Masters Degrees (Industrial Engineering)

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 5 of 469
  • Item
    Developing a selection and evaluation packaging framework for retail supply chains: a South African retail supply chain case study
    (Stellenbosch : Stellenbosch University, 2024-02) Lubbe, Nikola; Van Eeden, Joubert; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: Packaging has undergone a transformation, shifting from a supporting role to a key strategic element that impacts all aspects of modern supply chains. With products now traveling globally, the need for a structured process to select and assess packaging is evident. Packaging systems play a vital role in logistics, involving various resources. Current industry trends show a shift towards optimizing packaging supply chains to enhance logistics and environmental performance. This emphasizes the importance of effective collaboration between packaging systems and supply chain stakeholders to achieve superior supply chain performance and gain a competitive edge. This thesis focuses on developing a structured framework for selecting, evaluating, and implementing packaging solutions in retail supply chains. The framework aims to reposition packaging as a strategic element in the supply chain. The study employs a systematic approach to review existing packaging frameworks and identifies five relevant ones. Design requirements were extracted through surveys, interviews, and field observations and cross-referenced with specific existing packaging frameworks and utilized as input toward the framework development phase. The framework development phase outlines a structured process with six steps: identifying stakeholders, clarifying the packaging role, selecting evaluation criteria, weighting, and rating criteria, assessing environmental and cost impact, and testing and reviewing the packaging system. Each step provides clarity on input, action, and output, ensuring that the framework can be easily understood and implemented. A three-phase validation process verified the framework's comprehensiveness, adaptability, and effectiveness. The research concludes that the proposed framework effectively fills gaps in existing frameworks while maintaining flexibility for measurement inclusion or modification. It solidifies the framework's merit to be considered alongside packaging frameworks in the literature. This research contributes to the packaging industry by providing a comprehensive and adaptable framework that redefines packaging as a strategic component within the supply chain, promoting informed decision-making and addressing environmental and cost concerns.
  • Item
    A maturity model for data science in small and medium-sized enterprises from developing countries
    (Stellenbosch : Stellenbosch University, 2024-02) Rautenbach, Simon; De Kock, Imke; Grobler, Jacomine; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: Data science (DS) is an industry 4.0 (I4.0) technology with the potential to improve organisational decision-making through the use of insights previously unknown, which may provide a competitive advantage to an organisation. Small and medium-sized enterprises (SMEs) are known to be large contributors to economies across the globe, based on metrics such as the gross domestic product (GDP) and the total share of the workforce. SMEs are generally less inclined to implement I4.0 technologies due to various challenges, such as a lack of capital and skills, which is detrimental to their development and competitive advantage. It can be argued that the successful implementation of DS has the potential to improve organisational decision-making in SMEs and increase their competitive advantage. A semi-structured literature review was conducted to explore the different I4.0 technologies, along with SMEs and how they fit into economies across the globe. A structured literature review was then performed to contextualise the problem, and to understand the factors that influence the successful implementation of DS in SMEs — both from developing and developed countries. Several challenges and opportunities associated with the implementation of DS were identified. Furthermore, a lack of research products in literature that address these challenges was identified, especially within the context of developing countries. The aim of this research was thus to contribute towards the successful implementation of DS in SMEs from developing countries. A requirement specification chapter revealed that a maturity model would be the most suitable research product for this study. Maturity models are designed as tools that enable the user to measure the current state of maturity for various domains within an organisation. Consequently, this study investigated the use of a maturity model as an appropriate research product for the implementation of DS in SMEs from developing countries. In pursuit thereof, the data science maturity model for SMEs (DSMMSMEs) was developed. The model consists of five domain components, which may be viewed as high-level categories of the given domain, which is DS for the purpose of this study. The chosen domain components are data, infrastructure, people, management, and governance. The DSMMSMEs was developed based on a foundational knowledge of current literature, which consists of various maturity models and research pertaining to DS and SMEs from developing countries. The development of the model followed a rigorous methodology for maturity model development, which is widely accepted across literature. Therefore, this research may be described as a non-empirical, qualitative study, consisting of both inductive and deductive approaches in an investigative manner. Once the DSMMSMEs had been developed, it was subject to a verification process which consisted of subject matter expert interviews. The feedback from the interviews was used to develop a second iteration of the model, which addressed any concerns raised by the subject matter experts. Next, the model was subject to a validation and implementation stage, which evaluated the appropriateness in terms of applicability, practicability, and usability. The findings of the implementation and validation stage showed that the DSMMSMEs is an appropriate tool that may contribute towards the successful implementation of DS in SMEs from developing countries.
  • Item
    A dynamic business framework aimed at guiding South African small businesses towards sustainability by considering Industry 4.0 and Industry 5.0 trends and technologies.
    (Stellenbosch : Stellenbosch University, 2024-02) Nel, Bianca; Von Leipzig, Konrad; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering. Engineering Management (MEM).
