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 "Bitsch, Günter"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Algorithm selector for dynamic AGV scheduling in a smart manufacturing environment using machine learning
    (Stellenbosch : Stellenbosch University, 2022-11) Schweitzer, Felicia Cathrin; Louw, Louis; Bitsch, Günter; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: Artificial intelligence is considered as significant technology for driving the future evolution of smart manufacturing environments forward. At the same time, automated guided vehicles (AGVs) play an essential role in manufacturing systems because they have such great potential when it comes to improving internal logistics by increasing production flexibility. Consequently, the productivity of the entire system relies on the quality of the schedule, which is capable of achieving massive cost savings by minimizing delay and the total makespan. However, traditional scheduling algorithms often have difficulties in adapting to changing environment conditions, and the performance of a selected algorithm depends on the individual scheduling problem. That is why the analysis of scheduling problem classes can help to identify the most suitable algorithm depending on a given problem. Currently, the focus in the literature lies on individual algorithm approaches for specific AGV scheduling scenarios, but the influence of framework conditions to the algorithm performance lacks attention. More research is necessary in terms of the dynamic and independent reaction for optimizing the AGV scheduling procedure without human surveillance in case of failures. To develop an algorithm selection approach for AGV scheduling scenarios, this research answered the question of how machine learning approaches must be implemented so that the allocation of tasks in the context of dynamic AGV scheduling can be improved to increase performance. This study followed Design Science Research, particularly the cognition process based on Osterle et al. (2011) that builds on an analysis, design, evaluation, and diffusion phase. During the design phase, laboratory experiments unveiled the successful implementation of two constraint programming solvers for solving scheduling problems based on the Job Shop Scheduling Problem (JSSP) and Flexible Job Shop Scheduling Problem (FJSSP). OR-Tools developed by Google and CP Optimizer of IBM solved large instances in reasonable time, and the performance of the solver strongly depended on the given scheduling problem class and problem instance. Consequently, it is beneficial to make use of an algorithm selection, as the overall production performance increased by selecting the most suitable algorithm for a given instance. The field experiment within the learning factory of Reutlingen University enabled the implementation of the approach within a dynamic environment, that can react to disruptions like machine break-downs or AGV failures. As a limitation, the research considered a simplification of the AGV scheduling problem based on the JSSP and FJSSP. As such, the parameters are limited to transport orders, transport durations, sequences and AGVs. Furthermore, the training of the selector was with a limited amount of 544 benchmark instances. Nevertheless, this research showed an exemplary extension of existing scheduling approaches to develop an algorithm selection model which can be built upon in the future. This research places the focus on constraint programming solutions for scheduling problems and emphasizes the benefits of applying machine learning for algorithm selection on a per-instance base. In this way, scheduling systems can be computationally faster and more efficient in the future and help to achieve the desired overall performance of smart manufacturing systems.
  • Thumbnail Image
    Item
    Development of a conceptual framework for integrating intelligent-product structures into a flexible manufacturing system
    (Stellenbosch : Stellenbosch University, 2022-11) Burkart, Adrian; Bitsch, Günter; De Kock, Imke; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: Product complexity, shorter product life cycles, and short lead times to market challenge the manufacturing industry. Consequently, manufacturers seek to respond with a growing product variety. and new business models to serve the customer’s individual needs. Thus, there is a need for flexible. manufacturing. In particular multi-model production requires enhanced communication and decision-making of the manufacturing resources. Addressing these challenges without IoT technologies will be difficult. Thus, integrating intelligent-product structures is the leading pathway toward a flexible manufacturing system. The industry 4.0 paradigm requires methods for integrating IoT Solutions into manufacturing. These solutions mainly consist of connected, intelligent products to increase flexibility and adaptability in smart factories. However, identifying the requirements and solution scenarios incorporating intelligent products presents a challenge for the manufacturing industry, especially in the SME sector. There are still uncertainties when implementing intelligent-product structures and managing mixed product intelligence structures holistically. This thesis aims twofold: firstly, contextualising flexibility, intelligent products, and their required technologies. Secondly, providing a conceptual framework to analyse the existing manufacturing environment and derive intelligent-product structures. In the context of flexibility, intelligent products only directly influence the four dimensions: Material handling flexibility, Process flexibility, Routing flexibility, and Program flexibility. The systematic literature review provides comprehensive models for defining and classifying intelligent products in manufacturing. A generic product classification regarding its functionalities across the entire product lifecycle is established, and fundamental technologies for each functionality are derived. Thus, the literature review addresses the first part of the research aim. The Intelligent-Product Initiation Decision-Support (IPIDS) framework, as a designed result of the requirement specification, defines, analyses, designs, and executes intelligent products and resources within the context of flexible manufacturing. Methods, tools, and processes are provided to guide the user through the four stages of the IPIDS framework. The first stage of definition assesses the existing infrastructure of the manufacturing by classifying the products and resources according to functionalities. In addition, manufacturing problems are identified and classified. Subsequently, a feasibility study of the identified problems derives the desired solution to manage the manufacturing problem with intelligent products. Stage 3 specifies design requirements based on the target functionalities of the products. Finally, the design requirements are used to develop intelligent products. Thus, the IPIDS framework addresses the second part of the research aim of providing a holistic concept to assess the existing manufacturing environment, identifying value-adding factors through intelligent products, and deriving design and implementation concepts. The evaluation of the IPIDS framework is addressed through a theoretical verification and a prototype implementation in a learning factory. The implementation findings showcase that the IPIDS framework provides applicable, valuable and practicable methods for assessing the manufacturing environment based on the functionalities of the products and resources and deriving implementation concepts for intelligent-product structures. The validation is based on a comprehensive application of the IPIDS framework and statistical analysis, comparing the initial situation with the developed solution. The validity and applicability of the IPIDS framework provide a premise for intelligent-product structures in flexible manufacturing systems.