A Novel Data-Driven Fault Diagnosis Algorithm Using Multivariate Dynamic Time Warping Measure
Figure 2
The relationship between the fault diagnosis performance and the length of the MTS pieces. The points on FAR-FDR curves record the experimental results with different in algorithm. Among these points, the one which is the closest to the EER curve represents the fault diagnosis performance. The experimental results reveal that the proposed method will have the best performance when the length of the MTS pieces is set as 16. (a) The results on IDV(11). (b) The results on IDV(21).
