caa a22 4500 606159517 CHVBK 20210128100625.0 cr unu---uuuuu 210128e20150401xx s 000 0 eng 10.1007/s00521-014-1654-5 doi (NATIONALLICENCE)springer-10.1007/s00521-014-1654-5 Large, high-dimensional, heterogeneous multi-sensor data analysis approach for process yield optimization in polymer film industry [Elektronische Daten] [Michael Kohlert, Andreas König] Today's advanced complex manufacturing processes from microelectronics to pharmaceutical industries provide huge datasets (big data) from heterogeneous multi-sensory monitoring. Analytical tools for such high-dimensional and large datasets are available to support manufacturers in quality and yield optimization, but latent problems efficiently linking process data to these tools exist, the available methods are not fully satisfactory, and the real-time support is very limited. In this work, one particular industrial process from polymer industry was investigated as a research vehicle for the development of methods for efficient process interfacing, process status classification and prediction, as well as online result visualization. Novelty filtering, anomaly detection, and one-class classification (OCC) methods have been in the focus of the investigation. These methods are of particular importance as expert knowledge from the production lines discloses that the process shows unexpected states and behavior during production runs, which lead to low yield and high cost. Causes for this abnormal behavior are assumed sensor faults, environmental influences, and unexpected raw material properties' deviations. Thus, novelty filters, anomaly detection, and OCC methods are particularly suitable for such cases. A process line from standard production with approximately 160 sensory channels has been monitored for 3months in 1-min intervals. This provided 21,900 process data mostly normal condition samples of about 160 dimensions each for the conducted experiments. Accuracies of 99% in OCC were achieved, and a first prototype of an advanced novelty detection GUI for process monitoring was conceived, which supports the process monitoring by the responsible staff. The achieved results allow predicting process yield problems within 2h in advance of occurrence despite unknown objects. Future work will focus on exploiting this for advanced process control and yield optimization. The Natural Computing Applications Forum, 2014 One-class classification (OCC) nationallicence Novelty detection nationallicence Multi-sensor data analysis nationallicence Process yield prediction and optimization nationallicence Process state visualization nationallicence Kohlert Michael Department of Electrical and Computer Engineering, Institute of Integrated Sensor Systems, University of Kaiserslautern, 67663, Kaiserslautern, Germany aut König Andreas Department of Electrical and Computer Engineering, Institute of Integrated Sensor Systems, University of Kaiserslautern, 67663, Kaiserslautern, Germany aut Neural Computing and Applications Springer London 26/3(2015-04-01), 581-588 0941-0643 26:3<581 2015 26 521 https://doi.org/10.1007/s00521-014-1654-5 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00521-014-1654-5 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Kohlert Michael Department of Electrical and Computer Engineering, Institute of Integrated Sensor Systems, University of Kaiserslautern, 67663, Kaiserslautern, Germany aut NATIONALLICENCE 700 1- König Andreas Department of Electrical and Computer Engineering, Institute of Integrated Sensor Systems, University of Kaiserslautern, 67663, Kaiserslautern, Germany aut NATIONALLICENCE 773 0- Neural Computing and Applications Springer London 26/3(2015-04-01), 581-588 0941-0643 26:3<581 2015 26 521