电力系统保护与控制2025，Vol.53Issue(8)：1-13,13.DOI:10.19783/j.cnki.pspc.240502
基于深度自适应K-means++算法的电抗器声纹聚类方法
Reactor voiceprint clustering method based on deep adaptive K-means++algorithm
摘要
Abstract
In high-voltage shunt reactor voiceprint signal monitoring systems,the high-dimensional non-stationarity of long-term,large-scale unlabeled voiceprint data make feature extraction difficult and reduce the adaptability of unsupervised clustering.To address this,a 750 kV reactor voiceprint clustering method based on deep adaptive K-means++clustering algorithm(DAKCA)is proposed.First,the improved stacked sparse autoencoder(SSAE),fine-tuned using a two-stage unsupervised strategy,is used to extract the 32-dimensional depth features from the normalized frequency domain data obtained via fast Fourier transform.Then,an adaptive K-means++clustering algorithm is developed using clustering validation index based on the nearest neighbor(CVNN),and a reactor voiceprint clustering model which can adaptively determine the optimal number of clusters is constructed.Finally,the method is validated using real measured voiceprint data from a 750 kV reactor in Northwest China.The results demonstrate that the DAKCA algorithm can stably extract 32-dimensional depth features from unlabeled voiceprint data under varying sample balance conditions and achieve optimal clustering,providing a reference for the direct and efficient use of unlabeled reactor voiceprint data.关键词
750 kV电抗器/声纹聚类/自适应聚类算法/稀疏自编码器/深度自适应K-means++算法Key words
750 kV reactor/voiceprint clustering/adaptive clustering algorithm/sparse autoencoder/DAKCA引用本文复制引用
闵永智,郝大宇,王果,何怡刚,贺建山..基于深度自适应K-means++算法的电抗器声纹聚类方法[J].电力系统保护与控制,2025,53(8):1-13,13.基金项目
This work is supported by the National Natural Science Foundation of China(No.62066024). 国家自然科学基金项目资助(62066024) （No.62066024）
甘肃省联合基金项目资助(24JRRA852) （24JRRA852）
