Thesis (MScEng)--Stellenbosch University, 2012. / ENGLISH ABSTRACT: Construction projects are risky by nature, with many variables a ecting their outcome. A contingency cost and duration are allocated to the budget and schedule of a project to provide for the possible impact of risks. To enable the management of project-related risk on a portfolio level, contingency estimation must be performed consistently and objectively. The current project contingency estimation method used in the capital program management department of Eskom Distribution Western Cape Operating Unit is not standardised, and is based solely on expert opinion. The aim of the study was to develop a contingency estimation tool to decrease the in uence of subjectivity on contingency estimation methods throughout the project lifecycle so as to enable consistent project risk re ection on a portfolio level. From a review of contingency estimation approaches in literature, a hybrid method combining neural network analysis of systemic risks and expected value analysis of project-speci c risks was chosen. Interviews were conducted with project managers (regarding network asset construction projects completed in the last two nancial years) to distinguish systemic and project-speci c risk impact on cost and duration growth. Outputs from 22 interviews provided three data patterns for each of 89 projects. After interview data processing, 138 training patterns pertaining to 85 projects remained for neural network training, validation and testing. Six possible neural network inputs (systemic risk drivers) were selected as project de nition level, cost, duration, business category, voltage category and job category. A multilayer feedforward neural network was trained using a supervised training approach combining a multi-objective simulated annealing algorithm with the standard backpropagation algorithm. Neural network results were evaluated for di erent scenarios considering possible combinations of model input variables and number of hidden nodes. The best scenario (exclusion of business category input with nine hidden nodes) was chosen based on training and validation errors. Validation error levels are comparable to those of similar studies in the project management eld. The chosen scenario was shown to outperform multiple linear regression, but calculated R2 values were lower than anticipated. It is expected that neural network performance will further improve as additional training patterns become available. The trained neural network was combined with an expected value analysis tool (risk register format) to estimate contingency due to systemic risks alongside an estimation of contingency due to project-speci c risks. The project-speci c expected value method was modi ed by basing the contingency estimation on the expected number of realised risks according to a binomial scenario. A total cost distribution was included in tool outputs by assuming the contingency cost equal to the standard deviation of the cost estimate. To aid business integration of the developed tool, study outputs included the points in the project lifecycle model at which the tool should be applied, and the process by which tool outputs become inputs to the enterprise risk management system. By following this approach, systemic and project-speci c risks are contained in a single tool providing contingency cost and duration output on project level, while enabling integration with reporting on program, portfolio and enterprise level. / AFRIKAANSE OPSOMMING: Konstruksieprojekte het van nature 'n ho e risiko omdat hulle uitsette deur baie veranderlikes gea ekteer word. Gebeurlikheidsreserwes vir koste en tyd word toegeken aan die begroting en skedule van 'n projek om voorsiening te maak vir die moontlike gevolge van risiko's. Om die bestuur van projekverwante risiko op 'n portefeulje-vlak te vergemaklik, moet die beraming van gebeurlikheidsreserwes op 'n konsekwente en objektiewe manier uitgevoer word. Die huidige beramingsmetode vir projek gebeurlikheidsreserwes in die kapitaal programbestuur departement van Eskom Distribusie Wes-Kaap Bedryfseenheid is nie gestandardiseer nie, en word slegs gebaseer op deskundige opinie. Die doel van hierdie studie was om 'n gebeurlikheidsreserwe beramingsinstrument te ontwikkel wat die invloed van subjektiwiteit op beramingsmetodes verminder deur die hele projeklewensiklus, en sodoende die konsekwente weerspie eling van projekrisiko op 'n portefeulje-vlak, te bewerkstellig. Vanuit 'n studie van bestaande literatuur oor gebeurlikheidsreserwe-beraming, is 'n hibriede metode wat neurale netwerk analise van sistemiese risiko's en verwagte waarde analise van projek-spesi eke risiko's kombineer, gekies. Onderhoude is gevoer met projekbestuurders (rakende netwerk batekonstruksieprojekte wat voltooi is in die afgelope twee nansi ele jare) om te onderskei tussen die impak van sistemiese en projek-spesi eke risiko's op koste- en duurgroei. Uitsette van 22 onderhoude het drie datapatrone vir elk van 89 projekte verskaf. Na onderhouddata verwerk is, het 138 datapatrone vanuit 85 projekte oorgebly vir neurale netwerk opleiding, validasie en toetsing. Ses moontlike neurale netwerk insette (sistemiese risikodrywers) is gekies as projek de nisievlak, koste, duur, besigheidskategorie, spanningskategorie en werkskategorie. 'n Multi-laag vooruitvoerende neurale netwerk is deur 'n opleidingonder- toesig benadering opgelei { 'n multi-doelwit gesimuleerde uitgloei ngsalgoritme gekombineer met die standaard agteruit-propagerende algoritme. Die resultate van die neurale netwerk is oorweeg vir verskillende scenario's rakende moontlike kombinasies van die aantal versteekte nodes en model insetveranderlikes. Die beste scenario (uitsluiting van besigheidskategorie inset met nege versteekte nodes) is gekies op grond van opleidings- en validasiefoute. Validasie foutvlakke is vergelykbaar met di e van soortgelyke studies in die projekbestuur veld. Daar is gewys dat die gekose scenario meervoudige line^ere regressie klop, maar met laer R2 waardes as wat verwag is. Dit word verwag dat die neurale netwerk beter sal presteer soos bykomende opleidingsdatapatrone beskikbaar word. Die opgeleide neurale netwerk is gekombineer met 'n verwagte waarde analise instrument (risiko-register formaat) om gebeurlikheidsreserwes as gevolg van sistemiese risiko's hand-aan-hand met gebeurlikheidsreserwes as gevolg van projekspesi eke risiko's, te beraam. Die projek-spesi eke verwagte waarde metode is aangepas deur gebeurlikheidsreserwe-beraming te baseer op die aantal verwagte gerealiseerde risiko's volgens 'n binomiaal scenario. 'n Totale koste-verdeling is ingesluit in modeluitsette deur aan te neem dat die gebeurlikheidsreserwe vir koste gelyk is aan die standaardafwyking van die kosteberaming. Om die besigheidsintegrasie van die ontwikkelde instrument te vergemaklik, het studie uitsette die punte in die projek lewensiklus waarby die instrument toegepas moet word, en die proses waardeur instrument uitsette omgesit word na insette vir die risikobestuur sisteem op ondernemingsvlak, ingesluit. Deur hierdie benadering te volg, word sistemiese en projek-spesi eke risiko's omvat in een instrument wat gebeurlikheidsreserwes vir koste en tyd op projekvlak verskaf. Die integrasie met verslagdoening op program-, portefeulje- en ondernemingsvlak word ook bewerkstellig.

