We present a detailed dataset collected via a wireless IoT sensor network monitoring three industrial centrifugal pumps (units A, B, and C) at the Italian Aerospace Research Centre (CIRA), along with the methods for data collection and structuring. Background: Centrifugal pumps are critical in industrial plants, and monitoring their condition is essential to ensure reliability, safety, and efficiency. High-quality operational data under normal operating conditions are fundamental for developing effective maintenance strategies and diagnostic models. Methods: Data were gathered by means of smart sensors measuring motor and pump vibrations, temperatures, outlet fluid pressures, and environmental conditions. Data were transmitted over a WirelessHART mesh network and acquired through an IoT architecture. Results: The dataset consists of eight CSV files, each representing a specific pump during a distinct operational day. Each file includes timestamped measurements of displacement, peak vibration values, sensor temperatures, fluid pressure, ambient temperature, and atmospheric pressure. Conclusions: This dataset supports advanced methodologies in feature extraction, multivariate signal analysis, unsupervised pattern discovery, vibration analysis, and the development of digital twins and soft sensing models for predictive maintenance optimization.
This paper proposes an interpretable framework for industrial condition monitoring, enabling a three-level understanding of machinery behaviour (machine, context, and system). Using multivariate time-series from a WirelessHART sensor network, the framework combines transparent data-mining and statistical-learning components (density-based clustering, principal component analysis, variable-importance modelling, and time-series dependency analysis) to extract readable patterns and rules describing operational dynamics. Unlike approaches that treat machine, context, or system levels in isolation, the proposed workflow unifies them within a single analytical scheme built around intrinsically interpretable modules. At the machine level, DBSCAN and PCA identify and characterise distinct operational states and enable compact decision rules; at the context level, the Kolmogorov-Smirnov test and a consensus ranking of variable importance quantify campaign-to-campaign drift and highlight the role of environmental variables; at the system level, Granger test and cross-correlation analysis identify short-lag directional predictive relationships between concurrently operating machines. The framework is demonstrated on three centrifugal pumps monitored across multiple campaigns in an industrial plant. All data are publicly available, enabling full replication.