Vibration Analysis in Industry 4.0: Machine Learning, Energy Harvesting, and Bibliometric Analysis

Abstract

This research investigates the significance of bibliometric analysis, energy harvesting, and machine learning and diagnostic techniques to machine vibration analysis within the context of Industry 4.0. The study highlights the importance of early detection of machine defects and issues in reducing the likelihood of downtime and costly repairs and ensuring the optimal performance of industrial operations. Energy harvesting systems, machine learning, and diagnostic procedures are only some of the technologies used in the research of machine vibration analysis. Using these methods, it has been demonstrated that vibration patterns in machines can be analyses and predicted, that mechanical vibration energy can be converted into electrical energy, and that energy costs can be lowered. The study also includes a bibliometric analysis of the literature based on VOSviewer. Linear vibration, non-linear vibration, and vibration analysis are some of the topics it explores as it surveys the literature on vibration analysis of machines. Future research directions are proposed, and new perspectives on the current status of the field's study are provided. Practical implications for academics, professionals, and decision-makers in engineering and technology domains are derived from the study's findings, which call attention to the necessity for further study and improvement of machine vibration monitoring in Industry 4.0. This research contributes to the existing literature by providing valuable insight into the potential impacts of energy harvesting, machine learning, and bibliometric analysis on business processes.