Brito, SergioAzinheira, GonçaloSemião, JorgeSousa, Nelson2026-05-252026-05-252024-12-08http://hdl.handle.net/10400.1/29029This paper presents a cost-effective, Internet of Things (IoT)-based solution for predictive maintenance (PdM) in industrial pumping systems. The proposed system integrates custom-built hardware with machine learning (ML) algorithms to monitor and detect anomalies in real-time. The innovation of the system lies in its non-intrusive design, ease of installation, and adaptability to a variety of industrial environments, providing a practical, low-cost alternative to traditional PdM solutions. Detailed discussion is provided on the hardware component selection, which prioritizes affordability without sacrificing performance, as well as the machine learning strategies used for anomaly detection. Preliminary results from laboratory and field testing demonstrate the system’s potential for reducing downtime and maintenance costs, with a focus on extending the application to broader industrial contexts.engPredictiveMaintenanceInternet of thingsMachine learningIndustrial monitoringAnomaly detectionconference object10.1109/oncon62778.2024.10931406