Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Lead time prediction using machine learning algorithms: A case study by a semiconductor manufacturer

: Lingitz, Lukas; Gallina, Viola; Ansari, Fazel; Gyulai, Dávid; Pfeiffer, András; Sihn, Wilfried; Monostori, László

Volltext urn:nbn:de:0011-n-5206593 (599 KByte PDF)
MD5 Fingerprint: ba4b7eda72fcd97ce5124b8ac8ffbf8e
(CC) by-nc-nd
Erstellt am: 24.4.2020

Procedia CIRP 72 (2018), S.1051-1056
ISSN: 2212-8271
Conference on Manufacturing Systems (CMS) <51, 2018, Stockholm>
European Commission EC
H2020; 692466; SemI40
Power Semiconductor and Electronics Manufacturing 4.0
Zeitschriftenaufsatz, Konferenzbeitrag, Elektronische Publikation
Fraunhofer Austria ()
Fraunhofer IPA ()
Durchlaufzeit; Durchlaufzeitplanung; Halbleiterfertigung; maschinelles Lernen; Produktionsplanung- und steuerung PPS; predictions; machine learning; comparison; features

The accurate prediction of manufacturing lead times (LT) significantly influences the quality and efficiency of production planning and scheduling (PPS). Traditional planning and control methods mostly calculate average lead times, derived from historical data. This often results in the deficiency of PPS, as production planners cannot consider the variability of LT, affected by multiple criteria in today's complex manufacturing environment. In case of semiconductor manufacturing, sophisticated LT prediction methods are needed, due to complex operations, mass production, multiple routings and demands to high process resource efficiency. To overcome these challenges, supervised machine learning (ML) approaches can be employed for LT prediction, relying on historical production data obtained from manufacturing execution systems (MES). The paper examines the use of state-of-the-art regression algorithms and their effect on increasing accuracy of LT prediction. Through a rea l industrial case study, a multi-criteria comparison of the methods is provided, and conclusions are drawn about the selection of features and applicability of the methods in the semiconductor industry.