Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ TDX (Tesis Doctorals...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
TDX (Tesis Doctorals en Xarxa)
Doctoral thesis . 2023
License: CC BY NC ND
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
Recolector de Ciencia Abierta, RECOLECTA
Doctoral thesis . 2023
License: CC BY NC ND
DBLP
Doctoral thesis
Data sources: DBLP
versions View all 3 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Predictive maintenance of industrial water cooling systems

Authors: Galve Ceamanos, Sergio;

Predictive maintenance of industrial water cooling systems

Abstract

Trabajando en el entorno práctico de la empresa LAUDA Ultracool, este proyecto trabaja con equipos de refrigeración industrial para lograr detectar y diagnosticar fallos antes de que impacten en la eficiencia de la máquina. Una vez identificadas las limitaciones de la bibliografía en un entorno industrial, es posible identificar los criterios de evaluación para los resultados de la detección y el análisis que debe generar el entrenamiento de un modelo. Para lograrlo se recogieron por un lado datos de la máquina trabajando en todas las condiciones de trabajo reproducibles y bajo el efecto de fallos provocados, pero también el conocimiento experto del equipo de ingeniería. El conocimiento experto permite proponer una interfaz con el equipo de LAUDA mediante la que recoger los esquemas de la máquina para proponer un análisis estructural como base del modelado. Creando modelos que cumplen los requisitos de una aplicación industrial se pueden presentar los resultados interpretables y analizables.

Working in the practical environment of the LAUDA Ultracool company, this project worked with industrial refrigeration equipment to detect and diagnose failures before they impact the efficiency of the machine. Once the limitations of the literature in an industrial environment had been identified, it was possible to identify the evaluation criteria for the results of the detection and analysis that the training of a model must generate. To achieve this, data was collected from the machine working in all reproducible working conditions and under the effect of caused failures, and expert knowledge was gathered from the engineering team. The expert knowledge made it possible to propose an interface with the LAUDA team through which to collect the schematics of the machine to propose a structural analysis as the basis for the modeling. By creating models that meet the requirements of an industrial application, interpretable and analyzable results can be presented.

Treballant a l'entorn pràctic de l'empresa LAUDA Ultracool, aquest projecte treballa amb equips de refrigeració industrial per aconseguir detectar i diagnosticar errors abans que impactin en l'eficiència de la màquina. Un cop identificades les limitacions de la bibliografia en un entorn industrial, és possible identificar els criteris d'avaluació per als resultats de la detecció i l'anàlisi que ha de generar l'entrenament d'un model. Per aconseguir-ho es van recollir dades de la màquina treballant en totes les condicions de treball reproduïbles i sota l'efecte d'errors provocats, però també el coneixement expert de l'equip d'enginyeria. El coneixement expert permet proposar una interfície amb l'equip de LAUDA mitjançant la qual recollir els esquemes de la màquina per proposar una anàlisi estructural com a base del modelatge. Creant models que compleixen els requisits d'una aplicació industrial es poden presentar els resultats interpretables i analitzables.

Tecnologías de la información y de redes

Country
Spain
Keywords

anàlisi estructural, Internet of things, internet de les coses, análisis estructural, manteniment, diagnosis, modelado, maintenance, explicability, 004, modelatge, modelling, internet de las cosas, diagnosi, Tecnologies de la informació i de xarxes, mantenimiento, explicabilitat, explicabilidad, structural analysis

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green