基于小波-神经网络的某电厂汽轮机振动故障诊断系统的研究  

Research on a Steam Turbine Vibration Fault Diagnosis System for a Power Plant Based on Wavelet-Neural Network

作　　者：余熳烨[1] 林颖[1] 

机构地区：[1]华南理工大学广州学院,广东广州510800

出　　处：《机床与液压》2013年第15期194-196,共3页Machine Tool & Hydraulics

摘　　要：以某电厂的汽轮机组振动故障诊断为工程背景,针对振动信号的分析处理方法、小波包能量法提取特征向量及神经网络技术在汽轮机振动故障诊断中的应用展开深入的研究。实践表明:设计的系统在汽轮机的振动故障诊断中取得了良好的效果,具有较强的工程实践价值。Steam turbine unit vibration fault diagnosis of a power plant was taken as the engineering background. Analysis meth- ods for vibration signal, eigenvector extraction by using wavelet packets analysis and application of neural network techniques in turbine vibration fault diagnosis were illustrated. Practice shows that the designed system has good effect in vibration fault diagnosis of turbine. It has strong practical value in actual project.

关 键 词：汽轮机 振动故障诊断 小波分析 小波神经网络 

分 类 号：TK268[动力工程及工程热物理—动力机械及工程]