Analysis of the Relationship Between Process and Vibex Data

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00227964" target="_blank" >RIV/68407700:21230/14:00227964 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Analysis of the Relationship Between Process and Vibex Data

Popis výsledku v původním jazyce

We explored how vibrations (recorded in the VIBEX dataset) are related to values of standard process variables, and particularly whether some of the vibration variables can be predicted from the process variables. We _rst looked at the global relationships between the two categories, by analysing the dependencies between the principal components of the two data families. This analysis shows a visual pattern indicating there is a non-random association between the two. Then we tried to learn a predictivemodel for each individual VIBEX variable, in which the inputs are formed by the process variables. Some of the vibration variables proved predictable as demonstrated by the values of the correlation coe_cient which measures the statistical agreement between the prediction and the actual value. The correlation coe_cient values estimated on independent test sets were often over 0.5 (a correlation ce_cient ranges from -1 to 1, where any positive number indicates a correlation).

Název v anglickém jazyce

Analysis of the Relationship Between Process and Vibex Data

Popis výsledku anglicky

We explored how vibrations (recorded in the VIBEX dataset) are related to values of standard process variables, and particularly whether some of the vibration variables can be predicted from the process variables. We _rst looked at the global relationships between the two categories, by analysing the dependencies between the principal components of the two data families. This analysis shows a visual pattern indicating there is a non-random association between the two. Then we tried to learn a predictivemodel for each individual VIBEX variable, in which the inputs are formed by the process variables. Some of the vibration variables proved predictable as demonstrated by the values of the correlation coe_cient which measures the statistical agreement between the prediction and the actual value. The correlation coe_cient values estimated on independent test sets were often over 0.5 (a correlation ce_cient ranges from -1 to 1, where any positive number indicates a correlation).

Druh

O - Ostatní výsledky

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

<a href="/cs/project/7E13027" target="_blank" >7E13027: SUstainable PREdictive Maintenance for manufacturing Equipment</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2014

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů