论文部分内容阅读
针对电厂汽轮发电机组故障诊断问题,将小波变换和BP网络结合构造了一个三层的小波BP网络故障诊断系统。在输入层对振动信号进行二进离散小波变换,提取其在多尺度下的细节系数作为故障特征向量,根据这些特征向量进行小波BP网络的学习,最后用该学习过的小波BP网络诊断故障并将此方法成功地应用于汽轮发电机组故障诊断。仿真结果表明此方法是可行和有效的。
Aiming at the fault diagnosis of steam turbine generator set in power plant, a three-layer wavelet BP network fault diagnosis system is constructed by combining wavelet transform and BP network. In the input layer of the vibration signal binary discrete wavelet transform to extract its multi-scale coefficient of detail as a fault feature vector, based on these eigenvectors wavelet neural network learning, and finally using the learned wavelet BP network fault diagnosis and This method is successfully applied to the fault diagnosis of steam turbine generator sets. Simulation results show that this method is feasible and effective.