Framework for process improvement in manufacturing of metal packaging

Simple item page
dc.contributor.advisorDirkse Van Schalkwyk, T.en_ZA
dc.contributor.authorRautenbach, Ericen_ZA
dc.contributor.otherStellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.en_ZA
dc.date.accessioned2022-02-08T10:20:45Z
dc.date.accessioned2022-04-29T09:20:37Z
dc.date.available2022-02-08T10:20:45Z
dc.date.available2022-04-29T09:20:37Z
dc.date.issued2022-04
dc.descriptionThesis (MEng)--Stellenbosch University, 2022.en_ZA
dc.description.abstractENGLISH ABSTRACT: Due to increased competitiveness in the packaging industry, process improvement is important to give businesses an edge over their competition. This thesis represents a study of the application of machine learning for process improvement in metal can manufacturing. A five step process improve ment framework based on the Six Sigma process improvement methodology and the CRISP-DM data science framework was developed. The framework consisted of different steps that included steps used in the Six Sigma process improvement methodologies as well as steps used in data science processes.The five steps were; Define, Understand, Model, Evaluate and Deploy (DUMED). The DUMED framework was used in a case study that predicted the axial load resistance of 2-piece metal food cans during the manufacturing process. The objective is to understand how axial load resistance relates to other factors in the process with the outcome that any changes made in the process will still deliver cans with suitable axial load resistance. A predictive model on axial load resistance will give enhanced capability to control axial load resistance, and will lead to less rejections and therefore less waste. A predictive model on axial load resistance can also supply valuable information on the possible viability for light weighting of material, which will have a decreased cost of raw material as a result and therefore hold financial benefit for the manufacturer. Various data science and machine learning principles were applied during the study related to data understanding, data assessing, data preparation, data modelling and model assessing. The framework was successfully applied in the case study, with the exception of the fifth step, deployment. The deployment phase will be dependent on further improvement of the predictive model. Machine learning was successfully used in the case study to develop a predictive model; the axial load resistance could be predicted within 2.3% of the actual values. The best results were obtained from using feature selected data obtained from a random forest feature selection algorithm that was modelled by using a gradient boost ensemble regression model. Machine learning was successfully applied to a metal package manufacturing line to predict quality characteristics of the final product and possibly bring about process improvement.en_ZA
dc.description.abstractAFRIKAANSE OPSOMMING: As gevolg van die toenemende kompetisie in die verpakkings industrie is proses verbetering belangrik om besighede ’n voorsprong oor hulle kompetisie te gee. Hierdie tesis is ’n studie van die gebruik van masjienleer vir proses verbetering in metaal blik vervaardiging. ’n Vyf stap proses verbeterings raamwerk wat gebaseer was op die Ses Sigma proses verbeterings metodologie an die CRISP-DM data wetenskap raamwerk was ontwikkel. Die vyf stappe was; definieer, verstaan, modeleer, eval ueer, en ontplooi (DUMED, na aanleiding van die engelse akroniem). Die DUMED raamwerk was gebruik vir ’n gevallestudie wat die aksiale ladings weerstand van 2-stuk metaal kos blikke voorspel gedurende die vervaardigings proses. Verskeie data wetenskap en masjienleer beginsels was toegepas gedurende die studie relevant tot die verstaan van die data, assessering van die data, voorbereiding van die data, modelering van die data en die assessering van die data modelle. Die raamwerk was suk sesvol toegepas vir die gevallestudie, behalwe vir die vyfde stap, naamlik die ontplooing. Die ontploo ings fase sal afhanklik wees van verdere verbeteringe op die voorspellende data model. Masjienleer was suksesvol gebruik in die gevallestudie om ’n voorspellende model te ontwikkel; die aksiale lad ings weerstand kon voorspel word tot binne 2.3% van die werklike waardes. Die beste resultaat was verkry deur die ’gradient boost’ masjienleer algoritme toe te pas op ’random forest feature selected’ data. Masjienleer was suksesvol toegepas op ’n metaal verpakkings vervaardigings lyn om kwaliteits eienskappe op die finale produk te voorspel en so moontlikke proses verbetering te bewerkstellig.af_ZA
dc.description.versionMastersen_ZA
dc.format.extent195 pagesen_ZA
dc.identifier.urihttp://hdl.handle.net/10019.1/124579
dc.language.isoen_ZAen_ZA
dc.publisherStellenbosch : Stellenbosch Universityen_ZA
dc.rights.holderStellenbosch Universityen_ZA
dc.subjectPackaging industryen_ZA
dc.subjectMachine learningen_ZA
dc.subjectTin containers -- Manufacturingen_ZA
dc.subjectUCTDen_ZA
dc.titleFramework for process improvement in manufacturing of metal packagingen_ZA
dc.typeThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
rautenbach_process_2022.pdf
Size:
8.29 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Masters Degrees (Industrial Engineering)