ENGLISH ABSTRACT: It is very seldom that a decision-making problem concerns only a single value or objective. The process of simultaneously optimising two or more con icting objectives is known as multi-objective optimisation (MOO). A number of metaheuristics have been successfully adapted for MOO. The aim of this study was to investigate the feasibility of applying an agent-based modelling approach to MOO. The (s; S) inventory problem was chosen as the application eld for this approach and Anylogic used as model platform. Agents in the model were responsible for inventory and sales management, and had to negotiate with each other in order to nd optimal reorder strategies. The introduction of concepts such as agent satisfaction indexes, aggression factors, and recollection ability guided the negotiation process between the agents. The results revealed that the agents had the ability to nd good strategies. The Pareto front generated from their proposed strategies was a good approximation to the known front. The approach was also successfully applied to a recognised MOO test problem proving that it has the potential to solve a variety of MOO problems. Future research could focus on further developing this approach for more practical applications such as complex supply chain systems, nancial models, risk analysis and economics. / AFRIKAANSE OPSOMMING: Daar is weinig besluitnemingsprobleme waar slegs 'n enkele waarde of doelwit ter sprake is. Die proses waar twee of meer doelwitte, wat in konflik staan met mekaar, gelyktydig optimiseer word, staan bekend as multi-doelwit optimisering (MOO). 'n Aantal metaheuristieke is al suksesvol aangepas vir MOO. Die doelwit van hierdie studie was om ondersoek in te stel na die lewensvatbaarheid van die toepassing van 'n agent gebasseerde modelerings benadering tot MOO. As toepassingsveld vir hierdie benadering was die (s; S) voorraad probleem gekies en Anylogic was gebruik as model platform. In die model was agente verantwoordelik vir voorraad- en verkope bestuur. Hulle moes onderling met mekaar onderhandel om die optimale bestelling strategiee te verkry. Konsepte soos agentbevrediging, aggressie faktore en herinneringsvermoens is ingestel om die onderhandeling tussen die agente te bewerkstellig. Die resultate het gewys dat die agente oor die vermoe beskik om met goeie strategiee vorendag te kom. Die Pareto fronte wat gegenereer is deur hul voorgestelde strategiee was 'n goeie benadering tot die bekende front. Die benadering was ook suksesvol toegepas op 'n erkende MOO toets-probleem wat bewys het dat dit oor die potensiaal beskik om 'n verskeidenheid van MOO probleme op te los. Toekomstige navorsing kan daarop fokus om hierdie benadering verder te ontwikkel vir meer praktiese toepassings soos komplekse voorsieningskettingstelsels, finnansiele modelle, risiko-analises en ekonomie.

Thesis (MScEng)--Stellenbosch University, 2012. / ENGLISH ABSTRACT: This study explores the implementation of an integrated capital budgeting visual mapping framework comprised of both Discounted Cash Flow (DCF) and Real Options Analysis (ROA) techniques. Physical asset investment decisions are based largely on rigid discounted cash flow tools which provide untimely and incomplete decisional criteria. While literature outlines the wide spread use of traditional DCF techniques, it very openly reveals large limitations, including its static inflexibility and slow to evolve framework. ROA is a more recent valuation tool based on stock option theory. It brings into account added value found in the flexibility of managerial decision making and uncertain conditions. This study implements a combined DCF and ROA capital budgeting tool within a Physical Asset Management (PAM) environment. The validity of the framework is realised through an industry relevant case study presented by a South African mining company. / AFRIKAANSE OPSOMMING: Hierdie tesis ondersoek die toepassing van ’n geïntegreerde visuele kapitaalbegrotingafbeeldingsraamwerk wat uit verdiskonteerde kontantvloei en reële opsie–analise bestaan. Fisiese batebeleggingsbesluite is dikwels gebaseer op rigiede kapitaalbegrotingstegnieke wat onvolledige besluitnemingsmaatstawwe aanbied. Terwyl literatuur die wydverspreide uiteensetting van verdiskonteerde kontantvloei openbaar, is daar nog steeds baie beperkings, soos die onbuigsaamheid en die stadige ontwikkelingstempo van verdiskonteerde kontantvloei– analise. Reële opsie–analise is ’n meer onlangse waardasiemetode wat op aandelemarkfinansies gebaseer is. Reële opsies word addisionele waarde bygevoeg deur die onsekerheid en buigsaamheid van fisiese batebeleggings. Hierde tesis implimenteer ’n gekombineerde verdiskonteerde kontantvloei en reële–opsie kapitaalbegrotingmetode binne ’n fisiese batebestuur omgewing. Die geldigheid van die gekombineerde metode is getoets met behulp van ’n gevallstudie beskikbaar gestel deur ’n Suid Afrikaanse myn.

