AI Demulsifier Control for Electrostatic Coalescer Separation Stability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional Gas-Oil Separation Plants (GOSP) face challenges in efficiently separating water from crude oil due to unpredictable demulsifier dosage requirements and lack of proactive monitoring of electrostatic coalescer operational conditions, leading to process upsets and suboptimal crude quality.
Innovation Solution
The implementation of an artificial intelligence (AI) based Smart Demulsifier Control (SDC) system that utilizes electric voltage and current readings from modulated AC/DC electrostatic coalescers to optimize demulsifier dosage and prevent process upsets by continuously updating target separation efficiencies and temperature controller set points in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional demulsifier control methods are used, then操作简单 (operation is simple), but demulsifier dosage requirements are unpredictable and crude quality is suboptimal
Solution Approach 1:
The patent implements a closed-loop feedback control system where AI models continuously predict optimal demulsifier dosage based on real-time process parameters (temperature, pressure, flow rates) and feedstock characteristics. The predicted dosage is fed back to the dosing system, creating a dynamic adjustment mechanism that improves crude quality while maintaining operational simplicity.
Solution Approach 2:
The system employs self-service through automated AI-based prediction and control algorithms that autonomously determine optimal demulsifier dosage without requiring manual intervention. The system self-adjusts based on real-time data, eliminating the need for operator expertise while improving prediction accuracy and crude quality consistency.
2Reliability
If proactive monitoring of electrostatic coalescer operational conditions is not implemented, then device complexity is low, but process upsets occur and separation efficiency decreases
Solution Approach 1:
The patent implements preliminary action by continuously monitoring electrostatic coalescer operational conditions (voltage, current, power consumption) and predicting potential process upsets before they occur. The system detects anomalies in real-time and triggers preventive adjustments to demulsifier dosage or operational parameters, preventing process disruptions before they affect crude quality.
Solution Approach 2:
The monitoring system provides continuous feedback on electrostatic coalescer performance parameters, enabling real-time detection of degradation trends or abnormal conditions. This feedback loop allows the control system to adjust operations proactively, maintaining process stability and preventing upsets that would otherwise require reactive intervention.
3Productivity
If AI-based real-time optimization is implemented, then demulsifier dosage is optimized and energy consumption is reduced, but system complexity increases
Solution Approach 1:
The patent replaces conventional mechanical/control-based demulsifier dosing systems with AI-based predictive modeling. Instead of using complex multi-parameter control systems, the solution substitutes machine learning algorithms that process input data (temperature, pressure, flow rates, feedstock properties) to predict optimal dosage, achieving high separation efficiency through intelligent computation rather than complex hardware control.
Solution Approach 2:
The system optimizes separation efficiency and reduces energy consumption by dynamically adjusting key operational parameters (demulsifier dosage, temperature, pressure) based on AI predictions. The AI model continuously learns from operational data and adapts parameter settings to achieve optimal separation performance while minimizing energy consumption, replacing static operational parameters with dynamic, data-driven adjustments.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This AI-based control system enhances crude quality by optimizing demulsifier usage and energy consumption, reduces human intervention, and proactively prevents process upsets, thereby ensuring stable and efficient operation of the GOSP.
Implementation Method 1
electrostatic coalescers use electric field to promote water separation from oil
Implementation Method 2
demulsifier chemical is added to the production header. Demulsifier is a chemical that promotes water separation from the oil
Data Source
AI summary
A computer implemented method that enables artificial intelligence based demulsifier control for AC or modulated AC/DC electrostatic coalescers is described. The method includes monitoring parameters associated with the GOSP facility and inputting the parameters to a trained machine learning model that outputs a minimum HPPT separation efficiency. The method includes determining a target HPPT separation efficiency based on the minimum HPPT separation efficiency. Additionally, the method includes adjusting a demulsifier dosage being injected into the HPPT apparatus to separate dry oil at the target HPPT separation efficiency.