Introduction of a time series machine learning methodology for the application in a production system. (January 2021)

• Record Type: Journal Article
• Authors: Hennig, Martin; Grafinger, Manfred; Hofmann, René; Gerhard, Detlef; Dumss, Stefan; Rosenberger, Patrick
• Is Part Of: Advanced engineering informatics. Volume 47(2021)
• Publication Date: 2021-01
• Subjects: Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2020.101197
• Languages: English
• ISSNs: 1474-0346

Abstract

Graphical abstract: Abstract: Machine learning methods are considered a promising approach for improving operations and processes in manufacturing. However, the application of machine learning often requires the expertise of a data scientist combined with thorough knowledge of the manufacturing processes. Small and medium-sized companies that specialize in certain high value-added, variant rich production processes often lack an in-house data scientist and therefore miss out on generating a deeper data-driven insight from their production data streams. This paper proposes a three-step machine learning methodology to empower process experts with limited knowledge in machine learning: 1) data exploration through clustering, 2) representation of the production systems behaviour through specially structured neural networks and 3) querying this representation through evolutionary algorithms to achieve decision support through online optimization or scenario simulation. The chosen algorithms focus on parameter-light, well-established, general use algorithms in order to lower knowledge requirements for their application.