Thesis (MScEng)--Stellenbosch University, 2013. / ENGLISH ABSTRACT: Project management (PM) is a very important field in engineering as a whole. The management of most projects has become more complex in recent times, due to greater technical complexity and the requirement of diversified skills. The management of risks is a very important process to improve the performance of a project. This is due to the link between project risks and objectives. However, this aspect of PM becomes increasingly more difficult to manage with increasing project complexity. For these reasons a need exists for more efficient PM methods. This thesis had three objectives. The first was to understand the processes and principles of PM, systems engineering (SE) and risk management. This was achieved by doing a literature study on the three fields. The second objective was to identify areas of greater risk within the management of projects. The final objective was to develop an effective generic model that illustrates the integration of SE principles into PM, with the goal to reduce the identified risks. Five risks were identified during this research. They were considered to be the most important in project management. This was accomplished by means of a questionnaire that was sent out to experts in the industry. It was established from this investigation that the following five risks, in order of importance, pose the biggest threat to the success of a project: 1. Poorly defined requirements; 2. Poor communication; 3. Poor risk management; 4. Lack of customer involvement; and 5. Inaccurate estimates. These risks were addressed by integrating the principles of SE into PM. SE is an iterative process that needs a diverse set of people, with a variety of skills, to achieve customer requirements. Various SE approaches and strategies were developed throughout the years. They were investigated to obtain insight into which of them can be used to improve PM. The top-down iterative development principles of SE offer a great advantage, and therefore it was appropriate to integrate these principles into PM. A model was developed as part of this thesis to illustrate the integration of SE principles into PM, and the importance of risk management. The model was named “Project Management Integrated with Systems Engineering Principles Model”. This tool can be used by engineers and their project teams to enhance the management of projects. It is also a generic tool that can be used for any project. The final step of this research was the validation of the model. This was done by means of expert evaluation. The purpose of this validation was to test whether the objectives of the research were met, and if the model was valid in the sense of ease of use and usefulness. The final objective of the validation process was to determine if the integration of systems engineering (SE) principles into project management (PM) were successful, and if it will reduce risks in large scale projects. It was concluded from this evaluation that its objectives were met and that the model successfully demonstrated the integration of SE into PM to reduce risks in large scale projects. Several recommendations were made that may enhance this study. They main recommendations are: 1. Researching the impact of communication on projects, by using case studies. 2. SE principles are mainly used in the first two phases of the model. Further investigation of using SE principles in phase three may be researched. 3. Customer involvement may be used during changes in the project. For this reason it is recommended that future studies may include investigation of the impact the customer has on project changes and the change management process. 4. The model could be tested in the industry on an active project. This will greatly improve the validity of the model. / AFRIKAANSE OPSOMMING: Projekbestuur is ‘n baie belangrike veld in ingenieurswese as geheel. As gevolg van die toenemende tegniese kompleksiteit en die vereiste van verskillende vaardighede, het die bestuur van meeste projekte meer gekompliseerd geraak met tyd. Die bestuur van risiko’s is ‘n baie belangrike proses om die uitvoering van ‘n projek te verbeter. Hierdie aspek van projekbestuur het egter al hoe moeiliker geword om te bestuur. Dus hiervoor bestaan daar ‘n behoefte vir meer doeltreffende projekbestuur metodes. Hierdie tesis het drie doelwitte gehad. Die eerste doelwit was om die prosesse en beginsels van projekbestuur, stelsels ingenieurswese en risikobestuur te verstaan. Dit was bevredig deur ‘n literatuur studie wat gedoen is in die drie velde. Die tweede doelwit was gestel om die areas van groter risiko binne die bestuur van projekte te identifiseer. Die finale doelwit was die ontwilkkeling van ‘n effektiewe generiese model wat die integrasie van stelsels ingenieurswese beginsels binne projekbestuur demonstreer, met die doel om die geïdentifiseerde risiko’s te verminder. Vyf risiko’s, wat as die mees belangrikste in projekbestuur beskou word, was geïdentifiseer. Hierdie risiko’s was deur middel van ‘n vraelys, wat aan deskundiges in die industrie gestuur was, geïdentifiseer. Die risiko’s, gelys in volgorde van belangrikheid, was: 1. Swak bepaalde vereistes; 2. Swak kommunikasie; 3. Swak risiko bestuur; 4. Onnoukeurige skattings; en 5. Geen kliënt betrokkenheid. Vervolgens was hierdie risiko’s deur die integrasie van stelsels ingenieurswese beginsels in projekbestuur toegespreek. Stelsels ingenieurswese is ‘n herhalingsproses wat die kliënt se vereistes bevredig, deur gebruik te maak van ‘n diverse groep mense met ‘n verskeidenheid van vaardighede. Verskeie stelsels ingenieurswese benaderings en strategië is deur die jare ontwikkel. Hierdie benaderings en strategië was geondersoek om vas te stel watter van hulle toegepas kan word om projekbestuur te verbeter. Die “top-down” herhalende ontwikkeling beginsels van stelsels ingenieurswese bied ‘n groot voordeel, en dit was om hierdie rede toepaslik om dié beginsels in projekbestuur te integreer. ‘n Model was ontwikkel as deel van die navorsing om die integrasie van stelsels ingenieurswese beginsels binne projekbestuur te illustreer, asook die belangrikheid van risikobestuur. Die model is genoem “Project Management Integrated with Systems Engineering Principles Model”. Hierdie model kan deur ingenieurs en hul projekspanne gebruik word om die bestuur van projekte te versterk. Die finale stap van die navorsing was die evaluasie van die model. Dit was gedoen deur middel van deskundige evaluasie. Die validasie proses het twee doelwitte gehad. Die eerste doel was om te bepaal of die doelwitte van die ondersoek bereik was, asook om vas te stel of die model geldig was in die sin van gemak van gebruik en bruikbaarheid. Die tweede doel van die validasie proses was om te bepaal of die model suksesvol die integrasie van stelsels ingenieurswese binne projekbestuur gedemonstreer het, en of hierdie integrasie risiko’s in groot skaalse projekte sal verminder. Dit was afgelei van die evaluasie dat die model wel suksesvol die integrasie van stelsels ingenieurswese binne projekbestuur demonstreer om risiko’s in grootskaalse projekte te verminder. Verskeie aanbevelings was gemaak wat hierdie navorsing kan versterk in waarde. Die hoof aanbevelings was: 1. Die impak wat kommunikasie op projekte het kan geondersoek word deur middel van gevallestudies. 2. Stelsels ingenieurswese beginsels is hoofsaaklik gedurende die eerste twee fases van die model gebruik. Die gebruik van stelsels ingenieurswese beginsels in fase drie kan verder ondersoek word. 3. Kliënt betrokkenheid gedurende veranderinge in ‘n projek kan gebruik word. Om hierdie rede word dit aanbeveel dat verdere studies die kliënt se impak op projek veranderings en verandering in bestuursproses ondersoek word. 4. Die model kan getoets word in die industrie op ‘n aktiewe projek. Dit sal die geldigheid van die model grootliks verbeter.

