Modeling and Physics-Enhanced Fault Detection in Wastewater Pump Stations

TL;DR

This work introduces a physics-enhanced, parameter-driven simulator for a three-pump wastewater station that captures transient hydro-electro-mechanical dynamics at 1-second resolution and supports data-driven fault diagnostics. It integrates affinity-law-scaled pump curves with a system curve and explicit soft-start/stop control, enabling realistic what-if analyses and balanced faulty dataset generation. The paper develops two fault-origin indicators—a nested-model F-test and a tangent residual index—that distinguish pump degradation from system faults using only flow, head, and frequency, and validates them on simulated data with online applicability. Validation against high-frequency SCADA data demonstrates strong fidelity in hydraulic and operational metrics, while the diagnostic methods show robust discrimination between pump and system faults, supporting timely maintenance and spare-parts planning.

Abstract

Monitoring wastewater pump stations is essential because they are critical infrastructure. However, monitoring is still often performed manually due to the lack of suitable algorithmic methods and data. This paper introduces a high-fidelity, physics-enhanced simulator of a three-pump wastewater station that captures transient hydro-mechanical dynamics at a one-second resolution. The simulator is fully parameter-driven, adaptable to other wastewater stations, and capable of generating datasets for data-driven analytics. It can also generate balanced faulty datasets when real failures are scarce or confidential. A comparison with high-frequency SCADA data from a municipal station shows strong agreement across key operational metrics. Furthermore, the paper proposes robust statistical and mathematical frameworks for fault detection and isolation, including a nested-model F-test to detect pump degradation or system faults, and a tangent residual approach to distinguish pump faults from system faults using operating-point kinematics. This framework enables what-if studies, facilitates early fault diagnosis based on flow rate and head, and provides actionable insights for condition-based maintenance in wastewater pumping infrastructure.

Figures (23)

• Figure 1: The typical configuration of a submersible wastewater pump station inspired from FlygtBrochure2024. The wastewater pump station consists of (A) float switches, (B) outflow, (C) possible position of a flow rate sensor, (D) sump, (E) inflow, (F) possible position of a flow rate sensor, (G) pump, and (H) possible position of a pressure sensor.
• Figure 2: Operating point is the intersection of pump curve (blue) and system curve (green).
• Figure 3: Operating point shift along the system curve during pump blockage.
• Figure 4: Operating point shift along the pump curve caused by valve throttling.
• Figure 5: Observed inflow rate distribution from real-time monitoring data.