A Novel Piecewise Cubic Hermite Interpolating Polynomial-Enhanced Convolutional Gated Recurrent Method under Multiple Sensor Feature Fusion for Tool Wear Prediction

. 2024 Feb 8;24(4):1129. doi: 10.3390/s24041129

Algorithm 1 Signal_Segment (

S i g_{o r g}

L_{w}

d_{w}

)

Inputs:

$S i g_{o r g}$ —original time-domain signal

$L_{w}$ —width of sliding window

$d_{w}$ —moving step length of sliding window

Outputs:

$M a t_{w i n d o w}$ —data window matrix

1: Calculate $c l$

2: Initialize $M a t_{w i n d o w}$

3: for $i = 1$ to $c l$ do

4: if $i = 1$

5: Assign the data from 1 to $L_{w}$ in $S i g_{o r g}$ to the ith column of the $M a t_{w i n d o w}$ .

6: else if $i! = c l$

7: Assign the data who are located from the $(i * d_{w} + 1)$ th to the $(i * d_{w} + 1 + L_{w})$ th in $S i g_{o r g}$ to the ith column of $M a t_{w i n d o w}$ .

8: else

9: Assign the data who are located from the $(i * d_{w} + 1)$ th to the end of $S i g_{o r g}$ to the ith column of $M a t_{w i n d o w}$ and replace the Null in the ith column with 0.

11: End if

12: End for