A Novel Data-Driven Fault Diagnosis Algorithm Using Multivariate Dynamic Time Warping Measure
Figure 1
The comparison of original data and the data after preprocessing. (a)–(d) illustrate the comparison on the measurement signals on IDV(0) and IDV(13): (a) original training data; (b) original testing data; (c) training data after preprocessing; (d) and testing data after preprocessing. (e)–(h) illustrate the comparison on the measurement signals on IDV(0) and IDV(21): (e) original training data; (f) original testing data; (g) training data after preprocessing; (h) and testing data after preprocessing.