Thesis (MEng)-- Stellenbosch University, 2013. / ENGLISH ABSTRACT: Asset Management initiatives suffer many barriers in implementation which hinder their influence and sustainability. One of these barriers is the lack of buy-in from all levels in the organisation, due to a lack of understanding of the perceived benefits of Asset Management. The relationship between throughput and the maturity of Asset Management implementation is usually felt throughout the organisation, but is difficult to prove or quantify. Furthermore, it is di cult to isolate the effects of maintenance using traditional methods. Organisational alignment in an Asset Management project is achieved by aligning employees' views on what the deficient areas in the organisation are, and managing their expectations in what the perceived benefit of a good application of Asset Management would bring forth. However, the lack of a transparent method to convey the significance of critical areas in the system, and a clear way to communicate these problems creates a barrier in implementation. Without empirical evidence people rely on argumentative opinions to uncover problems, which tends to create friction as opinions from various factions may differ. Typically, these initiatives are constrained by available resources, and the allocation of resources to the correct areas is thus vital. In order for Asset Management initiatives to be successful there first needs to be alignment in execution through a clear understanding of which assets are critical, so that resources can be allocated effectively. In this study, this problem is thoroughly examined and solutions are sought in literature. A method is sought which seeks to isolate the effects of the maintenance function in an operation and uncover critical areas. A study is performed on methods which are typically used to create such understanding, which are shown to have shortcomings that limit their applicability. Thus a new methodology utilising simulation is created in order to overcome these problems. The methodology is validated through a case study, where it is shown that the simulation, in the context of the methodology, is highly beneficial to uncovering critical areas and achieving organisational alignment through communication of results. / AFRIKAANSE OPSOMMING: Fisiese bate bestuursinitiatiewe het verskeie tekortkominge in hulle implementering wat hulle invloed en volhoubaarheid verhinder. Een van hierdie hindernisse is die tekort aan ondersteuning van alle vlakke in die organisasie, wat as gevolg van 'n gebrek aan begrip van die voordele van bate bestuur voorkom. Die verhouding tussen die volwassenheid van batebestuur en produksie deurset word gewoonlik reg deur die organisasie gevoel, maar hierdie verhouding is moeilik om te bewys of te kwantifiseer. Verder is dit moeilik om met huidige methodes die gevolge van instandhouding te isoleer, en dus deeglik te begryp. Organisatoriese aanpassing by `n bate bestuursprojek word bereik deur werknemers se siening te belyn oor wat die gebrekkige areas is, en om hulle verwagtinge te bestuur oor die voordele wat `n goeie bate bestuursprojek kan voortbring. Daar is `n gebrek aan metodes om in `n deursigtige wyse die kritieke areas aan te dui en te komunikeer aan werknemers. Dit skep `n hindernis in die uitvoer van projekte en, in die afwesigheid van empiriese bewyse van probleme, is werknemers afhanklik van argumentatiewe menings om probleme te ontbloot, en die menings van verskeie rolspelers kan verskil. Enige inisiatiewe is tipies beperk deur die beskikbaarheid van hulpbronne daarvoor, en `n effektiewe toedeling van beskikbare hulpbronne is dus noodsaaklik. Om `n suksesvolle batebestuursprojek uit te voer, moet daar eers `n duidelike begrip en ooreenstemming wees oor wat die verskeie kritieke areas is wat die meeste aandag verlang, sodat hulpbronne doeltreffend toegeken kan word. In die studie word hierdie probleem deeglik ondersoek deur oplossings na te vors in die literatuur. `n Metode is gesoek wat daarop gemik is om die gevolge van instandhouding te isoleer in `n produksiestelsel en kritiese areas te ontbloot. `n Studie is uitgevoer op metodes wat gewoonlik gebruik word om sodanige analises uit te voer, en dit word gewys dat huidige metodes terkortkominge het wat hulle toepaslikheid beperk. Dus is `n nuwe metode geskep wat gebruik maak van simulasie om hierdie probleme te oorkom. Die metode is gevalideer deur om `n gevallestudie uit te voer, waar dit bevestig is dat die metode voordelig is om op `n deursigtige wyse kritiese areas te ontbloot en om organisatoriese belyning te bewerkstellig deur effektiewe kommunikasie van die resultate.

Thesis (MSc)--Stellenbosch University, 2014. / ENGLISH ABSTRACT: Evolutionary Algorithms (EAs) are stochastic techniques, based on the idea of biological evolution, for finding near-optimal solutions to optimisation problems. Due to their generality and computational speed, they have been applied very successfully in a wide range of disciplines. However, as a consequence of their stochasticity and generality, very little has been rigorously established about their performance. Developing models for explaining and predicting algorithmic performance is, in fact, one of the most important challenges facing the field of optimisation. A qualitative version of such a model of EAs is developed in this thesis. There are two paradigms for explaining why EAs are expected to converge toward an optimum. The traditional explanation is that of Universal Darwinism, but an alternative explanation is that they are hill climbing algorithms which utilise all possible escape strategies — restarting local search, stochastic search and acceptance of non-improving solutions. The combination of the hill climbing property and the above escape strategies leads to a fast algorithm that is able to avoid premature convergence. Due to the difficulty in mathematically or empirically explaining the performance of EAs, terms such as exploitation, exploration, intensity and diversity are routinely employed for this purpose. Six prevalent views on exploitation and exploration