正交迭代局部Fisher判别转子故障诊断

Rotor Fault Diagnosis Using Orthogonal Iteration Local Fisher Discriminant

通过局部加权邻接矩阵重新定义类内散度和类间散度,建立局部Fisher判别函数,在特征值求解过程中以正交迭代方式找出最优投影向量,得到故障诊断模型。该方法能保证数据降维过程中的重构误差最小,并可直接运用故障诊断模型识别增量数据,避免了一般流形学习模式识别时对动态增量数据需要重建模型的问题。转子故障诊断试验表明,对于多传感器振动特征融合信号,相对其他流形学习算法,正交局部Fisher判别(orthogonl locally Fisher discriminant,简称OLFD)的故障诊断效果最好。

A method of fault diagnosis by using orthogonal iterative local fisher discriminant was proposed to better recognize faults of rotor system.Divergences within and between classes were both redefined on base of local weighted adjacency matrix,and local fisher discriminant function was established.Then optimal projection vector was found by iterative orthogonal approach and fault diagnosis model was achieved which can be directly used to recognize patterns of incremental data.The method guarantees minimum reconstruction errors during dimensionality reduction and be free from model reconstruction on the dynamic incremental data in general manifold learning methods.The experimental result shows that the orthogonal local fisher discriminant (OLFD) algorithm is superior to other manifold learning algorithms in rotor fault diagnoses.