摘要
当前研究方法存在数据采集效率低、无法满足实际数据使用需求等问题,设计一种新的变压器非电量保护智能感知方法。通过四象限图法实施非电量保护数据采集优先等级的判别,以便针对不同数据采取不同的采集策略,对采集的非电量保护数据样本实施特征提取,搭建变压器非电量保护智能感知模型,在模型中输入提取变压器非电量保护数据特征,实现变压器非电量保护智能感知的目的,在现场实施设计方法的性能应用与案例分析,以测试该方法的性能。测试结果为该方法可以实现气体健康置信度与变压器故障率的准确、智能化感知,可以满足设计需求与实际使用需求。
The current research methods have some problems, such as low data acquisition efficiency and can not meet the needs of actual data.A new intelligent sensing method for transformer non-electric quantity protection is designed.The four-quadrant diagram method is used to determine the priority of non-electric quantity protection data acquisition, so as to adopt different acquisition strategies for different data, implement feature extraction for collected non-electric quantity protection data samples, build an intelligent sensing model for transformer non-electric quantity protection, input and extract the characteristics of transformer non-electric quantity protection data in the model, realize the purpose of intelligent sensing for transformer non-electric quantity protection, and implement the performance application and case analysis of the design method in the field to test the performance of the method.The test results show that this method can realize the accurate and intelligent perception of gas health confidence and transformer fault rate, and can meet the design and practical needs.
作者
林翔宇
王晓明
陈梁远
黎大健
彭博雅
Lin Xiangyu;Wang Xiaoming;Chen Liangyuan;Li Dajian;Peng Boya(Guangxi Key Laboratory of Intelligent Control and Maintenance of Power Equipment,Nanning 530000,China;Electric Power Research Institute of Guangxi Power Grid Co.,Ltd.,Nanning 530000,China)
出处
《能源与环保》
2023年第1期286-291,共6页
CHINA ENERGY AND ENVIRONMENTAL PROTECTION
基金
南方电网科技项目(GXKJXM20200449)。
关键词
变压器
非电量保护数据采集
智能感知
快速傅里叶变换
特征提取
transformer
non-electricity protection data collection
intelligent perception
fast Fourier transform
feature extraction
