首页> 外文会议>International Conference on Smart City and Systems Engineering >Research on a General Fast Analysis Algorithm Model for PD Acoustic Detection System: Experimental Research
【24h】

Research on a General Fast Analysis Algorithm Model for PD Acoustic Detection System: Experimental Research

机译:PD声学检测系统通用快速分析算法模型研究:实验研究

获取原文

摘要

Nowadays, the acoustic detection (AD) of partial discharge (PD) is widely used for defect diagnosis of gas insulated substations (GIS) in normal operation and factory tests, including the live detection, on-line monitoring, and offline tests etc. In this paper, in order to design and develop a general fast analysis algorithm model for PD acoustic detection (AD) system to make an assistant diagnosis, the characteristic of acoustic emission (AE) signals generated by different artificial defects such as protrusions (corona discharge), floating shield (floating discharge), void in spacer (inner discharge) and bouncing particles are investigated in the HV laboratory. Some meaningful parameters behind the detected AE signals are extracted and discussed with showing the discharge pattern of (Δ ti, qi) and (ti, qi) respectively, which are used to distinguish the background noise, PD phenomena or bouncing particles. The results show that the data generated from the discharge tests of the defect models can be used as a sample library for artificial intelligence learning, which can be processed to form a general intelligent analysis model algorithm for GIS PD acoustic detection.
机译:如今,局部放电(PD)的声音检测(AD)在正常运行和工厂测试中广泛用于气体绝缘变电站(GIS)的故障诊断,包括实时检测,在线监测和离线测试等。为了设计和开发用于PD声学检测(AD)系统的通用快速分析算法模型,以进行辅助诊断,该模型将由不同的人工缺陷(如突起(电晕放电))产生的声发射(AE)信号的特征,高压实验室研究了浮动护罩(浮动放电),垫片中的空隙(内部放电)和弹跳粒子。提取并讨论了检测到的AE信号背后的一些有意义的参数,并显示了(Δt i ,qi)和(t i q i ),分别用于区分背景噪音,局部放电现象或弹跳粒子。结果表明,缺陷模型的放电测试所产生的数据可以用作人工智能学习的样本库,可以对其进行处理,以形成用于GIS PD声学检测的通用智能分析模型算法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号