PumpSpectra: An MCSA-Based Platform for Fault Detection in Centrifugal Pump Systems

Highlights What are the main findings? PumpSpectra achieved 91.2% accuracy and rapid diagnostics for centrifugal pump faults in industry. It introduces an explainable, rule-based platform with severity grading for major pump faults. What is the implication of the main finding? Enables cost-saving, sensor-minimal predictive maintenance for pump assets. Supports transparent, trusted decisions for industrial maintenance teams.Highlights What are the main findings? PumpSpectra achieved 91.2% accuracy and rapid diagnostics for centrifugal pump faults in industry. It introduces an explainable, rule-based platform with severity grading for major pump faults. What is the implication of the main finding? Enables cost-saving, sensor-minimal predictive maintenance for pump assets. Supports transparent, trusted decisions for industrial maintenance teams.Abstract Reliable detection of faults in centrifugal pump systems is challenging in industrial environments due to harsh operating conditions, limited sensor access, and the need for fast, explainable decisions. We developed PumpSpectra, an industrial Motor Current Signature Analysis (MCSA) platform that processes uploaded stator-current CSV files using FFT/STFT with transparent, rule-based models designed to identify mechanical faults including misalignment, bearing defects, and impeller anomalies; field validation demonstrated misalignment detection. In a case study at the El Oued desalination plant (Algeria; n=40 operating points), PumpSpectra achieved 91.2% diagnostic accuracy with a 95% reduction in analysis time compared to manual MCSA post-processing, and a false-positive rate of 3.8% at 0.1 Hz resolution. These results suggest that current-only, explainable analytics can support predictive maintenance programs by accelerating fault triage, improving traceability of decisions, and reducing avoided maintenance costs in pump-driven industrial assets.