ESP Operating Parameters via Neural Network Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for controlling electric submersible pumps (ESPs) in oil and gas wells lack efficiency in determining optimal operating parameters to achieve desired production targets.
Innovation Solution
The use of a machine learning model, specifically an artificial neural network (ANN), trained on historical well data to determine ESP operating parameters such as choke size percentage and motor speed, thereby controlling the ESP to achieve desired production targets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional methods are used to control ESP operating parameters, then the control process is simple, but the efficiency in determining optimal operating parameters to achieve desired production targets is low
Solution Approach 1:
The patent replaces traditional mechanical/control-based ESP parameter determination methods with a machine learning model (neural network) that processes historical well data to predict optimal operating parameters. This substitution enables more efficient and accurate determination of choke size percentage and motor speed parameters while achieving desired production targets.
Solution Approach 2:
The patent utilizes machine learning models to dynamically determine optimal operating parameters (choke size percentage, motor speed) based on input data such as oil production rate, water cut, intake pressure, and differential pressure. The model processes these parameters to generate optimized control values that maximize production efficiency.
2Productivity
If ESP operates at higher speeds to increase production rate, then productivity increases, but power consumption increases
Solution Approach 1:
The machine learning model optimizes the relationship between motor speed, choke size percentage, and power consumption by processing historical data to identify optimal parameter combinations. This enables the system to achieve desired production rates while minimizing unnecessary power consumption through intelligent parameter adjustment rather than simple speed increases.
Solution Approach 2:
The system uses historical well data and real-time measurements (oil production rate, water cut, intake pressure, differential pressure) as feedback to continuously refine and adjust ESP operating parameters. This feedback mechanism allows the system to optimize the balance between production rate and power consumption by learning from past performance data.
3Productivity
If ESP operates for longer duration to meet production targets, then productivity improves, but run life and reliability are affected
Solution Approach 1:
The machine learning model determines optimal operating parameters that balance production target achievement with equipment protection. By analyzing historical data, the model identifies parameter settings that achieve desired production rates while avoiding excessive operational stress on the ESP, thereby extending run life and improving reliability.
Solution Approach 2:
The system uses historical well data and trained machine learning models to predict and determine optimal operating parameters before actual production operations begin. This preliminary planning allows the ESP to operate within safe parameters throughout its run, preventing premature wear and extending operational life while still meeting production targets.
Data Source
AI summary
This disclosure describes methods and systems for determining operating parameters for an electric submersible pump (ESP) and controlling the ESP based on the determined operating parameters. A method involves determining a target production rate for a wellbore; providing the target production rate as input to a neural network that provides as output ESP operating parameters to achieve the target production rate, the ESP operating parameters including a choke size percentage and a motor speed, and the neural network modeling an ESP-equipped wellbore; and controlling an ESP to operate according to the ESP operating parameters.