基于支持向量机的电声信号故障诊断方法
A fault Diagnosis Method for Electroacoustic Signals Based on Support Vector Machine
张春 1冯碧娟1
作者信息
- 1. 甘肃龙源新能源有限公司,甘肃 兰州 730000
- 折叠
摘要
针对电力设备状态监测领域中变压器的故障诊断问题,以电声技术为核心,结合支持向量机方法,提出一种新的故障诊断方案.首先,以变压器为例,研究电气设备状态监测系统.其次,引入一种集成学习方法,利用支持向量机模型诊断故障.最后,在MATLAB上进行仿真实验.实验结果表明,该方法能够有效识别正常状态和异常状态,具有较高的准确性、精确性及召回率.
Abstract
The article focuses on the fault diagnosis problem of transformers in the field of power equipment status monitoring, with electroacoustic technology as the core and support vector machine method combined, proposing a new fault diagnosis scheme. Firstly, taking transformers as an example, the electrical equipment status monitoring system was studied. Secondly, an ensemble learning method is introduced to diagnose faults using support vector machine models. Finally, conduct simulation experiments on MATLAB. The experimental results show that this method can effectively identify normal and abnormal states, with high accuracy, precision, and recall.
关键词
电声信号/状态监测/支持向量机/集成学习Key words
electroacoustic signal/status monitoring/support vector machine/integrated learning引用本文复制引用
出版年
2024
NETL
NSTL
万方数据