GOSP Crude Oil Quality Control Using Virtual Parameters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring and improving the quality of crude oil exiting a gas-oil separation plant (GOSP) are limited by their inability to accurately account for the complex interplay of geometrical distribution of multiphase fluids, chemicals, and emulsions, leading to suboptimal quality predictions and increased water handling challenges as oil fields mature.
Innovation Solution
A method involving sensors that determine process parameters, calculate WiO-parameters based on water concentration, add virtual parameters to these, and employ a feedback loop to optimize the quality of crude oil exiting the GOSP by adjusting total parameters, maintaining improvements and reversing changes when quality worsens, until the desired quality is achieved.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data sampling and expensive online instruments are used to monitor crude oil quality, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent creates a virtual copy of the physical separation process by training a machine learning model on historical process data. This virtual model replicates the behavior of the GOSP system, allowing quality prediction without requiring complex physical measurement instruments. The model copies the relationships between process parameters and crude oil quality outcomes, enabling accurate monitoring through software rather than expensive hardware.
Solution Approach 2:
The patent replaces the mechanical/physical measurement system (sensors, online instruments, data sampling equipment) with an information-processing system. Instead of using physical devices to directly measure crude oil quality, the system uses machine learning algorithms to predict quality based on process parameters, substituting mechanical measurement with computational analysis.
2Device complexity
If traditional methods ignore the complex interplay of geometrical distribution of multiphase fluid during flowing, then device complexity is reduced, but manufacturing precision and quality prediction accuracy deteriorate
Solution Approach 1:
The patent transforms the complex physical phenomenon of multiphase fluid flow into a set of measurable process parameters (temperature, pressure, flow rates). Instead of directly modeling the complex geometrical distribution and flow dynamics, the system changes the representation from physical flow patterns to statistical parameter relationships that can be captured by machine learning models, maintaining accuracy while reducing complexity.
Solution Approach 2:
The machine learning model creates a virtual representation of the complex fluid dynamics by learning from historical data. Rather than physically modeling the geometrical distribution of multiphase fluids, the model copies the input-output relationships between process conditions and quality outcomes, capturing the complex interplay indirectly through pattern recognition.
3Measurement precision
If operators rely on expensive online instruments, then measurement precision is improved, but loss of time in implementing quality improvement increases
Solution Approach 1:
The machine learning model is trained in advance on historical process data, creating a pre-built knowledge base that can immediately predict quality outcomes. This preliminary training phase allows the system to provide real-time predictions without requiring time-consuming data collection or complex analysis during operation, enabling rapid quality assessment and decision-making.
Solution Approach 2:
The patent replaces time-consuming physical measurement and analysis processes with instant computational predictions. Instead of waiting for sample analysis or complex instrument readings, the system provides immediate quality predictions based on current process parameters, dramatically reducing the time required for quality assessment and corrective action.
Data Source
AI summary
A method for determining the quality of crude oil exiting a gas-oil separation plant (GOSP) is disclosed. The GOSP comprises sensors that determine process parameters of the crude oil. The method involves determining, from the process parameters, WiO-parameters that depend on the concentration of water in the crude oil (WiO), determining virtual parameters of the crude oil, determining total parameters by adding the virtual parameters to the WiO-parameters. Further, a feedback loop involves changing one or more of the total parameters, determining the quality of the crude oil exiting the GOSP, wherein when the quality is improved, the change in the one or more total parameters is maintained, and when the quality is worsened, the change in the one or more total parameters is reversed. The feedback-loop is repeated as long as the quality of the crude oil exiting the GOSP increases.