Inaugural Addresses (Industrial Engineering)

Permanent URI for this collection

https://scholar2.stb.sun.ac.za/handle/10019.1/774

Browse

Recent Submissions

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Predictive maintenance using clustering methods for the use-case of bolted connections in the automotive industry
    (Stellenbosch : Stellenbosch University, 2023-03) Bekker, Emmarentia Lydia; Matope, Stephen; Grobler, Jacomine; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering. Engineering Management (MEM).
    ENGLISH ABSTRACT: The rise of Industry 4.0 and the implementation of “smart machines” have opened new opportunities to utilise all the data gathered from machines in an automotive manufacturing environment. A big obstacle faced by maintenance staff is understanding the data retrieved from the machines as the volume is often overwhelming and needs to be processed to be fully useful. The most prevalent model found in predictive maintenance is data-driven and based on statistical process control, pattern recognition, or machine learning algorithms. This thesis explores the feasibility of predictive maintenance, using clustering, specifically for the use case of bolted connections using electronically controlled nutrunners in a modern, high-volume manufacturing environment. The data for this study is collected from the wheel bolting machine of an automotive factory and consists of process parameters already recorded by the current system. The data retrieved from the system is unlabeled, time-series based and records the torque, angle, and time from the bolting process. During this period, the failure rate of one nutrunner was significantly higher than the others. After changing the socket, the machine showed a 2% improvement and the bolting graphs returned to the expected format. This thesis aims to retrospectively establish if the failure was predictable from the data by using clustering algorithms. The study includes a critical analysis of the mechanical machine-train of the nutrunner system based on literature and domain knowledge. A failure analysis is done to understand the key characteristics of common failures as identified on the bolting process curves. Due to the format of the data, a comprehensive data exploration phase had to be conducted to find and understand the outliers and data quality. Furthermore, the required features for the dataset used during modelling had to be designed. The clustering algorithms investigated are agglomerative hierarchical clustering (AHC), density-based spatial clustering of applications with noise (DBSCAN) and a selforganising feature map (SOFM). Each algorithm underwent extensive parameter optimisation and fine-tuning in order to establish the best clusters. The performance metrics used to compare and evaluate the clusters were the silhouette coefficient score (SC) and variation rate criterion (VRC). The SOFM clustering performed the best and the resulting clusters were used to further perform clustering analysis. The cluster analysis showed promising results as the clusters were well-defined and decipherable using domain knowledge. The results of this thesis show that it is feasible to use clustering to improve the maintenance strategy of nutrunners in the automotive industry.
  • Thumbnail Image
    Item
    Estimating the remaining useful lifetime of a vertical gripper by using prognostics and health management
    (Stellenbosch : Stellenbosch University, 2023-02) Mert, Serkan; Jooste, Wyhan; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering. Engineering Management (MEM).
    ENGLISH ABSTRACT: Industrial systems are becoming extremely complex in order to meet the increasing requirements in production environments. The use of flexible end effectors helps to support humans in the context of industrial evolution. Grippers are one of the most widely used groups of end effectors. Like all other systems that execute transferring work, grippers exhibit degradation behavior. The property of degradation must be counteracted with appropriate maintenance work to enable a reliable production process. One field of research within prognostics and health management is the estimation of the remaining useful lifetime for such industrial systems and their components. Many successful applications have already been published, but research is striving to extend this to as yet untreated industrial systems and components. In this context, this research study introduces a method to estimate the remaining useful lifetime for a vertical robotic gripper. For the development of the method, a literature study is conducted, which lists and explains the existing approaches. Based on the selection of an individual vertical gripper, an experimental setup is developed. The experimental setup obtains data in regards to the gripper force. The obtained data is then used to indicate degradation and determine the failure thresholds. With the support of a prediction model, further degradation is forecasted and compared to the failure thresholds. This approach concludes the estimation about the remaining useful lifetime. The overall objective of this information is to support a demand-oriented adjustment of the maintenance measures.
  • Thumbnail Image
    Item
    The interaction of human, information and technology components in real time physical asset management
    (Stellenbosch : University of Stellenbosch, 2007-03) Grove, Christiaan; Von Leipzig, Konrad; University of Stellenbosch. Faculty of Engineering. Dept. of Industrial Engineering.
    The last untapped margin of improvement in the manufacturing process is believed to be the improvement of physical asset maintenance. The latest opportunity is to move this process to a real time system. Although in recent years it has become somewhat of a cliché, the successful management of the human factor is one of the most critical components, and also one of the most difficult to manage, in all improvement projects. By combining the groundbreaking opportunity in Asset Performance Management with an enthusiasm for people and process improvement, the focus of this research is found. The motivation stems from a realization that Asset Performance Management will undergo radical changes and that it would not be sufficient to apply the traditional methods of managing change to the younger generations, that are currently entering the workforce and that would have to run this improved system. The industry trend was studied in order to better facilitate a solution that would suit this natural evolution. Specifically, trends were studied on Human, Information and Technology levels since background studies have shown that these three components are key to the Physical Asset Performance Management scenario. Through an in-depth literature study, the answers to the predetermined research questions were determined. To guide companies through the transition towards the real time enterprise as well as improve overall machine performance (research origin), the HIT Interaction model for real time Physical Asset Performance Management is proposed. A structure is also facilitated by which companies can be evaluated in terms of the stages of readiness for real time operation. This enables them to establish where they currently are and what strategic steps to take in order to reach the next level.