are identified in the literature, each expressing a different facet of these notions. The coherence of these views is substantiated by their deducibility from the proposed novel definitions of exploitation and exploration. This substantiation is based on a novel hypothetical construct, namely that of a Probable Fitness Landscape (PFL), which both unifies and clarifies the surrounding terminology and our understanding of the performance of EAs. The PFL is developed into a qualitative model of EAs by extending it to the notion of an Ideal Probability Distribution (IPD). This notion, along with the criteria of diversity and computational speed, forms a method for judging the performance of EA operators. It is used to explain why the principal operators of EAs, namely mutation and selection, are effective. There are three main types of EAs, namely Genetic Algorithms (GAs), Evolution Strategies and Evolutionary Programming, each of which employ their own unique operators. Important facets of the crossover operator (which is particular to GAs) are identified, such as: opposite step vectors, genetic drift and ellipsoidal parent-centred probability distributions with variance proportional to the distance between parents. The shape of the crossover probability distribution motivates a comparison with a novel continuous approximation of mutation, which reveals very similar underlying distributions, although for crossover the distribution is adaptive whereas for mutation it is fixed. The PFL and IPD are used to analyse the crossover operator, the results of which are contrasted with the traditional explanations of the Schema Theorem and Building Block Hypothesis as well as the Evolutionary Progress Principle and Genetic Repair Hypothesis. It emerges that the facetwise nature of the PFL extracts more sound conclusions than the other explanations which, falsely, attempt to prove GAs to be superior. / AFRIKAANSE OPSOMMING: Evolusionere Algoritmes (EAs) is stogastiese tegnieke vir die bepaling van naby-optimale oplossings vir optimeringsprobleme wat gebaseer is op die beginsel van biologiese evolusie. As gevolg van hul algemene toepasbaarheid en hoe berekeningspoed, is hierdie algoritmes al met groot sukses in ’n wye verskeidenheid dissiplines toegepas. Die stogastiese aard en algemene toepasbaarheid van hierdie klas van algoritmes het egter tot gevolg dat baie min al oor hul werkverrigting formeel bewys is. Die ontwikkeling van modelle waarmee die doeltreffendheid van algoritmes verklaar en voorspel kan word, is trouens een van die grootste uitdagings in die studieveld van optimering. ’n Kwalitatiewe weergawe van so ’n model word in hierdie verhandeling vir EAs daargestel. Daar bestaan twee paradigmas vir die verklaring van waarom daar van EAs verwag word om na ’n optimum te konvergeer. Die tradisionele verklaring geskied aan die hand van Universele Darwinisme, maar ’n alternatiewe verklaring is dat hierdie algoritmes bergtop-soekend is en van alle moontlike ontsnapstrategiee gebruik maak — lokale soekstrategiee, stogastiese soekstrategiee en die aanvaarding van minderwaardige oplossings. Die kombinasie van die bergtop-soekende eienskap en die insluiting van die bogenoemde ontsnapstrategiee gee aanleiding tot vinnige algoritmes wat daartoe in staat is om voortydige konvergensie te vermy. Omdat dit moeilik is om die werkverrigting van EAs wiskundig of empiries te verklaar, word terminologie soos uitbuiting, verkenning, intensiteit en diversiteit roetinegewys vir hierdie doel ingespan. Ses heersende menings in die literatuur oor uitbuiting en verkenning word ge¨ıdentifiseer wat elkeen ’n ander faset van hierdie begrippe uitlig. Die samehang van hierdie menings word deur hul afleibaarheid uit nuwe definisies van uitbuiting en verkenning gedemonstreer. Hierdie demonstrasie is gebaseer op ’n nuwe hipotetiese konstruk, naamlik die van ’n Waarskynlike Fiksheidslandskap (WFL), wat beide die omliggende terminologie¨e en ons begrip van die werking van EAs enersyds verenig en andersyds verduidelik. Die begrip van ’n WFL word tot ’n kwantitatiewe model vir EAs ontwikkel deur dit tot die konstruk van ’n Ideale Waarskynlikheidsverdeling (IWV) uit te brei. Hierdie konsep word saam met die kriteria van diversiteit en berekeningspoed gebruik om ’n metode te ontwikkel waarmee die werkverrigting van EAs beoordeel kan word. Die IWV word gebruik om te verklaar waarom die hoofoperatore van EAs, naamlik mutasie en seleksie, doeltreffend is. Daar is drie tipes van EAs, naamlik Genetiese Algoritmes (GAs), Evolusionere Strategiee en Evolusionere Programmering, wat elk hul eie, unieke operatore bevat. Belangrike fasette van die oorgangsoperator (wat eie is aan GAs) word uitgelig, soos regoorstaande trapvektore, genetiese neiging en ellipsoıdale ouer-gesentreerde waarskynlikheidsverdelings met variansies wat eweredig is aan die afstand tussen ouers. Die vorm van die oorgangs-waarskynlikheidsverdeling gee aanleiding tot ’n vergelyking tussen die begrip van oorgang en ’n nuwe, kontinue benadering van mutasie. Daar word gevind dat die onderliggende verdelings baie soortgelyk is, alhoewel die oorgangsverdeling aanpasbaar is, terwyl die verdeling vir mutasie vas is. Die WFL en IWV word gebruik om die oorgangsoperator te analiseer en die resultate van hierdie analise word teenoor die tradisionele verklarings van die Skemastelling en Boublok-hipotese sowel as die Evolusionere Vooruitgangsbeginsel en die Genetiese Herstel-hipotese gekontrasteer. Dit blyk dat meer grondige gevolgtrekkings gemaak kan word uit die fasetgewyse aard van die WFL as uit ander verklarings wat valslik poog om die meer doeltreffende werkverrigting van GAs te demonstreer. Die gebruik van faset-gewyse en kwalitatiewe modelle word geregverdig deur hul sukses in terme van die verklaring van EA werkverrigting. Die argument word gemaak dat die beste rigting vir voortgesette navorsing oor EAs is om weg te bly van vergelykende studies en die afleiding van sogenaamde vergelykings van beweging, maar om eerder die ontwikkeling van wetenskaplikgefundeerde, faset-gewyse modelle vir algoritmiese werkverrigting na te streef.

