KIT | KIT-Bibliothek | Impressum | Datenschutz

Virtual In-line Inspection for Function Verification in Serial Production by means of Artificial Intelligence

Wagner, Raphael; Fischer, Jakob; Gauder, Daniel; Haefner, Benjamin; Lanza, Gisela

In high-tech production, companies often deal with the manufacture of assemblies with quality requirements close to the technological limits of manufacturing processes. The article shows an approach of a virtual in-line inspection, predicting the products functionality. An artificial neural network (ANN) fed with product characteristics and process data as well as the resulting functional fulfillment of the product is trained for virtual function prognosis. Through the preventive identification of defective products before the final assembly step, components can be recovered and returned to serial production. By optimizing the parameters of the ANN, incorrect classifications are reduced and the practical applicability is ensured. The approach is demonstrated in an industrial application in the automotive industry.

Open Access Logo

Verlagsausgabe §
DOI: 10.5445/IR/1000125769
Veröffentlicht am 06.11.2020
DOI: 10.1016/j.procir.2020.03.126
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Produktionstechnik (WBK)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2020
Sprache Englisch
Identifikator ISSN: 2212-8271
KITopen-ID: 1000125769
Erschienen in 16th CIRP Conference on Computer Aided Tolerancing (CIRP CAT 2020). Ed.: E. Morse
Veranstaltung 16th CIRP Conference on Computer Aided Tolerancing (CIRP CAT 2020), Online, 15.06.2020 – 17.06.2020
Verlag Elsevier, Amsterdam
Seiten 63-68
Serie Procedia CIRP ; 92
Bemerkung zur Veröffentlichung Die Veranstaltung fand wegen der Corona-Pandemie als Online-Event statt
Schlagwörter Quality Control; Artificial Intelligence; Predictive Model
Nachgewiesen in Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page