基于信号包络与希尔伯特边际谱的高阻接地故障检测方法OA
High-impedance fault detection method based on signal envelope and Hilbert marginal spectrum
配电网高阻接地故障(HIF)信号具有失真性和随机性,故障特征微弱,难以被有效检测.为此,本文提出一种基于信号包络(SE)和希尔伯特边际谱(HMS)的HIF诊断方法.该方法对长时间尺度的零序电压提取SE和HMS,分别代表HIF的失真性和随机性特征.将这些特征转化为图像,利用ResNet18 实现对HIF的检测.该方法的有效性已在 10kV真型试验中得到验证,试验结果表明,该方法的HIF检测精度明显优于对比方法,尤其是在谐振接地系统中.
The diagnosis of high-impedance fault(HIF)is a critical challenge due to the presence of faint signals that exhibit distortion and randomness.In this study,a novel diagnostic approach for HIF based on the signal envelope(SE)and Hilbert marginal spectrum(HMS)is proposed.Longer timescale zero-sequence voltage is used to extract SE and HMS,representing HIF distortion and randomness characteristics.These features are transformed into images,and ResNet18 is employed to detect the presence of HIF.An industrial prototype of the proposed approach has been implemented and validated in a 10kV test system.The experimental results indicate that the proposed approach outperforms the comparison by a significant margin regarding detection accuracy,particularly in resonant distribution system.
李宽宏;林金树;江捷;朱少芬;肖中波
国网福建省电力有限公司泰宁县供电公司,福建 三明 365000国网福建省电力有限公司三明供电公司,福建 三明 365000
谐振接地系统高阻接地故障(HIF)故障检测深度学习信号包络(SE)希尔伯特边际谱(HMS)
resonant grounding systemhigh-impedance fault(HIF)fault detectiondeep learningsignal envelope(SE)Hilbert marginal spectrum(HMS)
《电气技术》 2024 (006)
39-46,55 / 9
国网福建省电力有限公司科技项目"具有增量学习功能的配电线路弧光接地故障人工智能识别方法研究"(521370230001)
评论