From Sensor to Service: Leveraging Data and Experience for Targeted Solutions

In Industry 4.0, the Internet of Things produces a large amount of data, creating new opportunities to improve manufacturing efficiency and proactive maintenance. However, the high volume and complexity of them present significant challenges. This thesis explores a practical method to tackle these problems by extracting data from IoT devices, processing them, and using Power BI to develop a comprehensive Dashboard for a selected model of woodworking machines. The main goal is to create a Dashboard that displays Key Performance Indicators, incorporating an Overall Performance gauge and an automated reporting system. This method uses domain expertise to convert knowledge into programmed rules, ensuring a meaningful representation of the data. The research involves extracting data from IoT devices using SQL, followed by processing and manipulation with Python to prepare the data for analysis. The analytical process will use rule-based insights to identify patterns, trends, and anomalies, which can guide proactive maintenance strategies to improve operational efficiency. Power BI visualizes the data, making the findings accessible and highlighting areas for improvement within the domain, both for the company and the clients. This research offers an example of a practical framework that integrates domain expertise with data analysis and visualization tools with the possibility to be extended to different scenarios. Providing insights for the manufacturing industry, especially in the woodworking field. Demonstrating how companies can benefit from IoT data to allow new types of maintenance and achieve operational efficiency within products and services.