电力变压器异常故障智能声纹监测与诊断系统研究及应用  

作　　者：余金龙 

机构地区：[1]国能神皖合肥发电有限责任公司,合肥230000

出　　处：《科技创新与应用》2024年第8期149-152,共4页Technology Innovation and Application

摘　　要：如何提高电力变压器运行潜伏性异常故障监测,并且变压器运行不受干扰,是目前电力行业亟待解决的重要问题之一。提出电力变压器异常故障智能声纹监测与诊断系统的研究与应用,通过对电力变压器各种故障声音发声机理分析、混合声音采集与分离、声音信号特征提取和故障类型识别的研究,结合独立分量分析算法、小波包能量分布向量和梅尔对数频谱、BP神经网络算法等人工智能技术的运用,在不影响变压器正常运行下对其进行监测,实现对变压器运行健康状态展示与告警,及时发现变压器异常故障,消除变压器隐患,保障变压器安全稳定运行,减少经济损失,对电力系统发展具有重要意义。How to improve the latent abnormal fault monitoring of power transformer operation without interference is one of the important problems to be solved in the power industry.Therefore,the research and application of intelligent voiceprint monitoring and diagnosis system for abnormal faults of power transformer is proposed.Through the research on sound mechanism analysis,mixed sound collection and separation,sound signal feature extraction and fault type identification of power transformer faults,combined with the application of artificial intelligence technologies such as independent component analysis algorithm,wavelet packet energy distribution vector and Mel logarithmic spectrum,BP neural network algorithm and so on.Monitoring the transformer without affecting the normal operation of the transformer,displaying and warning the operation health status of the transformer,finding the abnormal faults of the transformer in time,eliminating the hidden dangers of the transformer,ensuring the safe and stable operation of the transformer and reducing economic losses.It is of great significance to the development of power system.

关 键 词：变压器异常故障 声纹监测技术 智能诊断 声纹采集 监测算法 

分 类 号：TM41[电气工程—电器]