Thesis (MEng)--Stellenbosch University, 2014. / ENGLISH ABSTRACT: The cross-entropy method for multi-objective optimisation (MOO CEM) was recently introduced by Bekker & Aldrich (2010) and Bekker (2012). Results presented by both show great promise. The MOO CEM assumes that decision variables are independent. As a consequence, the question arises: under which circumstances would an algorithm that accounts for relationships between decision variables outperform the MOO CEM? Two algorithms reported to account for relationships between decision variables, the multi-objective covariance matrix adaptation evolution strategy (MOCMA- ES) and Pareto di erential evolution (PDE), are selected for comparison. In addition, two hybrid algorithms (Hybrid 1 and Hybrid 2) based on the MOO CEM are created. These ve algorithms are applied to a set of 46 continuous problems, six instances of the mission-ready resource (MRR) problem, and three instances of a dynamic, stochastic bu er allocation problem (BAP). Performance is measured using the hypervolume indicator and Mann-Whitney U-tests. One of the primary ndings is that accounting for relationships between decision variables is bene cial when solving small to medium-sized problems. In these cases, the MO-CMA-ES typically outperforms the other algorithms. However, on large problems, Hybrid 1 and the MOO CEM typically perform best. / AFRIKAANSE OPSOMMING: Die kruis-entropie metode vir meerdoelige optimering (MOO CEM) is onlangs deur Bekker & Aldrich (2010) en Bekker (2012) bekendgestel. Hul resultate is belowend. Die MOO CEM neem aan dat besluitnemingsveranderlikes onafhanklik is van mekaar. Gevolglik ontstaan die vraag: onder watter omstandighede sal 'n optimeringsalgoritme wat moontlike verhoudings tussen besluitnemingsveranderlikes in ag neem, beter vaar as die MOO CEM? Twee bestaande algoritmes, beide gerapporteer vir hul vermo e om moontlike verhoudings tussen besluitnemingsveranderlikes in ag te neem, naamlik die meerdoelige optimering kovariansiematriksaanpassing-evolusiestrategie (MO-CMA-ES) en Pareto afgeleide evolusie (PDE), word met die MOO CEM vergelyk. Twee nuwe hibriedalgoritmes (Hibried 1 en Hibried 2) word ook ter wille van di e vergelyking geskep. Die vyf algoritmes word op 'n stel van 46 kontinue probleme, ses statiese kombinatoriese gevalle en drie dinamies, stogastiese gevalle toegepas. Die prestasie van die algoritmes word deur middel van die hipervolume-aanwyser en Mann-Whitney U-toetse gemeet. 'n Prim^ere bevinding is dat dit voordelig is om moontlike verhoudings tussen besluitnemingsveranderlikes in ag te neem wanneer klein na medium-grootte probleme opgelos word. Vir hierdie gevalle presteer die MO-CMA-ES tipies beter as die ander algoritmes. Vir groot probleme presteer Hibried 1 en die MOO CEM beter as die ander algoritmes. / National Research Foundation

Thesis (PhD (Industrial Engineering))--University of Stellenbosch, 2010. / ENGLISH ABSTRACT: Innovation is important for competitiveness. It thrives on the availability of novel public and private domain knowledge. Thus the ability to access, analyze, synthesize, share, and re-use knowledge is paramount to enabling innovation within the different partners of the supply chain. These activities grow the available pool of knowledge. It also facilitates learning from mistakes, as well as capturing and enhancing opportunities for future innovation. Proactively networking resources within a formal and informal structure improve the ability of any participating enterprise to use/re-use knowledge, in a concurrently growing knowledge base. Such a "Knowledge Network” (KN) enhances knowledge sharing between and among individuals, groups and organizations in informal and formal ways. This network is also scalable in the sense that more individuals and enterprise may join the network as success cases are reported on. It is clear that knowing how to design, deploy and operate a Knowledge Network could be highly beneficial. How to successfully design and deploy a KN is a challenge and has been widely researched to a limited extent within in the past decade. The design, deploy and operate functions require understanding of social processes and how people learn and share knowledge. KN management requires a proactive, systematic approach to the planning and deployment of a formalized network for knowledge creation and transfer. It addresses promoting and improving conditions to cultivate informal and formal networking within a larger collaborative network of enterprises. This dissertation presents a refined methodology for initiating, deploying, managing and operating an Innovation Project based on the available research reported in this domain. It incorporates concepts of generic, partial and specific roadmaps, best practices, templates and examples and allows individual teams to capture knowledge about specific projects and expertise in context for later re-use. / AFRIKAANSE OPSOMMING: Om mededingend te kan wees, is innovasie belangrik. Laasgenoemde floreer op die beskikbaarheid van nuwe publieke, sowel as private domein kennis. Dus is die kundigheid om kennis te assesseer, te analiseer, saam te vat, uit te ruil met ander en dan weer te gebruik van die uiterste belang om innovasie moontlik te maak vir die onderskeie vennote in die voorsieningsketting. Hierdie genoemde aktiwiteite vergroot die beskikbare poel van kennis. Daarbenewens fasiliteer dit ook leer uit foute, sowel as die vasvang en versterking van geleenthede vir toekomstige innovasie. Deur pro-aktief en vindingryk van netwerk bronne gebruik te maak, binne ʼn formele sowel as informele struktuur, word die moontlikheid van enige deelnemende onderneming om kennis te gebruik of te hergebruik, vergroot in ʼn gelyktydig groeiende kennisbasis. So ʼn “Kennis Netwerk” (KN) versterk die uitruil van kennis tussen individue, groepe en organisasies op informele sowel as formele maniere. Hierdie netwerk is ook meetbaar in die sin dat hoe meer suksesse aangekondig word, deur individue en organisasies wat aansluit, hoe meer ondernemings wil aansluit. Dit is duidelik dat kennis ten opsigte van die ontwerp, ontplooiing en bestuur van ʼn Kennis Netwerk uiters voordelig kan wees. Dit is ʼn uitdaging om ʼn Kennis Netwerk suksesvol te ontwerp en te ontplooi en daar is die afgelope dekade op ʼn wye front beperkte navorsing op hierdie terrein gedoen. Die ontwerp, ontplooiing en bestuursfunksies vereis ʼn goeie begrip van sosiale prosesse met beklemtoning van hoe mense leer en kennis uitruil. Die bestuur van ʼn Kennis Netwerk moet pro-aktief en sistematies benader word, ten opsigte van die beplanning en ontplooiing van ʼn geformaliseerde netwerk vir die skep en oordrag van kennis. Die bevordering en verbetering van omstandighede kan formele sowel as informele netwerkbeoefening binne ʼn groter samewerkende netwerk van ondernemings vestig. Hierdie proefskrif bied ʼn verfynde metodologie vir die inisiëring, ontplooiing en bestuur van ʼn Innovasie Projek wat gebaseer is op die beskikbare navorsing wat in hierdie domein gerapporteer is. Dit behels konsepte van generiese, gedeeltelike en spesifieke padkaarte, asook die beste praktyke, patrone en voorbeelde en gee geleentheid vir individuele spanne om kennis ten opsigte van spesifieke projekte en kundigheid in konteks te bekom vir latere hergebruik.

