Acoustic emission (AE) technology can predict the occurrence of partial discharge (PD) faults, which is used to improve the safe operation level of gas-insulated switchgear (GIS) equipment. However, the strong noise interference from the production site is still the main factor affecting the identification accuracy. In this study, a simplified model is designed to approximate the accumulation of free metal particles on the surface of the GIS internal insulation structure, and white noise of various intensities is added to the collected PD-induced AE signals to simulate the background interference. The results prove that the proposed denoising method can achieve a better denoising effect in various signal-to-noise ratio (SNR) conditions. In particular, in the case of low SNR, the recognition accuracy of the accumulation degree of metal particles has been improved by more than 15%.

中文翻译：

---

局部放电检测中弱声发射信号的优化去噪方法

声发射（AE）技术可以预测局部放电（PD）故障的发生，用于提高气体绝缘开关设备（GIS）设备的安全运行水平。但是，来自生产现场的强噪声干扰仍然是影响识别精度的主要因素。在这项研究中，设计了一个简化模型来近似自由金属颗粒在 GIS 内绝缘结构表面的积累，并在收集到的 PD 引起的声发射信号中加入各种强度的白噪声来模拟背景干扰。结果证明，所提出的去噪方法在各种信噪比（SNR）条件下都能取得较好的去噪效果。特别是在低信噪比的情况下，