Fault diagnosis method based on multi-period segmented sliding window standard deviation

[0021] like figure 1 As shown, a fault diagnosis method based on the standard deviation of the multi-period segmented sliding window includes the following steps:

[0022] 1. Collect An period of current amplitude data during normal operation of an electrical equipment A as sample data, and normalize the maximum and minimum values ​​of the sample data of each period to the [0,1] interval;

[0023] 2. Convert the sample data into two-dimensional matrix data, that is, the complete data of a certain period in the horizontal direction, and the corresponding point data in each period in the vertical direction, such as figure 2 As shown; the specific operation is: initialize the two-dimensional array Array[x][y], x represents the number of acquisition cycles of the sample data, y represents the number of data points in a single cycle, fill the sample data into the two-dimensional array, initialize the list L, Ln , Lm, set the size of the sliding window as m*n, the sliding step as s,