得继续深入研究的内容和方向。
The accurate assessment of power transformer operating status and the timely detection of the potential transformer faults are of great importance to the stable operation of power systems.Based on the in-depth combination of power grids and advanced techniques like artificial intelligence and data mining,the key technologies and problems in the existing condition assessment of the transformer are summarized and discussed,focusing on exploring the establishment of index system for the transformer condition assessment,a data processing method and the application of the condition assessment method at the current stage,which will help to carry out the subsequent scientific research on the intelligentization and digitization of equipment management.Finally,from the aspect of data volume and quality,data enhancement,the unbalanced sample processing methods of small sample,multidimensional data application and multi-source information fusion,the future content and directions deserving further research are pointed out.
作者
邓雯瀚
苗宇
许逵
熊炜
袁旭峰
DENG Wenhan;MIAO Yu;XU Kui;XIONG Wei;YUAN Xufeng(School of Electrical Engineering,Guizhou University,Guiyang 550025,China;Electric Power Research Institute of Guizhou Power Grid Co.,Ltd.,Guiyang 550025,China;Guizhou Power Supply Co.,Ltd.,Guiyang 550025,China)
出处
《智慧电力》
北大核心
2023年第10期93-102,共10页
Smart Power
基金
国家自然科学基金资助项目(52067004)。
关键词
电力变压器
状态评估
数据预处理
特征量提取
评估方法
power transformers
condition assessment
data preprocessing
feature extraction
assessment method
