Real-Time Machine Performance Visualisation & Monitoring in Smart Manufacturing: A Dual-Tool Approach

Sammanfattning

This study investigates the implementation and effectiveness of real-time machine performance monitoring within a dynamic manufacturing environment. It highlights the critical role of data visualization in enhancing machine transparency and operator decision-making so that it can be used to improve overall production efficiency. Adopting a mixed-methods approach, the research seamlessly combines quantitative analysis of key performance indicators with rich qualitative insights acquired through operator interviews and detailed observational studies. Quantitative analysis employs various techniques, utilizing descriptive statistics to outline data trends, explore relationships, and assessing the impact of visualization strategies on machine performance. In parallel, qualitative analysis applies thematic analysis to dissect interview responses alongside user experience evaluations of dashboards. This dual focus allows researchers to comprehensively understand how effectively operators can use real-time KPI visualizations, considering usability and interpretability. To ensure the robustness of the findings, the study employs data triangulation, pilot testing, and expert validation throughout the research process. It also addresses critical ethical considerations, including safeguarding data security, ensuring participant anonymity, obtaining informed consent, and adhering to institutional review board guidelines. The main goal of this research is to offer practical guidelines for implementing effective realtime machine performance monitoring systems. It aims to provide valuable insights regarding the intricate quality of data relationship visualizations and their influence on operators' decisionmaking processes and production efficiency. Furthermore, the study introduces a structured comparative framework designed to evaluate the effectiveness of popular tools, such as Power BI and Grafana, while exploring Raspberry Pi-based IoT data acquisition methods. Through this comparative analysis, the researchers aim to uncover each tool's distinct roles, strengths, and potential integration challenges within real-time machine performance monitoring in smart manufacturing. The study also discusses the growing importance of artificial intelligence, especially for analyzing large amounts of data, as industries get ready to leverage the data collected by manufacturing companies daily. Incorporating AI-powered analytics to enhance the capabilities of real-time machine performance monitoring systems will enable more advanced insights and predictive capabilities in the future.