Pump Fault Monitoring Using Differential Volume Decision Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing pump monitoring systems require the identification of numerous parameters to associate a current operating state with fault scenarios, making it difficult to quickly identify and address issues in pump systems, especially in systems with multiple pumps.
Innovation Solution
A pump monitoring system that uses an interface module to receive operational values and a processing module to determine a decision vector, which compares the actual operating state to a non-faulty model, reducing the number of parameters needed by modeling the differential volume in the m-dimensional operating space, allowing for the association of the current state with fault scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple parameters are monitored to reliably identify fault scenarios in pump systems, then the reliability of fault detection is improved, but the complexity of the monitoring system and the difficulty of parameter identification increase
Solution Approach 1:
The patent extracts only the essential information needed for fault detection by monitoring the operating point in an m-dimensional space rather than analyzing multiple individual parameters. The differential volume calculation extracts the deviation from normal operation in a condensed form, eliminating the need to process and identify numerous separate parameters while maintaining reliable fault detection capability.
Solution Approach 2:
The patent transforms multiple operational parameters into a single differential volume parameter that represents the deviation from normal pump characteristic. By changing the parameter representation from multiple individual measurements to a consolidated volume metric, the system achieves reliable fault detection without requiring complex multi-parameter analysis.
2Measurement precision
If multiple parameters are monitored to associate operating state with fault scenarios, then the accuracy of fault identification is improved, but the time required for analysis and response increases
Solution Approach 1:
The patent extracts the essential fault information by calculating the differential volume that directly represents deviation from normal operation. This extraction method provides accurate fault identification without requiring time-consuming analysis of multiple parameters, as the differential volume immediately indicates when and where the operating point deviates from the pump characteristic.
Solution Approach 2:
The patent establishes the pump characteristic in the m-dimensional operating space in advance during normal operation. This preliminary modeling allows for immediate fault detection by simply comparing the current operating point against the pre-established characteristic, eliminating the need for real-time complex analysis and enabling rapid fault response.
3Adaptability or versatility
If comprehensive monitoring of pump system parameters is implemented, then the completeness of fault scenario coverage is improved, but the difficulty of identifying and processing parameters increases
Solution Approach 1:
The patent creates a universal monitoring approach that works for various fault scenarios by establishing the pump characteristic in an m-dimensional operating space. This single framework can detect different types of faults (clogging, leakage, mechanical failures) without requiring separate parameter identification methods for each scenario, providing comprehensive coverage while simplifying the monitoring process.
Solution Approach 2:
The patent transforms the monitoring approach by changing from identifying multiple specific parameters for different fault types to monitoring the differential volume in the m-dimensional space. This parameter transformation provides universal fault detection capability while eliminating the difficulty of identifying and processing numerous parameters for different fault scenarios.
Data Source
Figure 1a~1b
Figure 2
Figure 3
AI summary
A pump monitoring system for associating a current operating state of a pump system (1) comprising n ≥ 1 pumps (3) with one or more of k ≥ 1 fault scenarios, wherein the pump monitoring system comprises - an interface module for receiving at least one set of m ≥ 2 operational values from the pump system, wherein the m operational values define a current operational point in an m-dimensional operating space, and - a processing module (11) for processing the operational values received by the interface module, wherein the processing module (11) is configured to consult given or determined model parameters describing a non-faulty model pump characteristic in the m-dimensional operating space, wherein the processing module (11) is further configured to determine a k-dimensional decision vector with k decision vector components being indicative of a deviation between - an actual differential volume in the m-dimensional operating space based on distances between the m operational values and the non-faulty model pump characteristic, and - a modelled differential volume in the m-dimensional operating space for the respective fault scenario.