Speakers
Description
In this work, a methodology is presented for the advanced validation of KPI-based condition monitoring systems applied to industrial robotics. The proposed approach is demonstrated through a test case involving an industrial robotic arm equipped with ICP accelerometers for high-fidelity vibration measurements. The acquired signals are collected by a high-speed DAQ system and processed in real time on a Raspberry Pi used as an edge computing device. Digital signal processing techniques, including filtering, spectral analysis, Fast Fourier Transform, and statistical feature extraction, are applied to generate health-related KPIs associated with robotic joint conditions. The validation methodology assesses sensor reliability, signal processing robustness, KPI sensitivity, repeatability, false alarm rate, and diagnostic capability. The extracted indicators are transmitted via MQTT to an IIoT platform for remote monitoring, historical analysis, and maintenance alert generation. The test case aims at demonstrating the effectiveness of the methodology for early fault detection and predictive maintenance in Industry 4.0 environments.