Development of IoT Systems for Real–Time Assessment of Vibration Signals in a Generator

Abstract

The assessment of vibration signals in automotive generators is crucial for ensuring operational efficiency, reliability and predictive maintenance. Excessive vibrations can lead to mechanical failures, energy losses and reduced generator lifespan. However, traditional vibration monitoring methods often rely on periodic manual inspections, which are time-consuming, expensive and inefficient for real-time diagnostics. To address this issue, this study focuses on the development of an IoT-based system for real-time vibration signal assessment in automotive generators. The methodology involves designing and implementing a wireless sensor network integrated with microcontrollers and accelerometers to capture vibration signals continuously. The collected data is transmitted to a cloud-based platform for real-time processing and analysis using machine learning algorithms. The system employs edge computing techniques to enhance data processing speed and reduce latency. A prototype is tested in a controlled environment to evaluate its performance in detecting abnormal vibration patterns and predicting potential faults. The justification for this study lies in the increasing demand for intelligent and automated monitoring solutions in modern automotive power systems. By leveraging IoT technology, this research provides a cost-effective, scalable, and efficient alternative to conventional vibration monitoring techniques, contributing to improved energy efficiency and reliability of generators. The results demonstrate that the developed IoT system effectively detects and analyzes vibration anomalies in real time, enabling early fault detection and reducing maintenance costs. In conclusion, the proposed system enhances the predictive maintenance capabilities of automotive generators, ensuring longer operational life and reduced downtime. It was recommended that future research explore the integration of advanced artificial intelligence models for more accurate predictive analytics and the implementation of this system in real-world automotive applications to validate its robustness and scalability.