Thesis (PhD (Industrial Engineering))--University of Stellenbosch, 2009. / ENGLISH ABSTRACT: This research has its roots in Industrial Engineering, where the premise of improving and managing efficiency, effectiveness, productivity and quality is the most common and accepted source of organisational sustenance and furtherance. This dissertation, however, addresses the evolutionary and revolutionary imperatives of a new paradigm for competitive advantage – innovation. The notion of innovation is considered many things. First and foremost, however, it has become the primary differentiator of organisational competitiveness, rendering it the source of sustained long-term prosperity. What may seem ambiguous in the title of this dissertation is essentially the imperative of every organisation functioning within the competitive domain. Where organisational maturity and innovativeness were traditionally considered antonymous, the assimilation of these two seemingly contradictory notions is fundamental to the assurance of long-term organisational prosperity. Organisations are required, now more than ever, to grow and mature their innovation capability. In working towards the fulfilment of this objective, the Maturity Modelling approach was recognised for its ability to describe organisational progression in terms of innovation capability. An Innovation Capability Maturity Model, with the intention of describing generic and evolutionary plateaus of innovation capability maturity, was developed from a comprehensive literature study. This model was evaluated with an initial case study which led to a rigorous refinement initiative that included further literature study, a mapping and comparison exercise, and a detailed analysis of innovation capability themes using a Latent Dirichlet Allocation-based topic modelling approach. The consolidation of these activities and integration with the initial model resulted in the second version thereof – ICMM v2. This second version was then utilised in an additional 5 case studies that would serve to evaluate and validate the content and structure thereof, but also make a fundamental contribution to the application of the model – captured in the so called Innovation Capability Improvement Methodology. The case studies provide evidence that the content and structure of the ICMM v2, including the approach used to convey these aspects, fulfil their intended purpose by appropriately identifying the innovation capability strengths and weaknesses of the represented organisations. The ICMM v2 and accompanying methodology provides an organisation with a systematic approach for identifying organisational innovation capability strengths and weaknesses and a framework for identifying and prioritising innovation capability improvement opportunities in an organised and coordinated manner. This dissertation concludes with a few fundamental findings pertaining to innovation and a discussion of potential future collaboration and research opportunities. / AFRIKAANSE OPSOMMING: Hierdie navorsingsprojek het sy oorsprong binne die bedryfsingenieursdomain. Bedryfsingenieurswese is primêr gerig op die verbetering en bestuur van doelmatigheid, doeltreffendheid, produktiwiteit en gehalte. Dit is voorts „n vry-algemeen aanvaarde bron van organisatoriese volhoubaarheid en verbetering van maatskappye. Hierdie navorsingsverslag spreek die evolusionêre en revolusionêre vereistes van „n nuwe paradigme vir mededingendheid, naamlik innovasie, aan. Die term innovasie beteken verskillende dinge vir verskillende mense. Dit is sedert die 1930‟s intensief nagevors. Meer onlangs het innovasie ontwikkel tot „n primêre onderskeider van maatskappy-mededingendheid. Dit is vinnig besig om te ontwikkel in „n sleutelbron van volhoubare, langtermyn welvaartskepping. Die titel van hierdie proefskrif mag aanvangklik dubbelsinnig klink, maar dit beskryf eintlik die fundamentele vereistes van elke organisasie wat binne die mededingendheidsdomain funksioneer. Aanvanklik is innovasie en organisatoriese volwassenheid as teenstrydige konsepte beskou. Die versoening van hierdie twee oënskynlike teenstrydige konsepte is egter fundamenteel tot die ontwikkeling van langtermyn organisatoriese mededingendheid en gepaargaande welvaart. Mededingendheid word tans verseker deur die tempo en volhoubaarheid waarmee maatskappye hulle innovasie-vermoeë beoefen en uitbou. Die konsep van volwassenheidsmodelering is identifiseer as „n belangrike element om die innovasie volwassenheid van maatskappye volledig uit te bou, asook om organisatoriese groei in ten opsigte van innovasie-vermoeëns te beskryf. „n Eerste orde innovasie-vermoeë volwassenheidsmodel (ICMM v1) is met behulp van „n uitgebreide literatuur-ondersoek ontwikkel. Hierdie model het ten doel gehad om generiese en evolusionêre plateau‟s van innovasie-vermoeë volwassenheid te beskryf. Die aanvanklike model is geëvalueer met „n gevallestudie waarna dit drasties verfyn is, deur gebruik te maak van „n sekondêre literatuurstudie, die kartering en „n vergelykende evaluering, asook „n gedetailleerde ontleding van innovasie-vermoeë tema‟s. Dit is gedoen deur gebruik te maak van “Latent Dirichlet Allocation”-gebaseerde konsepmodellering. Hierdie aktiwiteite is gekonsolideer en geintegreer met die eerste model in „n weergawe twee, wat bekend staan as ICMM v2. Hierdie weergawe is verder ontplooi in vyf opvolg-gevallestudies wat gebruik is. Die doel hiervan was om die nuwe model te evalueer en valideer ten opsigte van die inhoud en struktuur daarvan. Voorts het die ook „n fundamentele bydra gemaak tot die toepassing van die model waartydens resulutate van die model vervat is in „n sogenaamde innovasie-vermoeë verbeterings metodologie. Die onderskeie gevallestudies het bevestig dat die inhoud en die struktuur van die ICMM v2 hulle aanvanklike doelwitte volledig bereik het deur beide die innovasie-vermoeë sterkpunte en swakpunte van die organisasies te identifiseer en uit te lig. Die ICMM v2 en gepaardgaande metodologie bied aan „n organisasie „n sistematiese benadering tot die identifisering van organisatoriese innovasie-vermoeë sterkpunte en swakpunte. Dit voorsien verder „n raamwerk vir die identifisering en prioritisering van innovasie-vermoeë verbeterings geleenthede binne maatskappye. Hierdie proefskrif word afgesluit met „n aantal fundamentele bevindings met betrekking tot innovasie en „n bespreking van toekomstige samewerking ten opsigte van navorsingsgeleenthede.

