拉杆转子装配振动检测分形研究

Fractal research on the assembly vibration detection of rod fastening rotor

针对单个螺栓预紧变化对篦齿盘振型无影响、通过统计分析振动响应信号时频域特征亦不能有效判断拉杆转子装配状态问题,提出利用分形理论分析拉杆转子装配振动检测信号新方法。通过拉杆转子装配振动检测试验获取振动响应信号,运用分形理论分析试验结果,分别计算三种螺栓预紧状态下矩形盒维数及多重分形谱参数,利用多重分形谱参数为支持向量机特征向量对拉杆转子装配状态进行模式识别。结果表明,拉杆转子螺栓松动时,振动响应信号的盒维数会相应增加,盒维数大于1.25时转子装配不合格。结合支持向量机用多重分形谱参数预测装配状态分类结果正确率达93.700 8%。

The change of single bolt preload makes only little difference to the vibration mode of labyrinth disc,so, the assembly state of a rod fastening rotor can not be detected effectively through the time domain and frequency domain analysis of vibration response signals.Aiming at the problem,the fractal method was adopted as a new method to analyze the assembly vibration signals of the rod fastening rotor.The vibration response signals were obtained by an assembly vibration detection test.Then the fractal theory was used to analyze the test result.And the rectangle box dimension and multi-fractal spectrum parameters of three bolt preload states were figured out.The multi-fractal spectrum parameters were applied as the feature vectors of support vector machine,by which the assembly state of the rod fastening rotor was identified.The result shows that when the bolt of rod fastening rotor looses,the box dimension of the vibration response signal will increase accordingly.When the box dimension is bigger than 1 .25 ,it shows that the rotor assembly is unqualified.When the support vector machine is used for classification,the correct ratio reaches 93.7008% while the multi-fractal spectrum is taken as the feature for assembly state prediction.