OpenAccess

Approach to identify product and process state drivers in manufacturing systems using supervised machine learning
File | Description | Size | Format | |
---|---|---|---|---|
00104199-1.pdf | 34.9 MB | Adobe PDF | View/Open |
Other Titles: | Ansatz zu Identifikation von relevanten Produkt- und Prozessparametern in Produktionssystemen durch den Einsatz von überwachtem maschinellen Lernen | Authors: | Wuest, Thorsten | Supervisor: | Thoben, Klaus-Dieter | 1. Expert: | Thoben, Klaus-Dieter | 2. Expert: | Irgens, Christopher | Abstract: | The developed concept allows identifying relevant state drivers of complex, multi-stage manufacturing systems holistically. It is able to utilize complex, diverse and high-dimensional data sets which often occur in manufacturing applications and integrate the important process intra- and inter-relations. The evaluation was conducted by using three different scenarios from distinctive manufacturing domains (aviation, chemical and semiconductor). The evaluation confirmed that it is possible to incorporate implicit process intra- and inter-relations on process as well as programme level through applying SVM based feature ranking. The analysis outcome presents a direct benefit for practitioners in form of the most important process parameters and state characteristics, so-called state drivers, of a manufacturing system. Given the increasing availability of data and information, this selection support can be directly utilized in, e.g., quality monitoring and advanced process control. |
Keywords: | Manufacturing Systems, Manufacturing Processes, Product State, Accumulating State Vector, Quality, Machine Learning, Feature Selection, Holistic Data and Information Management | Issue Date: | 24-Nov-2014 | Type: | Dissertation | URN: | urn:nbn:de:gbv:46-00104199-11 | Institution: | Universität Bremen | Faculty: | FB4 Produktionstechnik |
Appears in Collections: | Dissertationen |
Items in Media are protected by copyright, with all rights reserved, unless otherwise indicated.