基于灰度-基元共生矩阵的旋转机械故障诊断研究

研究了基于灰度-基元共生矩阵的故障诊断方法，该方法利用图形的灰度空间分布情况和描述纹理的纹理基元法结合起来提取和挖掘旋转机械振动状态参数图形特征，可以有效地提取图形中纹理特征信息，直接利用BP人工神经网络实现旋转机械故障诊断。在600MW模化汽轮机转子试验台上进行了转子正常、转子不平衡故障、转子不对中故障及轴承松动故障的试验，诊断结果表明可以获得较高的诊断精度。

A fault diagnosis method based on gray primitive co-occurrence matrixof vibration parameter image f

This paper investigates a diagnosis method that bases on gray primitive co-occurrence matrix. This method directly extracts the image characteristics about the vibration parameter of rotating machinery by combining ray space distribution characteristics with texture primitive method. It can directly conduct rotating machinery fault diagnosis by using BP artificial neural networks after extracting the information of image texture characteristic. This method is validated to get high diagnosis accuracy by conducting the normal state rotor, unbalanced rotor, misalignment rotor and loose bearing pedestal experiment on the modeling of 600MW turbine experimental bench.