基于声场空间分布特征的齿轮箱故障诊断研究

Gearbox fault diagnosis based on spatial distribution features of sound field

结合对近场声全息(NAH)与空间分布特征提取的研究,提出基于声场空间分布特征的齿轮箱故障诊断方法。鉴于齿轮箱运行状态与声场分布的对应关系,利用NAH算法重建声源附近声场,由所得声像图中提取反映声场分布特性的纹理特征,建立声场分布与各运行状态间内部联系,结合支持向量机模式分类实现故障诊断,获得满意的诊断结果,并通过实验证实该方法的有效性与优越性。

Gearbox fault diagnosis is mainly based on vibration signal analysis, however, vibration signal acquisition is not easy because of its contact-measuring. Acoustic-based diagnosis （ABD） can overcome this disadvantage. However, for the traditional ABD, it is hard to choose proper measuring positions, and acoustic signal analysis based on single channel measurement can be used only for local diagnosis. Combining near-field acoustic holography （NAH） with spatial distribution feature extraction, a method of diagnosing gearbox faults based on spatial distribution features of sound field was presented. With the corresponding relations between gearbox running states and spatial distribution of sound field, firstly, a sound field was reconstructed with NAH, and then the texture features reflecting the distribution characteristics of the sound field were extracted from the acquired acoustic images. The inner relationship between the spatial distributions of the sound field and gearbox running states was established with these features. Finally, combining with the support vector machine-based pattern classification, the fault diagnosis of a gearbox was realized. The effectiveness and superiority of the proposed method were validated with test results.