Implementation of machine learning to improve the decision-making process of end-of-usage products in a circular economy

dc.contributor.advisorLouw, Louisen_ZA
dc.contributor.advisorBraun, Anjaen_ZA
dc.contributor.authorDiem, Michaelen_ZA
dc.contributor.otherStellenbosch University. Faculty of Industrial Engineering. Dept. of Industrial Engineering.en_ZA
dc.date.accessioned2020-02-19T11:53:00Z
dc.date.accessioned2020-04-28T12:11:43Z
dc.date.available2020-02-19T11:53:00Z
dc.date.available2020-04-28T12:11:43Z
dc.date.issued2020-03
dc.descriptionThesis (MEng)--Stellenbosch University, 2020.en_ZA
dc.description.abstractENGLISH ABSTRACT: Rising consumption due to growing world population and increasing prosperity, combined with a linear economic system have led to a sharp increase in garbage production, general pollution of the environment and the threat of resource scarcity. At the same time, the perception of environmental protection becomes evident. The Circular Economy (CE) could reduce waste production and decouple economic growth from resource consumption, but most of the products currently in use are not designed for the recovery options of the CE. In addition, the decision-making process regarding following the steps of End-of-Usage (EoU) products has further weaknesses in terms of economic attractiveness for the participants, which leads to low return rates. This work proposes a model of the decision-making process for laptops, which is divided into two parts. In the first part, the condition of the product on component level is determined by the use of Machine Learning (ML). For this purpose stress factors are developed, which have an impact on the condition of the product. Furthermore, ways are elaborated to capture them, as the product is not physically present. A ML method is selected to process this information. A suitable software application is selected on the basis of defined criteria. In the second part, an economic and ecological evaluation is conducted based on the conditions delivered by the ML process. A possible purchase price is determined on the basis of the costs incurred and the expected selling price. In addition, the emissions saved as a result of the recovery are calculated. In order to demonstrate the potentials of the developed processes and thus validate them, comprehensive data is simulated and a prototype developed. The data is used to train the Artificial Neural Networks (ANNs) and as test cases. This work will contribute to carrying out more advanced decision-making and thereby increase the attractiveness, which should lead to higher return rates of EoU products.en_ZA
dc.description.abstractAFRIKAANSE OPSOMMING: Stygende verbruik as gevolg van die groeiende wêreld bevolking en toenemende welvaart, gekombineerd met 'n lineêre ekonomiese stelsel, het gelei tot 'n skerp toename in vullis produksie, algemene omgewingsbesoedeling en die bedreiging van skaarsheid in hulpbronne. Terselfdertyd word die persepsie van omgewings beskerming uitgelug. Die “Circular Economy” (CE) kan afval produksie verminder en ekonomiese groei van hulpbron verbruik ontkoppel, maar die meeste produkte wat tans in gebruik is, is nie ontwerp vir die herstel opsies van die CE nie. Daarbenewens het die besluitnemingsproses rakende die stappe van “End-ofUsage” (EoU) produkte verdere swakhede in terme van ekonomiese aantreklikheid vir die deelnemers, wat tot lae opbrengskoerse lei. Hierdie navorsing is in twee verdeel en stel 'n model voor van die besluitnemingsproses. In die eerste deel word die toestand van die produk op komponent vlak bepaal deur die gebruik van Masjienleer (ML). Daarom word stresfaktore ontwikkel wat 'n invloed het op die toestand van die produk. Verder word maniere uitgewerk om dit vas te lê, aangesien die produk nie fisies aanwesig is nie. 'n ML-metode is die geselekteerde metode om hierdie inligting te verwerk. 'n Gepaste sagteware toepassing word op grond van gedefinieerde kriteria geselekteer. In die tweede deel word 'n ekonomiese en ekologiese evaluering gedoen op grond van die toestande wat deur die ML-proses gelewer word. 'n Moontlike koopprys word bepaal op grond van die koste en die verwagte verkoopprys. Daarbenewens word die emissies wat as gevolg van die herstel bespaar is, bereken. Om die potensiaal van die ontwikkelde prosesse te demonstreer en sodoende te valideer, word uitgebreide data gesimuleer en 'n prototipe ontwikkel. Die data word gebruik om die “Artificial Neural Networks” (ANNs) sowel as die toetsgevalle op te lei. Hierdie werk sal bydra tot meer gevorderde besluitneming en sodoende die aantreklikheid verhoog, wat tot hoër opbrengskoerse van EoU-produkte behoort te lei.af_ZA
dc.description.versionMastersen_ZA
dc.format.extentxiv, 196 leaves : illustrations (some color)
dc.identifier.urihttp://hdl.handle.net/10019.1/107965
dc.language.isoenen_ZA
dc.publisherStellenbosch : Stellenbosch Universityen_ZA
dc.rights.holderStellenbosch Universityen_ZA
dc.subjectWaste minimization -- Technolocal innovationsen_ZA
dc.subjectEvironmental protectionen_ZA
dc.subjectMachine learningen_ZA
dc.subjectSalvage (Waste, etc.) -- Decision makingen_ZA
dc.subjectArtificial neural networksen_ZA
dc.subjectUCTDen_ZA
dc.subjectEnd-of-use products -- Sustainabilityen_ZA
dc.subjectCirucular economy -- Environmental aspectsen_ZA
dc.titleImplementation of machine learning to improve the decision-making process of end-of-usage products in a circular economyen_ZA
dc.typeThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
diem_implementation_2020.pdf
Size:
8.22 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Plain Text
Description: