基于声学特征提取的电厂汽机调速系统故障预测  

Fault Prediction of Power Plant Turbine Speed Control System Based on Acoustic Feature Extraction

作　　者：王京 WANG Jing(Gansu Power Investment Wuwei Thermal Power Co.,Ltd.,Wuwei 733000,China)

机构地区：[1]甘肃电投武威热电有限责任公司,甘肃武威733000

出　　处：《电声技术》2025年第2期184-186,共3页Audio Engineering

摘　　要：提出一种基于声学特征提取的电厂汽机调速系统故障预测方法。通过采集系统声音信号,结合小波变换和梅尔频率倒谱系数(Mel Frequency Cepstral Coefficient,MFCC)提取特征,使用卷积神经网络(Convolutional Neural Networks,CNN)和长短期记忆(Long Short-TermMemory,LSTM)网络模型进行故障分类。实验结果表明,该方法的分类准确率最高可达99.4%,有效提升了故障预测的准确性和实时性。A fault prediction method of turbine speed regulation system in power plant based on acoustic feature extraction is proposed.By collecting the sound signal of the system,combining wavelet transform and Mel Frequency Cepstral Coefficient(MFCC) to extract features,the fault classification is carried out by using Convolutional Neural Networks(CNN) and Long Short-Term Memory(LSTM)network models.The experimental results show that the classification accuracy of this method can reach up to 99.4%,which effectively improves the accuracy and real-time performance of fault prediction.

关 键 词：声学特征提取 电厂汽机调速系统 故障预测 

分 类 号：TN912.34[电子电信—通信与信息系统]