Analysis of Manufacturing Process Sequences, Using Machine Learning on Intermediate Product States (as Process Proxy Data)

Abstract : Quality and efficiency increased in importance over the last years within the manufacturing industry. To stay competitive companies are forced to constantly improve their products and processes. Today’s information technology and data analysis tools are promising to further enhance the performance of modern manufacturing. In this paper, at first, the concept of the product state based view in a distributive manufacturing chain is presented, followed by a brief introduction of relations between product states along the chain. After showing that a in detail description based on cause-effect models is not economical viable today, the possibilities of using machine learning on intermediate product states to analyze the process sequence is introduced and discussed. Providing a chance to analyze large amounts of data with high dimensionality and complexity, machine learning tools combined with cluster analysis are perfectly suited for the task at hand within the product state based concept.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-01470614
Contributor : Hal Ifip <>
Submitted on : Friday, February 17, 2017 - 3:52:33 PM
Last modification on : Friday, December 1, 2017 - 1:15:28 AM
Long-term archiving on : Thursday, May 18, 2017 - 2:46:47 PM

File

978-3-642-40361-3_1_Chapter.pd...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Thorsten Wuest, Christopher Irgens, Klaus-Dieter Thoben. Analysis of Manufacturing Process Sequences, Using Machine Learning on Intermediate Product States (as Process Proxy Data). 19th Advances in Production Management Systems (APMS), Sep 2012, Rhodes, Greece. pp.1-8, ⟨10.1007/978-3-642-40361-3_1⟩. ⟨hal-01470614⟩

Share

Metrics

Record views

414

Files downloads

416