Digital Twin-Enabled IoT Architecture for Early Fault Detection and Integrated Forklift Monitoring Using an ESP32 Platform

Jacha H.R.B.; Acuña E.H.A.; Acosta A.K.N.; Becerra Felipe J.L.; Rivas J.R.R.; Carrizales Navarro J.A. · Proceedings of the 2025 IEEE 32nd International Conference on Electronics, Electrical Engineering and Computing, INTERCON 2025 (2025) · DOI: 10.1109/intercon67304.2025.11244693

Resumen

This study proposes an intelligent forklift monitoring system based on the implementation of a low-cost Digital Twin using an ESP32 microcontroller and critical variable sensors. The main objective is to detect potential failures early and provide real-time operational data to improve fleet management in heavy equipment rental companies. The developed architecture records data on fuel level, GPS location, traveled distance (via wheel revolutions), engine temperature, exhaust temperature, and levels of pollutant gas emissions (CO and CO2). These data are transmitted to a web interface for remote visualization and analysis. The methodology integrates multisensor data acquisition, local processing via ESP32, and digital modeling of forklift behavior under real operating conditions. A configurable alert system is included and integration with machine learning algorithms is proposed for failure prediction. As a result, an effective synchronization was achieved between the physical state of the forklift and its digital representation, allowing continuous monitoring from any location. The system was shown to be functional, scalable and applicable to operating fleets, thereby enabling the development of accessible predictive maintenance solutions in demanding logistics contexts.

Instituciones: Universidad Peruana de Ciencias Aplicadas