# US 2024/0003352 A1 · Adaptive Learning System for Improving Sump Pump Control

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

- Number: US 2024/0003352 A1
- Document ID: US20240003352A1
- Status: Published application
- Kind: A1
- Application number: 18/369,009
- Filed: 2023-09-15
- Published: 2024-01-04
- Earliest claimed: 2021-02-12
- Assignees: State Farm Mutual Automobile Insurance Company
- Applicants: State Farm Mutual Automobile Insurance Company
- Inventors: Nathan L. Tofte; Jonathan Christopher Hull; John R. Donovan; Richard Jan Tjaden
- Web page: https://patentgrep.com/patent/US20240003352A1

## CPC

- F04D 15/0227: {Lack of liquid level being detected using a flow transducer}
- F04D 13/08: for submerged use
- F04D 13/086: {the pump and drive motor are both submerged}
- F04D 13/12: Combinations of two or more pumps (combinations with priming pumps or booster pumps to counteract vapour-lock F04D9/04)
- F04D 15/0077: {Safety measures (F04D15/02 takes precedence)}
- F04D 15/0088: {Testing machines}
- F04D 15/0209: {responsive to a condition of the working fluid (F04D15/029 takes precedence)}
- F04D 15/0218: {the condition being a liquid level or a lack of liquid supply}
- F04D 15/0254: {the condition being speed or load}
- F04D 15/0272: {the condition being wear or a position}
- G05B 13/021: {in which a variable is automatically adjusted to optimise the performance}
- G05B 13/026: {using a predictor}
- G05B 13/0265: {the criterion being a learning criterion}
- G05B 15/02: electric
- G05D 9/12: characterised by the use of electric means
- G06F 3/0481: based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F 3/04842: Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence)
- G06N 20/00: Machine learning
- G08B 21/182: {Level alarms, e.g. alarms responsive to variables exceeding a threshold}
- H04L 12/282: {based on user interaction within the home (receiver circuitry for displaying additional information being controlled by a remote control apparatus H04N21/42204)}
- H04L 12/2823: {Reporting information sensed by appliance or service execution status of appliance services in a home automation network (device-related reporting H04L43/065; arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom H04Q9/00)}
- G01M 1/22: and converting vibrations due to imbalance into electric variables
- G01M 13/045: Acoustic or vibration analysis
- 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)
- G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G01M: TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR

## Abstract

A sump pump system may implement adaptive learning and machine learning techniques to facilitate improved control of sump pumps. A sump pump system may implement the described techniques to generate, train, and/or implement a machine learning model that is capable of predicting or estimating one or more conditions of the sump pump system (e.g., water level in the basin, motor malfunction, stuck impeller, geyser effect, blocked outlet pipe, faulty level sensor/switch, faulty bearing, failure to engage pump at high-water mark, etc.) based on one or more detected input variables (e.g., acceleration or vibration patterns detected in water, on a pump, or on a pipe; capacitance values of water; audio signatures; electrical signatures, such as power or current draw; pump motor rotation speed; water pressure signatures or values, such as those detected at the bottom of a sump basin; etc.).

## Claims

### Claim 1

A sump pump system configured to implement adaptive learning, the sump pump system comprising:
a sump pump in a sump basin; and
a sump pump control system coupled to the sump pump and configured to activate and deactivate the sump pump, the sump pump control system comprising:
a first sensor, disposed in the sump basin, configured to detect water levels;
a second sensor, disposed in the sump basin, configured to detect acceleration of the second sensor; and
one or more processors coupled to the first sensor and the second sensor, the one or more processors configured to:
(A) access a machine-learning (ML) model previously trained by performing one or more statistical analyses on one or more sets of data indicative of the levels of water in a sump basin and one or more sets of data indicative of detected acceleration patterns, the ML model trained to discover one or more relationships between the one or more levels of water and the one or more acceleration patterns; and
(B) implement the ML model, wherein the sump pump control system activates or deactivates the sump pump based on the one or more predicted water levels that are predicted via the ML model based on (i) one or more acceleration data collected during operation of the sump pump and (ii) the one or more discovered relationships.

