Predictive Engine for Crude Selection Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Oil refineries face challenges in processing lower quality crudes due to lack of information and knowledge about their behavior, leading to operational issues and economic viability concerns, as existing methods like laboratory simulations and linear programming systems fail to address specific problems and chemical treatment solutions effectively.
Innovation Solution
A method and system utilizing a database with experiential and simulation data to create predictive performance and risk assessment models, which use desirability metrics and a predictive engine to assess crude selection and optimize refining processes, including chemical treatment options, based on historical data and real-time operational conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If oil refineries process lower quality crudes to reduce costs and increase availability, then economic benefits are improved, but operational reliability deteriorates due to lack of information about crude behavior
Solution Approach 1:
The system performs preliminary analysis of crude oil properties and processing history before actual refining operations. By pre-assessing crude behavior patterns, compatibility, and potential issues using stored data and predictive models, the system enables informed decision-making about crude selection and blending strategies, preventing operational problems before they occur.
Solution Approach 2:
The system implements continuous feedback loops where actual processing results, operational data, and performance metrics are fed back into the database. This feedback mechanism allows the predictive models to learn from real-world outcomes and improve their accuracy over time, enabling better predictions of crude behavior and more reliable operational decisions.
2Measurement precision
If laboratory simulations are used to develop predictive models of crude performance, then some predictive capability is improved, but the models remain limited and cannot address specific complex problems or chemical treatment solutions
Solution Approach 1:
The system merges multiple data sources including laboratory simulation data, actual processing history, crude properties, operational parameters, and performance metrics into a unified database. This integration combines the controlled precision of lab simulations with the real-world complexity of actual operations, creating a comprehensive system that can address both general predictive needs and specific complex problems.
Solution Approach 2:
The system is designed as a universal platform that can handle diverse crude types, processing conditions, and operational scenarios. The predictive models are configured to address multiple functions including crude compatibility assessment, processing optimization, problem prediction, and chemical treatment recommendations, making the system adaptable to various specific complex problems.
3Productivity
If linear programming systems are implemented to define crude cut and yield, then production optimization is improved, but the systems cannot address chemical treatment requirements or predict operational impacts
Solution Approach 1:
The system merges linear programming optimization capabilities with chemical treatment analysis and operational impact prediction. By integrating production optimization algorithms with databases containing chemical compatibility data and processing performance information, the system simultaneously optimizes crude allocation while identifying required chemical treatments and potential operational issues.
Solution Approach 2:
The system acts as an intermediary between production planning and operational execution. It translates production optimization decisions into actionable insights about chemical treatment requirements and operational impacts by querying the database for relevant data and providing comprehensive recommendations that bridge the gap between theoretical optimization and practical implementation.
Data Source
AI summary
A method and system for assessing and optimizing crude selection are provided. A predictive engine uses data from a database to execute at least one predictive performance model and/or at least one risk assessment model designed to optimize or improve refining operations during a refining process. The predictive engine takes as input key crude information corresponding to a particular crude or crude blend, e.g., at least one crude slate, and refinery operating parameters and/or conditions corresponding to a specific refinery and uses desirability metrics to assess the similarity to data in the database. Based on the resulting output, at least one predictive performance and/or at least one risk assessment model uses the output to predict performance or risk measures of refining the particular crude or crude blend using the specific refinery during the refining process, the probability of problems occurring during the refining process, the distribution of the problems throughout the refining process, etc.