Research on GIL Mechanical Fault Detection System Based on Combined Vibration and Acoustic Location Technology

XU Aihua; ZANG Chunyan; LI Yishuo; HU Hongbo; XU Hao; XU Shengbo; GUO Hai

doi:10.13296/j.1001-1609.hva.2025.06.006

您当前的位置：

首页 >

文章列表页 >

Research on GIL Mechanical Fault Detection System Based on Combined Vibration and Acoustic Location Technology

Research & Analysis | 更新时间：2025-06-12

- Research on GIL Mechanical Fault Detection System Based on Combined Vibration and Acoustic Location Technology
- High Voltage Apparatus Vol. 61, Issue 6, Pages: 52-58(2025)
- 作者机构：
  
  1.湖北省计量测试技术研究院，武汉　 430223
  2.华中科技大学电气与电子工程学院，武汉　 430074
- 作者简介：
- 基金信息：
  
  Technology Plan Project of State Administration for Market Regulation(2022MK083)
- DOI：10.13296/j.1001-1609.hva.2025.06.006
  CLC：
- Received：28 November 2024，
  
  Revised：25 February 2025，
  
  Published：16 June 2025
- 稿件说明：
移动端阅览
XU Aihua, ZANG Chunyan, LI Yishuo, et al. Research on GIL Mechanical Fault Detection System Based on Combined Vibration and Acoustic Location Technology[J]. High voltage apparatus, 2025, 61(6): 52-58.
DOI：

XU Aihua, ZANG Chunyan, LI Yishuo, et al. Research on GIL Mechanical Fault Detection System Based on Combined Vibration and Acoustic Location Technology[J]. High voltage apparatus, 2025, 61(6): 52-58. DOI： 10.13296/j.1001-1609.hva.2025.06.006.

摘要

作为非电量检测手段，振动和噪声检测在电力设备故障诊断中因抗干扰能力强、准确度高等优点受到广泛关注。文中将振动和噪声检测技术联合引入气体绝缘金属输电管道GIL设备的机械故障检测与定位工作中，首先结合振动信号构建了一种GIL机械故障诊断模型，通过对试点GIL的上百组振动信号数据进行采集和时频域分析，然后采用海鸥优化算法（SOA）对传统向量机（SVM）进行了改进，构建了SOA-SVM训练数据集并取得了较好的效果，验证了该模型的有效性，最后结合噪声信号进行了GIL机械故障的定位研究，并设计开发了可视化的GIL机械故障检测系统，有望在未来得到推广应用。

Abstract

As a non-electrical detection means

vibration and noise detection has received extensive attention in the fault diagnosis of power equipment due to its strong anti-interference ability and high accuracy. In this paper

the vibration and noise technology is jointly introduced into the mechanical fault detection and location of gas-insulated metal transmission (GIL) equipment. Firstly

a GIL mechanical fault diagnosis model is constructed in combination with vibration signals. Hundreds of sets of vibration signal data of the GIL are collected and analyzed in the time and frequency domains. Then

the traditional vector machine (SVM) is improved by the seagull optimization algorithm (SOA). The SOA-SVM training data set is constructed and good results are achieved

which verifies the effectiveness of the model. Finally

the location of GIL mechanical faults is studied in combination with noise signals

and a visual GIL mechanical fault detection system is designed and developed

which is expected to be promoted and applied in the future.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Study of Transformer Fault Diagnosis and Location Based on Machine Learning and DGA

Support Vector Machine Load Modeling Parameter Identification Method Based on Leave-one-out Cross Validation Method

Green Digital Management and Early Warning Method for Power Grid Infrastructure Files Based on Improved PKCNN

Non-destructive Detection Method for Nuts Missing Defect on Anchor Bolts of Transmission Tower Based on INGO-SVM

Mechanical Defect Detection Method of High Voltage Circuit Breaker Based on Motion Trajectory Detection and Support Vector Machine

Related Author

ZHOU Guangyu

MA Songling

XING Chao

WANG Penglin

HE Xin

DENG Can

CHEN Ran

ZHOU Li

Related Institution

School of Mechanical and Electrical Engineering,Xi’an University of Architecture and Technology

Electric Power Research Institute of Yunnan Power Grid Co, Ltd

State Grid Hubei Economic Research Institute

Hubei Keneng Power Electronics Co., Ltd.

College of Electrical Engineering and New Energy, China Three Gorges University

⁰