### Claim 2 (depends on 1)

The system of claim 1, wherein the first sensor is a float sensor.

### Claim 3 (depends on 1)

The system of claim 1, wherein the first sensor is a capacitance sensor.

### Claim 4 (depends on 1)

The system of claim 1, wherein the second sensor is an accelerometer.

### Claim 5 (depends on 1)

The system of claim 1, wherein the second sensor is a gyroscope or an inertial measurement unit (IMU).

### Claim 6 (depends on 1)

The system of claim 1, wherein the second sensor is a force acceleration sensor configured to detect acceleration based on a level of force exerted on the second sensor.

### Claim 7 (depends on 1)

The system of claim 1, wherein the one or more processors are further configured to (i) detect a difference between a first level of water measured via the first sensor and a second level of water predicted via the ML model; and (ii) generate an alarm in response to detecting that that the difference exceeds a threshold.

### Claim 8

A method for implementing adaptive learning in a sump pump system, the method comprising:
(A) accessing a machine-learning (ML) model previously trained by performing one or more statistical analyses on one or more sets of data indicative of levels of water in a sump basin and one or more sets of data indicative of detected acceleration patterns, the ML model trained to discover one or more relationships between the one or more levels of water and the one or more acceleration patterns; and
(B) implementing the ML model, including activating or deactivating the sump pump based on the one or more predicted water levels that are predicted via the ML model based on (i) one or more acceleration data collected during operation of the sump pump and (ii) the one or more discovered relationships.

### Claim 9 (depends on 8)

The method of claim 8, wherein the first sensor is a float sensor.

### Claim 10 (depends on 8)

The method of claim 8, wherein the first sensor is a capacitance sensor.

### Claim 11 (depends on 8)

The method of claim 8, wherein the second sensor is an accelerometer.

### Claim 12 (depends on 8)

The method of claim 8, wherein the second sensor is a gyroscope or an inertial measurement unit (IMU).

### Claim 13 (depends on 8)

The method of claim 8, wherein the second sensor is a force acceleration sensor configured to detect acceleration based on a level of force exerted on the second sensor.

### Claim 14 (depends on 8)

The method of claim 8, further comprising (i) detecting a difference between a first level of water measured via the first sensor and a second level of water predicted via the ML model; and (ii) generating an alarm in response to detecting that that the difference exceeds a threshold.

### Claim 15

A method for implementing adaptive learning in a sump pump system, the method comprising:
(A) accessing a machine-learning (ML) model previously trained by performing one or more statistical analyses on one or more sets of data indicative of levels of water in a sump basin and one or more sets of data indicative of detected capacitance values of water in the sump basin, the ML model trained to discover one or more relationships between the one or more levels of water and the one or more capacitance values; and
(B) implementing the ML model, including activating or deactivating the sump pump based on the one or more predicted water levels that are predicted via the ML model based on (i) one or more capacitance values detected during operation of the sump pump and (ii) the one or more discovered relationships between water levels and capacitance values.

### Claim 16 (depends on 15)

The method of claim 15, wherein the first sensor is a float sensor.

### Claim 17 (depends on 15)

The method of claim 15, wherein the first sensor is a capacitance sensor.

### Claim 18 (depends on 15)

The method of claim 15, further comprising: (i) detecting a difference between a first level of water measured via the first sensor and a second level of water predicted via the ML model; and (ii) generating an alarm in response to detecting that that the difference exceeds a threshold.

### Claim 19 (depends on 18)

The method of claim 18, further comprising: (i) detecting a fault with the first sensor based, at least in part, on the detected difference; and (ii) implementing control of the sump based on the second sensor instead of the first sensor.

### Claim 20 (depends on 15)

The method of claim 15, further comprising: (i) detecting a fault with the first sensor based, at least in part, on the detected difference; and (ii) implementing control of the sump based a schedule such that the sump pump is activated and deactivated based on time intervals.
