Conversion of Real Data from Production Process of Automotive Company for Process Mining Analysis

@inproceedings{35864,
   author = {Dišek, Miroslav and Šperka, Roman and Kolesár, Ján},
   address = {Switzerland},
   booktitle = {Smart Innovation, Systems and Technologies. Agent and Multi-Agent Systems: Technologies and Applications.},
   keywords = {Process mining; Data cleaning; Data cleaning tools; DISCO},
   howpublished = {paměťový nosič},
   language = {eng},
   location = {Switzerland},
   isbn = {978-3-319-59393-7},
   pages = {223-233},
   publisher = {Springer International Publishing AG},
   title = {Conversion of Real Data from Production Process of Automotive Company for Process Mining Analysis},
   url = {https://link.springer.com/chapter/10.1007/978-3-319-59394-4_22},
   year = {2017}
}

TY  - JOUR
ID  - 35864
AU  - Dišek, Miroslav - Šperka, Roman - Kolesár, Ján
PY  - 2017
TI  - Conversion of Real Data from Production Process of Automotive Company for Process Mining Analysis
PB  - Springer International Publishing AG
CY  - Switzerland
SN  - 9783319593937
KW  - Process mining
KW  - Data cleaning
KW  - Data cleaning tools
KW  - DISCO
UR  - https://link.springer.com/chapter/10.1007/978-3-319-59394-4_22
N2  - The aim of this paper is to convert the real data from the raw format from different information systems (log files) to the format, which is suitable for process mining analysis of a production process in a large automotive company. The conversion process will start with the import from several relational databases. The motivation is to use the DISCO tool for importing real pre-processed data and to conduct process mining analysis of a production process. DISCO generates process models from imported data in a comprehensive graphical form and provides different statistical features to analyse the process. This makes it possible to examine the production process in detail, identify bottlenecks, and streamline the process. The paper firstly presents a brief introduction of a manufacturing process in a company. Secondly, it provides a description of a conversion and pre-processing of chosen real data structures for the DISCO import. Then, it briefly describes the DISCO tool and proper format of pre-processed log file, which serves as desired input data. This data will be the main source for all consecutive operations in generated process map. Finally, it provides a sample analysis description with emphasis on one production process (process map and few statistics). To conclude, the results obtained show high demands on pre-processing of real data for suitable import format into DISCO tool and vital possibilities of process mining methods to optimize a production process in an automotive company.
ER  - 

DIŠEK, Miroslav, Roman ŠPERKA a Ján KOLESÁR. Conversion of Real Data from Production Process of Automotive Company for Process Mining Analysis. In \textit{Smart Innovation, Systems and Technologies. Agent and Multi-Agent Systems: Technologies and Applications.}. Switzerland: Springer International Publishing AG. s.~223-233. ISBN~978-3-319-59393-7. 2017.