Improving operator evaluation skills for defect classification using training strategy supported by attribute agreement analysis

Abstract Automatic Optical Inspection (AOI) machines have an important role in the monitoring and detection of errors during the manufacturing process of electronic circuit boards. These machines show images of products with potential assembly defects to an operator and let him decide whether the product has a real defect or on the contrary it was an automated false positive detection. The attribute agreement analysis methodology is part of a Six Sigma strategy to examine the repeatability and reproducibility of an evaluation system, thus giving important feedback on the suitability of each operator in classifying defects. In order to reduce the number of operator errors, a training method was developed with the support of the attribute agreement analysis method with test images presented to operators for classification. By using this methodology, it was possible to check the capability of each operator, and improve the operator's evaluation score. After the application of the tool, the improvement of results is shown.