# US 2024/0004377 A1 · A pump monitoring system and method for associating a current operating state of a pump system with one or more fault scenarios

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0004377 A1
- Document ID: US20240004377A1
- Status: Published application
- Kind: A1
- Application number: 18/037,366
- Filed: 2021-11-29
- Published: 2024-01-04
- Earliest claimed: 2020-12-23
- Assignees: Grundfos Holding A/S
- Applicants: Grundfos Holding A/S
- Inventors: Carsten Skovmose KALLESØE; Abdul-Sattar HASSAN; Jan Carøe AARESTRUP
- Web page: https://patentgrep.com/patent/US20240004377A1

## CPC

- F04D 15/0088: {Testing machines}
- G05B 23/0221: {Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods}
- F04D 15/029: {for pumps operating in parallel}
- G05B 23/024: {Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks}
- E03F 5/22: Adaptations of pumping plants for lifting sewage (wheeled apparatus for emptying sewers or cesspools E03F7/10; pumps, pumping plants, per se F04)
- F04D: NON-POSITIVE-DISPLACEMENT PUMPS (engine fuel-injection pumps F02M; ion pumps H01J41/12; electrodynamic pumps H02K44/02)
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- E03F: SEWERS; CESSPOOLS

## Abstract

A pump monitoring system associates a current operating state of a pump system including n≥1 pumps with one or more of k≥1 fault scenarios. The pump monitoring system includes an interface module for receiving at least one set of m≥2 operational values from the pump system. The m operational values define a current operational point in an m-dimensional operating space. A processing module processes operational values received by the interface module and consults given or determined model parameters describing a non-faulty model pump characteristic in the m-dimensional operating space and determines a k-dimensional decision vector with k decision vector components 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 modeled differential volume in the m-dimensional operating space for the respective fault scenario.

## Claims

### Claim 1

A pump monitoring system for associating a current operating state of a pump system comprising n≥1 pumps 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 for processing the operational values received by the interface module,
wherein the processing module 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 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 modeled differential volume in the m-dimensional operating space for the respective fault scenario.

### Claim 2 (depends on 1)

The pump monitoring system according to claim 1, wherein the n≥1 pumps of the pump system comprise one or more submersible pumps and/or wastewater pumps and/or booster pumps.

### Claim 3 (depends on 1)

The pump monitoring system according to claim 1, wherein each decision vector component is a scalar on a normalized scale, wherein the normalized scale is identical for all decision vector components.

### Claim 4 (depends on 1)

The pump monitoring system according to claim 1, wherein the processing module is configured to model the modeled differential volume by a model function comprising one or two variation parameters, wherein the processing module is configured to vary the one or two variation parameters for fitting the modeled differential volume to the actual differential volume.

### Claim 5 (depends on 1)

The pump monitoring system according to claim 1, wherein the processing module is configured to minimize the deviation between the modeled differential volume and the actual differential volume.

### Claim 6 (depends on 5)

The pump monitoring system according to claim 5, wherein the k decision vector components are indicative of a residual deviation after minimizing the deviation between the modeled differential volume and the actual differential volume.

### Claim 7 (depends on 1)

The pump monitoring system according to claim 1, wherein the processing module is configured to associate the current operating state with only those of the k fault scenarios for which the respective decision vector component has passed a pre-determined threshold.

### Claim 8 (depends on 1)

The pump monitoring system according to claim 1, wherein the processing module is configured to associate the current operating state with exactly one of k≥2 fault scenarios if the respective decision vector component for said fault scenario differs from a closest one of the other decision vector components by at least a pre-determined difference.

### Claim 9 (depends on 1)

The pump monitoring system according to claim 1, wherein the processing module is configured to command the pump system to run at another operational point in the m-dimensional operating space if none of k≥2 decision vector components differs from a closest one of the other decision vector components by at least a pre-determined difference.

### Claim 10

A method for associating a current operating state of a pump system comprising n≥1 pumps with one or more of k≥1 fault scenarios, wherein the method comprises:
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,
processing the operational values,
consulting given or determined model parameters describing a non-faulty model pump characteristic in the m-dimensional operating space,
determining 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 modeled differential volume in the m-dimensional operating space for the respective fault scenario, and
displaying at least one of the k decision vector components for the respective fault scenario.

### Claim 11 (depends on 10)

The method according to claim 10, wherein the n≤1 pumps of the pump system comprise one or more submersible pumps and/or wastewater pumps and/or booster pumps.

### Claim 12 (depends on 10)

The method according to claim 10, wherein each decision vector component is a scalar on a normalized scale, wherein the normalized scale is identical for all decision vector components.

### Claim 13 (depends on 10)

The method according to claim 10, wherein the modeled differential volume is modeled by a model function comprising one or two variation parameters, wherein the one or two variation parameters are varied for fitting the modeled differential volume to the actual differential volume.

### Claim 14 (depends on 10)

The method according to claim 10, wherein the deviation between the modeled differential volume and the actual differential volume is minimized.

### Claim 15 (depends on 14)

The method according to claim 14, wherein the k decision vector components are indicative of a residual deviation after minimizing the deviation between the modeled differential volume and the actual differential volume.

### Claim 16 (depends on 10)

The method according to claim 10, further comprising associating the current operating state to only those of the k fault scenarios for which the respective decision vector component has passed a pre-determined threshold.

### Claim 17 (depends on 10)

The method according to claim 10, further comprising associating the current operating state to exactly one of k≥2 fault scenarios if the respective decision vector component for said fault scenario differs from a closest one of the other decision vector components by at least a pre-determined difference.

### Claim 18 (depends on 10)

The method according to claim 10, further comprising commanding the pump system to run at another operational point in the m-dimensional operating space if none of k≥2 decision vector components differs from a closest one of the other decision vector components by at least a pre-determined difference.

### Claim 19 (depends on 10)

The method according to claim 10, wherein the deviation between the modeled differential volume and the actual differential volume is minimized by applying a least-squared method.

### Claim 20 (depends on 1)

The pump monitoring system according to claim 1, wherein the processing module is configured to minimize the deviation between the modeled differential volume and the actual differential volume by applying a least-squared method.
