Masters Degrees (Industrial Engineering)

Permanent URI for this collection

https://scholar.sun.ac.za/handle/10019.1/776

Browse

Browsing Masters Degrees (Industrial Engineering) by browse.metadata.advisor "Braun, Anja"

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    Development of a decision-support tool for implementing circular value creation structures using machine learning and a digital ecosystem
    (Stellenbosch : Stellenbosch University, 2023-11) Walter, Selina; Louw, Louis; Braun, Anja; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering. Engineering Management (MEM).
    ENGLISH ABSTRACT: The transition from a linear to a circular economy currently only succeeded for 8.6% of companies in various sectors worldwide. This research project aims to tackle this challenge by developing a tool that facilitates the implementation of a circular economy within companies. The tool serves as a guide and directly supports implementing circular economy practices. The study includes a systematic literature review on the circular economy, digital ecosystem and the sharing economy. Quantitative methods, including machine learning algorithms, are used to analyse product usage data and generate recommendations for the circular economy. The results highlight the importance of implementing the whole circular economy and considering the specific characteristics of its activities. The decision support tool developed demonstrates the critical link between the sharing economy and the circular economy by using data and machine learning techniques to improve circular economy practices. By providing insights on monetising circular economy practices and offering financial benefits while promoting sustainability, the tool enables companies to make informed decisions. The tool's applicability has been validated for utility products in the sharing economy, with precise data tracking ensuring accurate recommendations. The adaptive machine learning algorithms used in the tool are universally applicable across industries, making it a versatile solution for companies looking to implement the principles of the circular economy. The developed decision support tool provides essential insights for the practical implementation of circular economy principles in companies. It serves as a valuable research framework that enables the construction of similar decision support systems for other sustainability-related fields. Rigorous verification and validation processes ensure the efficiency and effectiveness of the tool and enhance its reliability and usability. In summary, this research project represents a comprehensive approach to managing the transition to a circular economy. The decision support tool developed provides practical insights and highlights the importance of data-driven decision-making and practical implementation in advancing circular economy practices. The results contribute to the scientific field and provide opportunities for further research and applications that promote sustainable development and environmental protection.
  • Thumbnail Image
    Item
    Fostering the adaptation of collaborative circular business models through digital platform-based ecosystems developing a matching algorithm: a design science research approach.
    (Stellenbosch : Stellenbosch University, 2023-03) Rapp, Jannis; de Kock, Imke; Braun, Anja; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: The principle of the circular economy is said to be a central building block for addressing the ecological, economic, and social problems of the evolved structures and processes in a highly interconnected world. Especially collaborative approaches that go beyond the boundaries of a single organisational unit are seen as having great potential. However, the challenge often is to bring together the right organisations, with the right concept, at the right time. This research work deals with the development of an algorithm that makes it possible to analyse organisations that have no prior interaction, in a digital platform-based ecosystem based on their digital image to see whether they can jointly realise business models that follow the principles of the circular economy. The approach of the matching process is based on the concept of digitally mapping proven circular business models and aligning them with the digital images of the organisations represented on the platform. On this basis, potentials are identified that are intended to offer an added value to the organisations on the platform in the form of suggestions. Methodologically, the thesis follows a design science research approach. An accompanying task is the configuration of a development environment to realise the design cycle around the matching algorithm. In this context, the process of matchmaking, a sufficient system architecture, a data model, a framework for the investigation of well-founded circular collaborative business models, and a graphical user interface are developed, accompanied by use cases. With reference to several literature reviews, including systematic literature reviews following the preferred reporting items for systematic reviews and meta-analyses framework, the foundations for the development deliverables are laid. An artefact in the Python development environment based on a multi-attribute decisionmaking approach is successfully verified via scenario and load testing using the user interface and is ready for implementation and associated validation involving user groups.
  • Thumbnail Image
    Item
    Human-robot collaboration for efficient circularity decision-making for end-of-usage products
