A Prestudy of Machine Learning in Industrial Quality Control Pipelines

• DOI: 10.31449/inf.v46i2.3938
• Publication Date: 2022-07-13T22:14:48Z
• Authors: Jože Ravničan; Anže Marinko; Gjorgji Noveski; Stefan Kalabakov; Marko Jovanovič; Samo Gazvoda; Matjaž Gams
• Keywords: Statistical Process Control

Today's fast paced industrial production requires automation at multiple steps during its process. Involving humans the quality control inspection provides high degree of confidence that end products are with best quality. Workers involved in process may have an impact on capacity by lowering throughput, depending complexity time is carried out, which a time-critical operation, or after completed. Companies striving to fully automate their stages and it comes naturally focus using various machine learning methods help build pipeline will offer throughput In this paper we give overview applying several approaches order achieve autonomous pipeline. The applications for these were used improve two biggest manufacturing companies Slovenia. One most challenging part study was tests had be performed only small number defective products, as reality. motivation test find promising one later actual application.