网格
计算机科学
判别式
失真(音乐)
信号(编程语言)
橡树岭国家实验室
特征提取
签名(拓扑)
事件(粒子物理)
特征(语言学)
数据挖掘
人工智能
功能(生物学)
模式识别(心理学)
数学
电信
物理
带宽(计算)
几何学
程序设计语言
放大器
核物理学
哲学
语言学
生物
进化生物学
量子力学
作者
Ozgur Alaca,Ali Rıza Ekti,Aaron Wilson,John H. Holliman,Elizabeth Piersall,Serhan Yarkan,Nils Stenvig
标识
DOI:10.1109/tsg.2023.3309532
摘要
This study proposes a novel method for signal detection and feature extraction based on the spectral correlation function, enabling improved characterization of grid-signal distortions. Our approach differs from existing treatments of signal distortion in its analysis of the varied spectral content of signals observed in real-world scenarios. The method we propose has state-of-the-art discriminative power that provides meaningful and understandable characterizations of various grid events and anomalies. To validate the approach, we use real world data from the Grid Event Signature Library, which is maintained jointly by Oak Ridge National Laboratory and Lawrence Livermore National Laboratory.
科研通智能强力驱动
Strongly Powered by AbleSci AI