Detail výsledku
Analyzing Machine Performance Using Data Mining
Bartík Vladimír, Ing., Ph.D., UIFS (FIT)
Hruška Tomáš, prof. Ing., CSc., UIFS (FIT)
This paper focuses onanalysis of machine performance in a manufacturing company. Machine behaviorcan be complex, because it usually consists of many tasks. Performance of thesetasks depends on product attributes, worker's speed, and therefore, analysis isnot simple. Performance analysis results can be used for different purposes.Prediction and description are typical products of data mining. Predictionshould be used for online monitoring of the manufactory process and as an inputfor a scheduler. Description can serve as information for managers to knowwhich attributes of products cause problems more frequently. Howevermanufacturing processes are complex, every process is quite unique. Our longterm goal is to generalize the most common patterns to build general analyzer.This task is not simple because the lack of real word data and information.Therefore this work may contribute to the other researchers in theirunderstanding of real world manufacturing problems.
Process mining, data mining, manufacturing, performance analysis, simulation, prediction, monitoring, scheduling.
@inproceedings{BUT131008,
author="Milan {Pospíšil} and Vladimír {Bartík} and Tomáš {Hruška}",
title="Analyzing Machine Performance Using Data Mining",
booktitle="2016 IEEE Symposium on Computational Intelligence and Data Mining",
year="2016",
pages="1--7",
publisher="Institute of Electrical and Electronics Engineers",
address="Athens",
doi="10.1109/SSCI.2016.7849923",
isbn="978-1-5090-4239-5",
url="https://www.fit.vut.cz/research/publication/11230/"
}