    (Stellenbosch : Stellenbosch University, 2024-03) Löffler, Stefanie; De Kock, Imke ; Braun, Anja; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: As we move into industry 5.0, the traditional linear economic model is proving unsustainable in the face of resource depletion and climate change. The circular economy offers a more promising path, shifting away from the take-make-dispose approach to create a more sustainable and resilient future. The circular economy focuses on resource efficiency, reducing waste, and preserving value, challenging the traditional "end of life" concept for products. However, the transition is challenging due to many products not being designed for recovery, hindering the shift from a linear to a circular product life cycle. This thesis proposes a human-robot collaboration to improve circularity decision-making for end-of usage products to enable the circular economy. Methodologically, the thesis follows the design science research approach and reviews the literature systematically to provide a generic understanding of the knowledge base and the application domain. Using this knowledge the thesis underscores the integration of human-robot collaboration into decision-making processes, emphasizing the economic, environmental, and social factors as well as product and production related information crucial for well-informed decisions within the circular economy. It explores the joint decision-making process and highlights the pivotal role of human-robot collaboration in achieving sustainability and circularity in product lifecycle management by elaborating on the unique strengths of both humans and cobots. For this, this thesis provides skill profiles of the human operator and the cobot focusing on the cognitive abilities of individuals and the analytical prowess of cobots. Additionally, the recovery strategies of the circular economy are examined for their compatibility with human-robot collaboration, and the integration of advanced technologies such as sensors and machine learning are explored. Those findings resulted in a generic decision-making framework integrating the skills of human operators and cobots to assign products to the optimal recovery strategy. For the evaluation, a case study in a collaborative environment is conducted. For this, a user friendly graphical user interface is chosen to deploy a developed machine-learning algorithm for image classification in a workstation where a cobot and a human operator execute the decision process following the framework.
  • Thumbnail Image
    Item
    Implementation of machine learning to improve the decision-making process of end-of-usage products in a circular economy
    (Stellenbosch : Stellenbosch University, 2020-03) Diem, Michael; Louw, Louis; Braun, Anja; Stellenbosch University. Faculty of Industrial Engineering. Dept. of Industrial Engineering.
    ENGLISH 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.
  • Thumbnail Image
    Item
    Towards a business model for lithium-ion battery recycling In South Africa.
    (Stellenbosch : Stellenbosch University, 2023-03) Kuhn, Willem Johannes; Louw, Louis; Braun, Anja; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: No lithium-ion-battery (LIB) recycling facility currently exists in South Africa (SA) (TIPS, 2021). Further research was needed to guide possible LIB recycling market entrants regarding their positioning in the value chain so that they can operate successfully. A market analysis in SA and the development of a business model would aid market entrants to understand various value chain integration strategies in this potential industry. The primary research objective of this thesis was thus: Develop a viable business model for the establishment of a local end-of-life (EoL) lithium-ion battery (LIB) treatment facility and recycling industry in the South African context. To fulfil the primary research objective, Osterwalder & Pigneur (2010)’s business model building blocks then formed the basis of the sub-research objectives (SROs) 1-10 defined in Chapter 1. The research process started with a foundational literature review to explore different concepts and foundational knowledge required in this research. Quantitative projections of LIB waste generation by application and chemistry were then made, as well as needed recycling rates. This was followed by LIB recycling market structure analysis (which included the market model, industry structure & 5 forces of competition, and types of competitive advantage). The insights gained then fed into a business case screening of developed hydrometallurgical recycling process technologies that would be suitable for recycling EoL LIB in SA. This was done using the Needs, Benefit, Approach, Competition (NABC) method to select the two best business cases out of 9 recycling processes considered by Maritz (2022) – resulting in the HCl and H2SO4 Mixed-NMC processes. The EoL LIB supply options in SA were also explored by analysing the current state of EoL LIBs in SA and comparing two future options for this supply – outsourcing supply to current collection infrastructure in SA and a vertically integrated collection infrastructure. Financial models for the two selected processes from the business case screening (HCl and H2SO4 Mixed-NMC processes) was then developed. These two financial models were compared in a quantitative financial analysis, while incorporating the option to produce a NMC811 hydroxide product instead of the initial NMC111 hydroxide which proved to be financially advantageous. The H2SO4 Mixed-NMC processes, producing a NMC811 hydroxide product, was selected as the process that would be best suited to secure the financial sustainability of a LIB recycling plant in SA. A financial comparison of this selected recycling process was done under the two EoL LIB supply options as well as two outbound logistics cost scenarios. A prediction was made for the most likely value chain scenario - Zero EoL LIBs cost & outbound logistics costs passed on. This selected recycling process and predicted value chain scenario then formed the basis on which further financial analysis could be done, as well as: - A financial risk analysis through the following methods: o Sensitivity analysis o Monte Carlo simulation - A business model canvas summary (answering sub-research questions 1-10 by tying together all of the conclusions made during the whole research process).