Development of a procedure model to forecast machine health based on long-term power consumption data

dc.contributor.advisorVon Leipzig, Konraden_ZA
dc.contributor.advisorBraun, Prof. Dr.-Ing. Anjaen_ZA
dc.contributor.authorHolzapfel, Timen_ZA
dc.contributor.otherStellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.en_ZA
dc.date.accessioned2022-11-11T09:55:09Zen_ZA
dc.date.accessioned2023-01-16T12:45:19Zen_ZA
dc.date.available2022-11-11T09:55:09Zen_ZA
dc.date.available2023-01-16T12:45:19Zen_ZA
dc.date.issued2022-08-31en_ZA
dc.descriptionThesis (MEng) -- Stellenbosch University, 2022.en_ZA
dc.description.abstractENGLISH ABSTRACT: Energy consumption data is already being studied for a variety of analyses. Still, there are fields of application in which energy consumption analysis is hardly used. One such application is the degradation of a machine. In this research work, a procedure model is developed based on a use case to infer the health of the machine. Through wear and tear of the machine, energy gets lost for instance in the form of friction or heat. This energy loss must be additionally supplied to the machine by electrical energy. The degradation of the machine can thus be represented by long-term trend modelling of the power consumption. A process model describes the individual steps of the data analysis and provides information about the necessary inputs and the output of the model. In the second step, the process model is implemented in a backend software segment. The software segment includes pre-processing of the data, analysis of the data, real-time data processing as well as visual presentation of the results, and alerting in case of critical conditions. The analysis of the data includes trend modelling on the one hand and predicting the power consumption using machine learning approaches on the other. The verification of the trend model yields logical results. Due to the short period of the data basis, the validity of the results is limited. For the prediction of power consumption, the quality of the forecast was checked using error metrics. The best result was achieved by the random forest regressor with a coefficient of determination of 0.79.en_ZA
dc.description.abstractAFRIKAANS OPSOMMING: Energie verbruik word alreeds bestudeer vir 'n verskeidenheid van analises. Tog is daar velde van toepassing waarin energieverbruikontleding skaars gebruik word. Een van die hierdie areas is die agteruitgang van n masjien. In hierdie navorsingswerk word 'n proseduremodel ontwikkel gebaseer op 'n gebruiksgeval om die gesondheid van die masjien af te lei. Deur slytasie van die masjien gaan energie verlore, byvoorbeeld in die vorm van wrywing of hitte. Hierdie energieverlies moet addisioneel deur elektriese energie aan die masjien voorsien word. Die agteruitgang van die masjien kan dus verteenwoordig word deur langtermynmodellering van die kragverbruik. 'n Proseduremodel beskryf die individuele stappe van die data-analise en verskaf inligting oor die nodige insette en die uitset van die model. Die proseduremodel is geïmplementeer in 'n sagteware segment, in die tweede stap. Die sagteware segment sluit voorafverwerking van die data in, so wel as regte-tyd data verwerking, visuele voorstelling van die resultate en waarskuwing in geval van kritiese kondisies. Die analise van data behels tendens modellering aan die een hand en die voorspelling van energie verbruik deur die bestudering van masjien benaderings op die ander hand. Die verifikasie van die tendensmodel lewer logiese resultate. As gevolg van die kort tydperk van die data grondslag is die geldigheid van die resultate beperk. Vir die voorspelling van kragverbruik, is die kwaliteit van die voorspelling nagegaan met behulp van foutmetrieke. Die beste resultaat is deur die ewekansige woud regressor behaal met 'n bepalingskoëffisiënt van 0,79.af_ZA
dc.description.versionMastersen_ZA
dc.format.extentxi, 97 pages : illustrationsen_ZA
dc.identifier.urihttp://hdl.handle.net/10019.1/126006en_ZA
dc.language.isoen_ZAen_ZA
dc.publisherStellenbosch : Stellenbosch Universityen_ZA
dc.rights.holderStellenbosch Universityen_ZA
dc.subjectMachinery -- Monitoringen_ZA
dc.subjectMachinery -- Maintenance and repairen_ZA
dc.subjectConsumption of energy – Analysisen_ZA
dc.subjectProduction engineeringen_ZA
dc.subjectMachine learningen_ZA
dc.subjectUCTDen_ZA
dc.titleDevelopment of a procedure model to forecast machine health based on long-term power consumption dataen_ZA
dc.typeThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
holzapfel_procedure_2022.pdf
Size:
8.11 MB
Format:
Adobe Portable Document Format
Description: