Centrifugal Pump Rotor Dynamics for Fast Anomaly Detection

Solution Overview

Problem

Existing methods for detecting anomalies in centrifugal pumps, particularly blockages, are not reliable and timely, leading to potential damage and inefficiencies.

Innovation Solution

A computer-implemented method that accelerates and decelerates the rotor of a centrifugal pump to quantify a dynamic rotor model, identifies disturbance parameters through an inverse problem, and classifies anomalies using a digital twin model to facilitate quick unblocking routines.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional anomaly detection methods are used in centrifugal pumps, then the detection process is simple, but the reliability and timeliness of anomaly detection is insufficient

Engineering Contradiction:

Improveanomaly detection reliabilityVSAvoiddetection system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-accelerating the rotor to a target rotational speed before the actual measurement phase. This pre-acceleration ensures that the rotor reaches the optimal operating point for anomaly detection, allowing the detection system to capture disturbance parameters at the most sensitive moment. The controller pre-plans and executes the acceleration sequence, ensuring that when measurement begins, the rotor is already at the predetermined speed where anomalies manifest most clearly, thereby improving detection reliability without requiring complex real-time speed control during measurement.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements dynamics by continuously varying the rotational speed of the rotor during the measurement phase. Instead of measuring at a fixed speed, the rotor speed is dynamically changed according to a predetermined sequence, allowing the system to capture how disturbance parameters evolve with speed. This dynamic approach enables the detection system to identify anomalies across multiple operating points, significantly improving detection reliability and timeliness while using standard sensors and controllers.

Inventive Principle:

Principle #15Dynamics

2Measurement precision

If the rotor is accelerated and decelerated to quantify dynamic rotor model terms, then the detection accuracy improves, but the detection time increases

Engineering Contradiction:

Improvedisturbance parameter detection accuracyVSAvoidanomaly detection time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-accelerating the rotor to a target rotational speed before the actual measurement phase. This pre-acceleration ensures that the rotor reaches the optimal operating point for anomaly detection, allowing the detection system to capture disturbance parameters at the most sensitive moment. The controller pre-plans and executes the acceleration sequence, ensuring that when measurement begins, the rotor is already at the predetermined speed where anomalies manifest most clearly, thereby improving detection reliability without requiring complex real-time speed control during measurement.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements skipping by rapidly transitioning the rotor through intermediate speed states and focusing measurements only at the critical target speed range where anomalies are most detectable. Instead of slowly sweeping through all possible speeds, the system accelerates directly to the optimal detection point, performs measurements, then decelerates. This rushing through of non-critical speed ranges significantly reduces detection time while maintaining high measurement precision at the critical operating point.

Inventive Principle:

Principle #21Skipping (Rushing through)

3Reliability

If disturbance parameters are detected during fault state, then anomaly classification improves, but the operational disruption increases

Engineering Contradiction:

Improveanomaly classification accuracyVSAvoidpump operational efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent applies periodic action by implementing scheduled detection cycles where the rotor is accelerated to measurement speed, disturbance parameters are detected, and then the system returns to normal operation. This periodic detection approach allows the pump to maintain high productivity during normal operation while periodically pausing to perform quick anomaly detection. The detection cycles are optimized to be as short as possible, minimizing operational disruption while ensuring reliable anomaly classification through repeated measurements at critical speed points.

Inventive Principle:

Principle #19Periodic action

Data Source

PatentEP4647606A1Computer-implemented method for detecting and/or determining an anomaly of a centrifugal pump

Publication Date: 2025.11.12 WILO SE

Figure 1
Figure 2

AI summary

The invention relates to a computer-implemented method for detecting and/or determining an anomaly of a centrifugal pump (1), comprising the steps: in a normal state, accelerating and/or decelerating a rotor (4) of the centrifugal pump (1) to quantify at least one term of a dynamic rotor model of the centrifugal pump (1); in a fault state deviating from the normal state, accelerating and/or decelerating the rotor (4) of the centrifugal pump (1) to detect at least one disturbance parameter; and solving an inverse problem of the dynamic rotor model to identify the at least one disturbance parameter for detecting and/or determining the anomaly.