Application of Machine Learning Algorithms for Tool Condition Monitoring in Milling Chipboard Process

. 2023 Jun 23;23(13):5850. doi: 10.3390/s23135850

Algorithm 3 Exhaustive Grid Search for Hyperparameter Optimization

1:
procedure GridSearch( $m o d e l, p a r a m_g r i d, d a t a s e t, s c o r i n g, c v$ )
2:
Preprocess $d a t a s e t$
3:
Split $d a t a s e t$ into $t r a i n_s e t$ and $t e s t_s e t$
4:
Initialize $b e s t_s c o r e \leftarrow - \infty$
5:
Initialize $b e s t_p a r a m s \leftarrow \emptyset$
6:
for all combinations $p a r a m s$ in $p a r a m_g r i d$ do
7:
$m o d e l \leftarrow$ Instantiate $m o d e l$ with $p a r a m s$
8:
$s c o r e s \leftarrow$ Perform $c v$ -fold cross-validation on $t r a i n_s e t$ with $m o d e l$
9:
$a v g_s c o r e \leftarrow$ Average $s c o r e s$
10:
if $a v g_s c o r e > b e s t_s c o r e$ then
11:
$b e s t_s c o r e \leftarrow a v g_s c o r e$
12:
$b e s t_p a r a m s \leftarrow p a r a m s$
13:
end if
14:
end for
15:
Train $m o d e l$ with $b e s t_p a r a m s$ on entire $t r a i n_s e t$
16:
Evaluate $m o d e l$ on $t e s t_s e t$ using $s c o r i n g$ metric
17:
return $m o d e l$ , $b e s t_p a r a m s$
18:
end procedure