基于自组织神经网络的轴流风机不对中故障诊断研究

利用神经网络的非线性映射及其高度的自组织和自学习能力,将自组织神经网络(SOM)应用于轴流风机的故障诊断.根据故障信号及其故障类型来构造网络,用单一故障样本对网络进行训练,根据输出神经元在输出层的位置对故障进行判断.风机的不对中故障是指风机转轴与电机主轴之间由联轴器联结构成轴系,由于机器安装误差、承载后的变形及机器基础的松动等,造成轴系对中变化误差.本文就结合不对中故障的实际情况,通过MATLAB仿真验证了该方法的正确性.

Misalignment fault diagnosis of the axial flow fan based on self-organizing neural network

For the neural network nonlinear mapping and a high degree of self-organizing and self-learning,the self-organizing neural network(SOM) is applied to the fault diagnosis of axial flow fan.According to the information of fault signals and its fault model to construct,the network is trained with a single fault sample.The location of the output neurons in the output layer determines the type of the fault.The fan shaft and the motor spindle constitute the coupling link,as the results of the error of the machine...