Pumpjack Operating Property Determination via Load-Travel Graph Normalization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for determining the operating conditions of pumpjacks are complex and prone to errors due to inaccurate sensor calibration, making it difficult to diagnose operating states accurately and efficiently.

Innovation Solution

A method using machine learning to normalize and compare load-travel graphs, employing random forest models and Kmeans algorithms to identify operating properties of pumpjacks, allowing for the use of model graphs from other pumps without prior training, and simplifying the calibration process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional sensor-based methods are used to determine pumpjack operating conditions, then measurement data can be collected, but the methods become complex and prone to errors due to inaccurate sensor calibration

Engineering Contradiction:

Improveaccuracy of operating condition determinationVSAvoidcomplexity of calibration process

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces traditional mechanical sensor-based measurement systems with a machine learning-based system that uses load-travel graphs and random forest models to determine pump operating conditions, eliminating the need for physical sensor calibration

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a reference load-travel graph that serves as a template or copy of normal pump operation, against which actual operating conditions are compared to determine pump status, avoiding direct measurement errors

Inventive Principle:

Principle #26Copying

2Productivity

If model load-travel graphs from other pumps are used without prior training, then analysis can be performed more quickly, but accuracy may be compromised without proper calibration

Engineering Contradiction:

Improvespeed of operating condition determinationVSAvoidaccuracy of pump diagnosis

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent transforms the load-travel graph data into a standardized format with normalized parameters that can be directly compared across different pumps, allowing model graphs from other pumps to be used without retraining while maintaining accuracy

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent creates a universal reference load-travel graph model that can be applied across multiple pumps and operating conditions, making the system versatile and eliminating the need for pump-specific training data

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20230366308A1Computer-implemented method for determining an operating property of a pumpjack, analysis device and pump system therefor

Publication Date: 2023.11.16 SIEMENS ENERGY GLOBAL GMBH & CO KG

AI summary

A computer-implemented method for determining an operating property of a pumpjack, wherein the pump has a pump head, which is connected to a kinematic converter via a rod system, and the kinematic converter is driven by a motor during operation and a load-travel graph containing curve points is determined for the delivery pump by an analysis device using recording and is provided as an operating load-travel graph containing operating curve points.