Centrifugal Pump Rotor Modeling for Reliable Blockage Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting anomalies in centrifugal pumps, particularly blockages, are not reliable and timely, leading to potential damage and inefficiency.
Innovation Solution
A computer-implemented method that accelerates and decelerates the rotor of a centrifugal pump to quantify a dynamic rotor model, identifies fault parameters by solving an inverse problem, and classifies anomalies using a digital twin, enabling rapid unblocking routines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional anomaly detection methods are used in centrifugal pumps, then the detection process is simple, but the reliability and timeliness of anomaly detection is insufficient
Solution Approach 1:
The patent applies preliminary action by pre-accelerating the rotor to a target rotational speed before the actual measurement process. This allows the system to quantify the dynamic rotor model and establish a baseline for normal operation in advance, enabling more reliable anomaly detection during actual pumping operations without repeatedly subjecting the rotor to high-speed acceleration.
Solution Approach 2:
The patent replaces traditional mechanical anomaly detection methods with a computational approach. By using a dynamic rotor model and solving inverse problems based on measured acceleration and torque data, the system substitutes physical inspection and simple mechanical tests with mathematical modeling and data analysis, significantly improving detection reliability and timeliness.
2Measurement precision
If the rotor is accelerated to quantify the dynamic rotor model in normal state, then the model accuracy is improved, but the time required for detection increases
Solution Approach 1:
The patent applies preliminary action by performing the time-consuming rotor acceleration and dynamic model quantification during a preliminary phase when the pump is known to be in normal condition. This establishes the dynamic rotor model in advance, so that during actual operation, only brief measurements of acceleration and torque are needed to detect anomalies by comparing against the pre-established model, significantly reducing detection time while maintaining high accuracy.
3Measurement precision
If fault parameters are detected by accelerating the rotor in fault state, then the anomaly classification accuracy is improved, but the productivity of the pump decreases
Solution Approach 1:
The patent applies the skipping principle by rapidly accelerating the rotor to the target speed and immediately performing measurements, rather than allowing the system to reach steady state. This rushed-through approach captures the dynamic characteristics during the acceleration phase itself, enabling fast anomaly detection and classification without prolonged interruption to pump productivity, while still achieving high classification accuracy through the dynamic rotor model.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enhances the detection and classification of anomalies, particularly blockages, allowing for faster and more efficient unblocking of centrifugal pumps, reducing downtime and damage.
Implementation Method 1
accelerating and/or decelerating a rotor of the centrifugal pump for quantifying at least one term of a dynamic rotor model
Implementation Method 2
accelerating and/or decelerating the rotor of the centrifugal pump for detecting at least one fault parameter
Data Source
AI summary
A computer-implemented method for detecting and/or determining an anomaly in a centrifugal pump includes the steps: in a normal state, accelerating and/or decelerating a rotor of the centrifugal pump for quantifying at least one term of a dynamic rotor model of the centrifugal pump, in a fault state differing from the normal state, accelerating and/or decelerating the rotor of the centrifugal pump for detecting at least one fault parameter, and solving an inverse problem of the dynamic rotor model for identifying the at least one fault parameter for detecting and/or determining the anomaly.