    ENGLISH ABSTRACT: The research presents a dynamic business framework designed to guide South African small businesses towards sustainability in the face of Industry 4.0 and Industry 5.0 trends and technologies. The study addresses three key research questions: RQ 1: What factors influence businesses? An exploration of the factors that influence small businesses. Drawing on a Systematic Literature Review (SLR) methodology, the study synthesizes existing knowledge to identify and analyze the different factors that are shaping the business landscape. RQ 2: What will be the effect on businesses to adopt technology? The research investigates the implication of technology adoption on small businesses, examining the transformative effect of Industry 4.0 and emerging Industry 5.0 trends. This study identifies both the adoption advantages and challenges on the business. RQ 3: What will constitute a dynamic framework to ensure business success during unpredictable and unstable future environments, especially focused on South African small businesses? In response to the dynamic and uncertain business environments, this research proposes a dynamic business framework tailored for South African small businesses. The framework is developed through a SLR methodology, ensuring a comprehensive understanding of the various factors influencing a business, the contributors, and the practices. The framework is validated through reviews from subject matter experts, incorporating practical insights to ensure that the application is relevant. The SLR serves as primary research method, allowing for a systematic exploration of the literature related to the research questions. The validity of the results and to enhance the findings, the findings from the SLR are critically evaluated against the reviews from subject matter experts in the South African small business context. The research found that although there are changes in the markets, it can be possible for a business to succeed. By ensuring the business has a dynamic business model in place, move with the markets by incorporating technology and innovation, and by fostering a problem-solving mindset- the business can be sustainable for any changes. This research study contributes to the growing discourse on business sustainability, provide small businesses in South Africa with a practical and adaptable framework to be able to withstand the impact of unpredictable events and evolving markets.
  • Item
    A machine learning framework for security forecasting and trading
    (Stellenbosch : Stellenbosch University, 2024-02) Van Schalkwyk, Philip; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: Financial markets are often perceived as unpredictable, a sentiment reinforced by the Random Walk Hypothesis and the Efficient Market Hypothesis. These theories underscore the considerable challenges in achieving excess returns without incurring substantial risk. Despite the expertise of fund managers, consistently outperforming passive index funds over the long term remains an elusive goal. This underperformance is not solely a reflection of human limitations but is indicative of the complexities and inherent uncertainties in market dynamics. Algorithms, unencumbered by human pitfalls such as fatigue, cognitive biases, and greed, demonstrate the capability for rapid and objective analysis of security pricing data. Their adaptability enables dynamic responses to market fluctuations, including the implementation of stop-losses and the avoidance of margin calls – a level of agility challenging for human traders to match. While various methods exist for time-series analysis, recent significant advancements in computer vision, along with the exceptional pattern-recognition ability of convolutional neural networks, have rendered them a favored tool in algorithmic trading. Employing computer vision algorithms, however, necessitates the transformation of a time series into a graphical representation. In this thesis, a comprehensive framework is designed and developed for the algorithmic trading of securities, centering on the image-encoding of time-series data. The objectives of the framework are two-fold in nature: Firstly, to predict the direction of security price movements using a set of conventional time-series classification methods and a suite of image-based convolutional neural networks, which utilise various encoding methodologies, including Gramian angular fields and Markov transition fields. Secondly, to demonstrate the practical utility of the obtained classification by simulating a trading environment where the effects of various components central to a trading strategy, are analysed. An instantiation of this framework is first tested on a benchmark time-series classification data set. Following this, the framework is applied to a real-world case study encompassing a diverse range of stocks, demonstrating its practical utility. In this real-world application, the image-based convolutional neural network models exhibit enhanced classification effectiveness compared to standard methods on average.
  • Item
    A roadmap to smart maintenance for inner-city public bus services in South Africa.
    (Stellenbosch : Stellenbosch University, 2024-03) Kloppers, Jacobus Le Roux; Von Leipzig, Konrad; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: In the current era of Industry 4.0, the rapid evolution of technologies is influencing all sectors of the economy. This requires maintenance to develop along the same vein. Recognising the potential for cost reduction and minimised downtime, organisations have realised the value of the implementation of digitised maintenance and effective maintenance practices. These developments have allowed Smart Maintenance to move from a distant dream to an attainable reality. There is a need to align maintenance with the industry 4.0 developments. This provides the opportunity to develop a roadmap to Smart Maintenance, providing a systematic plan of action to reach Smart Maintenance, while enhancing the current maintenance in the process. This is of particular importance to the inner-city public bus service industry in South Africa, as they are facing economic challenges and need to find ways to reduce costs while providing reliable service. A thorough literature review is conducted that identifies key elements that enable Smart Maintenance and provides the foundational knowledge for the development of a roadmap within the industry. These elements and components are further investigated by conducting an empirical investigation through structured surveys with management-level employees in the South African inner-city public bus service industry. This data informs the development of a Smart Maintenance roadmap incorporating the different elements that enable Smart Maintenance. This includes the maintenance strategy, Industry 4.0 tools, data collection methods, human capital resources, data-driven decision-making, internal integration and external integration and their components, aiming to maximise the technical and economic effectiveness of the maintenance measures. This roadmap is validated through face-to-face interviews with individuals with knowledge and experience within the industry. This ensures the practical applicability of the roadmap and provides valuable feedback to refine the roadmap. While the researcher acknowledges the limitations of the sample size and practical implementation of the roadmap, the thesis contributes both theoretically and practically. Theoretical contributions include the understanding of the interdependency between the different elements that enable Smart Maintenance and how their development can align with the improvement of current maintenance. This also provides a practical guide for inner-city public bus services in South Africa to navigate the intricate path to Smart Maintenance while aiming to reduce cost and increase reliability amid the challenges within the current economic environment.