Pump Control Parameters Using ML-Based Application Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Pumps are often installed without proper adjustment of control parameter settings, leading to suboptimal operation, increased power consumption, and shortened lifespan due to the need for manual input and expertise in selecting system types for optimal performance.

Innovation Solution

A computer-implemented method using a trained machine-learning model to monitor operational variables and automatically determine application-specific control parameters, allowing for adaptive pump operation based on identified application types, facilitating easier and more efficient control.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual adjustment of control parameters is performed, then pump performance can be optimized for specific applications, but it requires user expertise and is time-consuming

Engineering Contradiction:

Improvepump performance optimizationVSAvoidmanual parameter adjustment

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The pump system automatically determines its own application type by monitoring operational variables and using a machine-learning model to select optimal control parameters, eliminating the need for manual user configuration and expertise while ensuring proper performance optimization

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system pre-configures multiple application types with their associated control parameters and uses a machine-learning model to automatically match the current operation to the appropriate pre-configured settings, enabling rapid optimization without manual intervention

Inventive Principle:

Principle #10Preliminary action

2Productivity

If pumps are installed with factory default settings, then installation is simplified and faster, but pump operation becomes suboptimal leading to increased power consumption and reduced lifespan

Engineering Contradiction:

Improveinstallation speedVSAvoidpower consumption

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The system continuously monitors operational variables such as power consumption, flow rate, and pressure, using this feedback to automatically adjust control parameters and identify the optimal application type, thereby reducing energy loss while maintaining fast installation through automated adaptation

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The pump system dynamically adapts its control parameters based on real-time monitoring of operational variables and machine-learning-based application type determination, allowing it to transition from static factory defaults to optimized dynamic operation without requiring manual reconfiguration

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS20240027975A1Method and system for controling a pump

Publication Date: 2024.01.25 GRUNDFOS HLDG

AI summary

A computer-implemented method for determining one or more application-specific control parameters of a pump operating in a system for moving a fluid. The method includes monitoring one or more operational variables of the pump during operation of the pump in the system; applying a trained machine-learning model to automatically determine an application type from the monitored operational variables, the application type representing a type of system the pump operates in and/or representing a type of operation performed by the pump when operating in said system, each application type being associated with a respective set of one or more application-specific control parameters; controlling the pump based on the set of one or more application-specific control parameters associated with the determined application type.