短丝纤维卷绕牵伸齿轮箱故障信号的图像特征提取方法

Image feature extraction method for fault signal of short fiber winding and drafting gearbox

摘要:

针对短丝纤维卷绕牵伸齿轮箱故障信号不易提取的问题，提出了基于图像纹理信息的特征提取方法。通过对齿轮箱振动信号进行小波包双谱分析，获得具有稳定纹理信息的振动信号双谱图，采用基于小波变换对双谱图进行图像融合，提高图像的综合纹理特征。采用灰度共生矩阵的四个特征参数对振动信号的双谱图进行加权融合特征提取。在短丝生产线上对齿轮箱常见的齿轮破损和裂纹进行了实验分析，结果表明本文方法的故障识别率达到85%以上。

Abstract:

Aiming at the problem that the fault signal of the draft fiber gear winding is difficult to extract, the feature extraction method based on image texture information is proposed. By wavelet packet bispectrum analysis of the vibration signal of the gearbox, the bispectrum of the vibration signal with stable texture information is obtained. The image fusion based on wavelet transform is used to improve the integrated texture features of the image. The weighted fusion feature extraction of the bispectrum of the vibration signal is performed by using four characteristic parameters of the gray level co-occurrence matrix. The common gear damage and crack of gearbox are analyzed in the short wire production line. The results show that the fault identification rate of this method is more than 85%.