PSI - Issue 38

Frédéric Kihm et al. / Procedia Structural Integrity 38 (2022) 12–29

19

8

Kihm, Miu, Bonato / Structural Integrity Procedia 00 (2021) 000 – 000

3.5. Correlation

The correlation of the output (strain damage) to all of the inputs was then calculated. The results are given in Table 2 :

Table 2. Correlation coefficients between the output and the inputs. Correlation coefficient with StrainDamage TemperatureDamage 0.90 PressureDamage 0.17 AccelerationDamage 0.01

It appears clearly that the strain damage correlates best, by far, with the relative damage of the temperature signal. This preliminary finding is used to justify the investigation of linear regression models between strain damage and temperature damage. Note the same correlation analysis was performed on the inputs only and the results are presented in Table 3

Table 3. Correlation coefficients between the inputs. PressureDamage

AccelerationDamage

TemperatureDamage

TemperatureDamage AccelerationDamage

1.0

1.0

0.01 0.08

PressureDamage

1.0

-0.04

The inputs are not correlated, which means that there is no hidden correlation in the input variables.

3.6. Linear Models

The first investigation involves a linear model fit between temperature damage and strain damage. The linear fit that was obtained is shown in Fig. 4.

UNRESTRICTED