为提高变压器有载分接开关机械振动信号特征提取的精度，针对K-means

To improve the accuracy of transformer load tap-tap vibration signals feature extraction, which is susceptible to the selected initial cluster centers for the K-means clustering effect, mechanical OLTC proposed based on K-means algorithm and locust combination condition monitoring methods.

In order to improve the precision of the transformer's mechanical vibration signal extraction with carrier tap switch, and for the K-means clustering effect to be susceptible to the influence of its initial clustering center selection, a method of OLTC mechanical state monitoring based on locust algorithm and K-means combined is proposed.

In order to improve the accuracy of feature extraction of mechanical vibration signal of transformer on load tap changer, this paper proposes an OLTC mechanical condition monitoring method based on locust algorithm and k-means.<br>