旋转机械故障诊断的图形识别方法研究

PDF(1594 KB)

振动与冲击 ›› 2012, Vol. 31 ›› Issue (17) : 171-175.

论文

旋转机械故障诊断的图形识别方法研究

窦唯，刘占生

作者信息 +

A fault diagnosis method based on graphic recognition for rotating machinery

DOU Wei ，LIU Zhansheng

Author information +

文章历史 +

摘要

以旋转机械振动三维参数图形为研究对象，提出了基于图形识别技术的旋转机械故障诊断方法。该方法用表征纹理的统计法、结构法及图形纹理方向的梯度法形成描述图形纹理特征的灰度-梯度-基元三维共生矩阵。该矩阵精确地反映了图形纹理的粗糙程度、重复方向和空间复杂度及纹理方向，准确地描述了图形灰度空间分布特性(概率)、空间统计相关性和图形内各像素点梯度的分布规律。描述了灰度统计和空间结构的纹理特征，有效地提取旋转机械状态参数图形中纹理特征信息。最后，利用RBF人工神经网络实现旋转机械故障诊断。在汽轮机转子试验台上进行了6种状态试验研究，诊断结果表明该方法具有较高的诊断准确率，为旋转机械故障诊断探索了一条新路。

Abstract

Taking the three-dimensional vibration image of rotating machinery as the studying objective, this paper investigates the fault diagnosis method based on graphic recognition technology. This method uses the statistical method, the structural method based on texture and the gradient method which characterize the graphic textural direction is studied for describing graphic textural characteristic. The rough degree, direction and spatial complex degree and direction of texture are reflected precisely. The graphic grayscale spatial distribution characteristic, spatial statistical dependence and pixel point gradient distributed rule are described accurately. Textural feature information in rotating mechanical state parameter graph is extracted effectively. It can directly conduct rotating machinery fault diagnosis by using artificial neural networks after extracting the information of image texture characteristic. This method is validated to get high diagnosis accuracy by experimenting on the modeling of 600MW turbine experimental bench.

导出引用

窦唯;刘占生. 旋转机械故障诊断的图形识别方法研究[J]. 振动与冲击, 2012, 31(17): 171-175

DOU Wei;LIU Zhansheng. A fault diagnosis method based on graphic recognition for rotating machinery [J]. Journal of Vibration and Shock, 2012, 31(17): 171-175