Knowledge elicitation for fault diagnostics in plastic injection moulding : a case for machine-to-machine communication

Vrabič, Rok (author), Kozjek, Dominik (author), Butala, Peter (author)

In most manufacturing processes the defect rate is very low. Sometimes, only a few parts per million are defective because of a faulty process. For this reason, fault diagnostics is faced with extremely imbalanced data sets and requires large volumes of data to achieve a reasonable performance. This paper explores whether a machine-to-machine approach can be used, in which several work systems share the process data to improve the accuracy of the fault-detection model. The model is based on machine learning and is applied to industrial data from approximately two million process cycles performed on several injection moulding work systems.

• Language: English
• Keywords: manufacturing system, predictive model, machine-to-machine
• Typology: 1.01 - Original Scientific Article
• Organization: FS - Faculty of Mechanical Engineering
• Publication version: Author Accepted Manuscript
• Year: 2017
• Number of pages: Str. 433-436
• Numbering: Vol. 66, iss. 1
• PID: 20.500.12556/RUL-101580
• UDC: 658.5(045)
• ISSN on article: 0007-8506
• DOI: 10.1016/j.cirp.2017.04.001
• COBISS.SI-ID: 15490587
• Publication date in RUL: 18.06.2018

Record is a part of a journal

• Title: CIRP annals
• Shortened title: CIRP ann.
• Publisher: Technische Rundschau, Hallwag Verlag, Colibri, Elsevier
• ISSN: 0007-8506
• COBISS.SI-ID: 170267

Secondary language

• Language: Slovenian
• Keywords: proizvodni sistemi, napovedni modeli, komunikacija stroj-stroj

Projects

• Funder: ARRS - Slovenian Research Agency
• Project number: P2-0270
• Name: Proizvodni sistemi, laserske tehnologije in spajanje materialov