Thesis (PhD (Industrial Engineering))--University of Stellenbosch, 2010. / ENGLISH ABSTRACT: Information on the milling of Ti6Al4V is limited; with most studies concluding that it is not possible to obtain a significant increase in the material removal rate (Qw). Tool wear maps can be a diagnostic instrument for failure analysis. Cutting speed (vc), maximum un-deformed chip thickness (heMax) and the radial immersion percentage (ae/Ø %) are the key variables in understanding the milling of titanium alloys. The objective of this research study was to construct tool wear maps for the milling of Ti6Al4V. This will form the foundation of understanding the cutting demands on the tool, in order to analyse the main wear mechanisms. Remedial actions, which are developed by tool suppliers, can be considered and integrated via this understanding of the failure modes and related mechanisms. Firstly, experimental data from background studies, literature and industry on wear rates and wear mechanisms pertaining to the milling conditions was gathered to construct the tool wear map. Mathematical models describing the wear behaviour for these conditions were also investigated. Secondly, work piece failure maps have been superimposed onto the tool wear maps constructed to understand the global failure boundaries. Experimentation was carried out to validate the constructed maps. The tool wear map could then be used to discuss the observed effects and consider remedial actions. Cutting speed corresponds to the magnitude of the thermal load and heMax represents the mechanical load. The ae/Ø % defines the duration of the exposure to the thermal load at the edge of the cutting tool. This investigation has shown the following issues to be of importance when considering tool performance via the tool wear map approach: 1. The key to designing tool wear maps is to identify the most economic Scheduled Replacement Time (SRT) for the specific components. Knowing the correct SRT makes it possible to optimize the milling conditions so that the cutting tool wears gradually under the cutting conditions, and lasts longer than the economic SRT. 2. Increased vc will decrease tool life (TL). However, in low transverse rupture strength tools there may be a minimum vc below which mechanical overload may occur. Similarly, a local maximum TL (a sweet spot) may exist if there is a phase change in the work piece material. 3. Increased heMax will decrease TL. However, heMax must be kept below a maximum critical value to avoid mechanical overload, but above a minimum critical value to avoid work hardening. 4. Increased ae/Ø % will decrease TL. The best balance of high Qw and economic TL is found with ae/Ø between 30-40% for rough milling. In finish milling the radial cut is limited to 1 mm finishing stock of the work piece. This study revealed the following important factors when considering work piece failure in the milling of Ti6Al4V: 1. Increased vc will reduce the cutting resistance of the work piece and increase Qw. However, vc must be kept below a maximum critical value to avoid work piece material burn, but above a minimum critical value to avoid burring and poor surface finish, due to tool build-up and chip jamming. 2. Increased heMax will increase the cutting resistance of the work piece and increase Qw. The heMax must be kept below a maximum critical value to avoid poor surface finish, poor flatness and parallelism (due to work piece bending). Likewise, heMax must be kept above a minimum critical value to avoid work hardening and burring. The constructed tool wear maps are validated with experimental work. This research work identified safe zones to productively mill Ti6Al4V, while producing components with a sufficient surface integrity. / AFRIKAANSE OPSOMMING: Inligting rondom freeswerk van Ti6Al4V is beperk en volgens meeste studies is dit nie moontlik om ‗n wesenlike toename in die materiaal verwyderingstempo (Qw) te behaal nie. Snybeitel verwerings kaarte kan ‗n diagnostiese hulpmiddel wees tydens analisering van snybeitels. Snyspoed (vc), maksimum onvervormende spaanderdikte (heMax) en radiale snitdiepte persentasie (ae/Ø %) is die sleutel veranderlikes om die freeswerk van Ti6Al4V beter te kan verstaan. Die doel van die navorsingstudie was om snybeitel verweringskaarte vir die freeswerk van Ti6Al4V te bou. Die werk vorm ‗n fondasie om die eise van freeswerk op die snybeitel beter te verstaan. Sodoende kan die hoof verweringsmeganismes analiseer word. Regstellende aksies wat deur snybeitel vervaardigers ontwikkel is, was ondersoek en integreer met die huidige kennis rondom die falingstipe en verwerings meganismes. Aanvanklik was eksperimentele data van agtergrond studies, literatuur en industrie oor die verweringstempos en -meganismes rondom die freeswerk van Ti6Al4V versamel. Hiermee is verweringskaarte gebou. Wiskundige modelle wat die verwering kan beskryf was ook ondersoek. Daarna was werkstuk falingskaarte integreer met die ontwikkeling van die snybeitel verweringskaarte om sodoende die grense in geheel te verstaan. Eksperimentele werk was gedoen om die snybeitel verweringskaarte se uitleg te toets. Sodoende kon die snybeitel verweringskaarte gebruik word om die gedrag van die snybeitel te bespreek en regstellende aksies te ondersoek. Snyspoed (vc) stem ooreen met die grootte van die termiese lading en heMax verteenwoordig die grootte meganiese lading. Die ae/Ø % omskryf die tydperk van blootstelling aan die termiese lading op die snyrand. Die ondersoek het bewys dat die volgende faktore belangrik is wanneer snybeitel prestasie met die snybeitel verweringskaart evalueer word: 1. Die sleutel tot die ontwerp van snybeitel verweringskaarte is om die mees ekonomies beplande vervangingstyd (SRT) vir spesifieke komponente te identifiseer. Sodoende is dit moontlik om die frees toestande te optimaliseer, waaronder die snybeitels geleidelik sal verweer onder die eise en vir ‗n langer tydperk as die ekonomiese SRT sal kan sny. 2. Toename in vc sal snybeitelleeftyd (TL) laat afneem. Snybeitels met ‗n lae dwarsbreuksterkte, kan ‗n minimum vc hê waaronder meganiese oorlading plaasvind. Terselfdertyd, kan ‗n maksimum TL (‗n ―sweet spot‖) bestaan as daar ‗n fase verandering in die werkstuk materiaal plaasvind. 3. Toename in heMax sal TL laat afneem, maar moet laer as ‗n maksimum- en hoer as ‗n minimum kritiese waarde wees, om sodoende meganiese oorlading en werksverharding onderskeidelik te vermy. 4. Toename in ae/Ø % sal TL laat afneem. Die beste balans tussen TL en ae/Ø % is gevind met ae/Ø % tussen 30-40% vir growwe freeswerk. In afrondingsfreeswerk is die radiale snit beperk tot 1 mm van die oorblywende werkstuk. Die ondersoek het bewys dat die volgende faktore belangrik is wanneer werkstukfaling in ag geneem word met snybeitel verweringskaarte: 1. Toename in vc sal die werkstukweerstand geleidelik verminder en Qw laat toeneem. Ongelukkig is vc beperk tot ‗n maksimum kritiese waarde om werkstukfaling te voorkom weens ‗material burn‘. Die snyspoed moet ook hoër as ‗n kritiese waarde wees om werkstukklitsing en swak afronding weens spaander probleme te vermy. 2. Toename in heMax sal die werkstuk weerstand geleidelik vermeerder en Qw laat toeneem. Die heMax is beperk tot ‗n maksimum kritiese waarde om swak werkstuk afronding, weens die buiging van die werkstuk, te vermy. Terselfdertyd moet heMax hoër as ‗n kritiese waarde wees om werkstukverharding en -klitsing te voorkom. Die saamgestelde snybeitel verweringskaarte was bekragtig met eksperimentele werk. Die navorsingswerk het veiligheidsareas identifiseer om Ti6Al4V produktief te frees, sonder om die werkstukoppervlak krities te beïnvloed.