Non-intrusive low-cost IoT-based hardware system for sustainable predictive maintenance of industrial pump systems

Brito, Sergio; Azinheira, Gonçalo; Semião, Jorge; Sousa, Nelson; Pérez Litrán, Salvador

http://hdl.handle.net/10400.1/27786

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
electronics-14-02913-v2 (1).pdf		6.79 MB	Adobe PDF	Download

Send Feedback

Authors

Pérez Litrán, Salvador

Abstract(s)

Industrial maintenance has shifted from reactive repairs and calendar-based servicing toward data-driven predictive strategies. This paper presents a non-intrusive, low-cost IoT hardware platform for sustainable predictive maintenance of rotating machinery. The system integrates an ESP32-S3 sensor node that captures vibration (100 kHz) and temperature data, performs local logging, and communicates wirelessly. An automated spectral band segmentation framework is introduced, comparing equal-energy, linear-width, nonlinear, clustering, and peak-valley partitioning methods, followed by a weighted feature scheme that emphasizes high-value bands. Three unsupervised one-class classifiers-transformer autoencoders, GANomaly, and Isolation Forest-are evaluated on these weighted spectral features. Experiments conducted on a custom pump test bench with controlled anomaly severities demonstrate strong anomaly classification performance across multiple configurations, supported by detailed threshold-characterization metrics.