Title: AI, Innovation and Global Transformation: Interdisciplinary Perspectives on Technology, Business and Society
Editors: Dr. J. Preetha, and Dr. Siddhartha Mehrotra
ISBN: 978-81-69857-64-2
Chapter: 16
DOI: https://doi.org/10.59646/809/16
Author: S. Sivakumar
Abstract
Modern industrial environments demand continuous operational reliability, elevated safety thresholds, and minimized downtime for rotary machinery. This chapter presents an end-to-end framework for IoT-enabled condition monitoring and automated fault diagnostics across mission-critical assets. Integrating smart multi-modal sensor nodes—encompassing triaxial MEMS accelerometers, wideband piezoelectric vibration sensors, infrared thermography, acoustic emission (AE) transceivers, and motor current signature analysis (MCSA) probes—the system captures high-bandwidth degradation signatures. Sensor data is processed via an edge-computing gateway utilizing localized feature extraction, edge inference, and an energy-efficient MQTT-SN communication pipeline linked to a cloud analytics core. Empirical validation on high-speed induction motors and planetary gearboxes operating over a 12-month operational period demonstrates that this multi-modal edge-cloud IoT architecture yields a 99.1% fault classification accuracy. It reduces network bandwidth consumption by 78.4% via adaptive compressive sensing, detects micro-faults up to 340 operating hours prior to catastrophic failure, and mitigates unscheduled downtime by 38.6%.
Keywords: Smart Sensors; Industrial Internet of Things (IIoT); Condition Monitoring; Vibration Analysis; Edge Computing; Predictive Maintenance.