Pattern Recognition in Multivariate Time Series: Towards an Automated Event Detection Method for Smart Manufacturing Systems
This paper presents a framework to utilize multivariate time series data to automatically identify reoccurring events, e.g., resembling failure patterns in real-world manufacturing data by combining selected data mining techniques. The use case revolves around the auxiliary polymer manufacturing pro...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Journal of Manufacturing and Materials Processing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4494/4/3/88 |
| _version_ | 1797554462954356736 |
|---|---|
| author | Vadim Kapp Marvin Carl May Gisela Lanza Thorsten Wuest |
| author_facet | Vadim Kapp Marvin Carl May Gisela Lanza Thorsten Wuest |
| author_sort | Vadim Kapp |
| collection | DOAJ |
| description | This paper presents a framework to utilize multivariate time series data to automatically identify reoccurring events, e.g., resembling failure patterns in real-world manufacturing data by combining selected data mining techniques. The use case revolves around the auxiliary polymer manufacturing process of drying and feeding plastic granulate to extrusion or injection molding machines. The overall framework presented in this paper includes a comparison of two different approaches towards the identification of unique patterns in the real-world industrial data set. The first approach uses a subsequent heuristic segmentation and clustering approach, the second branch features a collaborative method with a built-in time dependency structure at its core (TICC). Both alternatives have been facilitated by a standard principle component analysis PCA (feature fusion) and a hyperparameter optimization (TPE) approach. The performance of the corresponding approaches was evaluated through established and commonly accepted metrics in the field of (unsupervised) machine learning. The results suggest the existence of several common failure sources (patterns) for the machine. Insights such as these automatically detected events can be harnessed to develop an advanced monitoring method to predict upcoming failures, ultimately reducing unplanned machine downtime in the future. |
| first_indexed | 2024-03-10T16:32:26Z |
| format | Article |
| id | doaj.art-0072bd3878fc432bb99e4320e758e41e |
| institution | Directory Open Access Journal |
| issn | 2504-4494 |
| language | English |
| last_indexed | 2024-03-10T16:32:26Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Manufacturing and Materials Processing |
| spelling | doaj.art-0072bd3878fc432bb99e4320e758e41e2023-11-20T12:42:03ZengMDPI AGJournal of Manufacturing and Materials Processing2504-44942020-09-01438810.3390/jmmp4030088Pattern Recognition in Multivariate Time Series: Towards an Automated Event Detection Method for Smart Manufacturing SystemsVadim Kapp0Marvin Carl May1Gisela Lanza2Thorsten Wuest3Wbk Institute of Production Science, Karlsruhe Institute of Technology, Kaiserstr. 12, 76131 Karlsruhe, GermanyWbk Institute of Production Science, Karlsruhe Institute of Technology, Kaiserstr. 12, 76131 Karlsruhe, GermanyWbk Institute of Production Science, Karlsruhe Institute of Technology, Kaiserstr. 12, 76131 Karlsruhe, GermanyBenjamin M. Statler College of Engineering and Mineral Resource, West Virginia University, Morgantown, WV 26506, USAThis paper presents a framework to utilize multivariate time series data to automatically identify reoccurring events, e.g., resembling failure patterns in real-world manufacturing data by combining selected data mining techniques. The use case revolves around the auxiliary polymer manufacturing process of drying and feeding plastic granulate to extrusion or injection molding machines. The overall framework presented in this paper includes a comparison of two different approaches towards the identification of unique patterns in the real-world industrial data set. The first approach uses a subsequent heuristic segmentation and clustering approach, the second branch features a collaborative method with a built-in time dependency structure at its core (TICC). Both alternatives have been facilitated by a standard principle component analysis PCA (feature fusion) and a hyperparameter optimization (TPE) approach. The performance of the corresponding approaches was evaluated through established and commonly accepted metrics in the field of (unsupervised) machine learning. The results suggest the existence of several common failure sources (patterns) for the machine. Insights such as these automatically detected events can be harnessed to develop an advanced monitoring method to predict upcoming failures, ultimately reducing unplanned machine downtime in the future.https://www.mdpi.com/2504-4494/4/3/88smart manufacturingIndustry 4.0polymer processingpolymer manufacturingsmart maintenanceunsupervised learning |
| spellingShingle | Vadim Kapp Marvin Carl May Gisela Lanza Thorsten Wuest Pattern Recognition in Multivariate Time Series: Towards an Automated Event Detection Method for Smart Manufacturing Systems Journal of Manufacturing and Materials Processing smart manufacturing Industry 4.0 polymer processing polymer manufacturing smart maintenance unsupervised learning |
| title | Pattern Recognition in Multivariate Time Series: Towards an Automated Event Detection Method for Smart Manufacturing Systems |
| title_full | Pattern Recognition in Multivariate Time Series: Towards an Automated Event Detection Method for Smart Manufacturing Systems |
| title_fullStr | Pattern Recognition in Multivariate Time Series: Towards an Automated Event Detection Method for Smart Manufacturing Systems |
| title_full_unstemmed | Pattern Recognition in Multivariate Time Series: Towards an Automated Event Detection Method for Smart Manufacturing Systems |
| title_short | Pattern Recognition in Multivariate Time Series: Towards an Automated Event Detection Method for Smart Manufacturing Systems |
| title_sort | pattern recognition in multivariate time series towards an automated event detection method for smart manufacturing systems |
| topic | smart manufacturing Industry 4.0 polymer processing polymer manufacturing smart maintenance unsupervised learning |
| url | https://www.mdpi.com/2504-4494/4/3/88 |
| work_keys_str_mv | AT vadimkapp patternrecognitioninmultivariatetimeseriestowardsanautomatedeventdetectionmethodforsmartmanufacturingsystems AT marvincarlmay patternrecognitioninmultivariatetimeseriestowardsanautomatedeventdetectionmethodforsmartmanufacturingsystems AT giselalanza patternrecognitioninmultivariatetimeseriestowardsanautomatedeventdetectionmethodforsmartmanufacturingsystems AT thorstenwuest patternrecognitioninmultivariatetimeseriestowardsanautomatedeventdetectionmethodforsmartmanufacturingsystems |