Skip to main content

Table 5 Mean and standard deviation of the feature importance of three ML models obtained by using 100 random states

From: Classification of failure modes of pipelines containing longitudinal surface cracks using mechanics-based and machine learning models

Model

a/wt

2c/(Dwt)0.5

Ac (wt-a)σy/Cv

DT

Mean

0.2496

0.1238

0.6266

Std. Dev.

0.0083

0.0059

0.0045

RF

Mean

0.3682

0.1819

0.4499

Std. Dev.

0.0127

0.0062

0.0134

GB

Mean

0.2905

0.1539

0.5556

Std. Dev.

0.0026

0.0026

0.0001