In a visual control, the measurement system is human. Each appraiser must control the part and judge the conformity. Consequently, the subjectivity of measure is very present and the variability therefore high. The subjectivity of this inspection is generated by two aspects: the exploration i.e. the capacity to perceive the defect by the appraiser and the evaluation i.e. the capacity to evaluate correctly the defect. So, after to realize the exploration and after to have made the evaluation, the appraiser could with more of facilities to give a reponse and so a judgement on the acceptability of the defect. The inspection must be separated into two operations: the exploration and the evaluation. Thus, in this text, we propose a method to measure the variability of inspections and to know the causes: the R2E2 test.
[1]
E. Köster,et al.
Sensory memory and food texture
,
2005
.
[2]
Samuel E. Windsor.
Attribute Gage R&R
,
2003
.
[3]
Morten Meilgaard,et al.
Sensory Evaluation Techniques
,
2020
.
[4]
J. Fleiss,et al.
Inference About Weighted Kappa in the Non-Null Case
,
1978
.
[5]
J. Fleiss,et al.
The Reliability of Dichotomous Judgments: Unequal Numbers of Judges per Subject
,
1979
.
[6]
B. Everitt,et al.
Statistical methods for rates and proportions
,
1973
.
[7]
B. Everitt,et al.
Large sample standard errors of kappa and weighted kappa.
,
1969
.
[8]
Jacob Cohen.
A Coefficient of Agreement for Nominal Scales
,
1960
.