Oil List Evaluation for Asphalt Production

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The existing methods for evaluating oils for asphalt production, such as Shell’s Heukelon diagram, are inadequate for current refining conditions in Brazilian refineries, particularly with pre-salt oils, leading to operational and commercial disruptions due to improper evaluation of oil suitability for Oil Asphalt Cement (OAC) production.

Innovation Solution

A method using a hierarchical logistic regression model with Bayesian methods and Business Intelligence techniques to analyze oil properties and production routes, implemented in a web application and electronic spreadsheet, which generates a probabilistic model for evaluating oil lists’ suitability for asphalt production, reducing the need for experimental analysis and improving operational reliability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If Shell's Heukelon diagram is used for evaluating oils for asphalt production, then the evaluation can be performed in a simple and practical way, but the evaluation accuracy deteriorates for current pre-salt oils and Brazilian refining conditions

Engineering Contradiction:

Improveevaluation simplicityVSAvoidoil suitability evaluation accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent transforms the evaluation from a graphical diagram-based method to a probabilistic mathematical model using hierarchical logistic regression. The model uses multiple oil composition parameters (saturated, aromatics, asphaltenes, resin, carbon residue, viscosity) to calculate a probability value, replacing the simplified Heukelon diagram approach with a more accurate parameter-driven calculation that accounts for pre-salt oil characteristics

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces the manual graphical analysis method (Heukelon diagram) with an automated computational system using Bayesian hierarchical logistic regression. This substitution eliminates the need for manual plotting and interpretation of graphical data, providing automated, objective, and more accurate probability-based evaluation results

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If Shell's Heukelon diagram is used for evaluating oils, then the method can be applied quickly, but operational reliability information cannot be extracted

Engineering Contradiction:

Improveevaluation speedVSAvoidoperational reliability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent implements a feedback mechanism where the probabilistic model is trained on historical production data from Brazilian refineries. The model learns from past successful and unsuccessful asphalt production campaigns, continuously improving its ability to predict operational reliability. The probability output provides quantitative feedback on the likelihood of successful production under specific oil composition conditions

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent performs preliminary evaluation of oil lists before actual asphalt production campaigns by calculating probability values based on oil composition data. This advance assessment allows refineries to pre-screen oil combinations and avoid problematic production campaigns, extracting operational reliability information before committing to production

Inventive Principle:

Principle #10Preliminary action

3Stability of the object's composition

If the Heukelon diagram assumptions are applied to current oils, then the evaluation process remains consistent, but the evaluation results become improper for pre-salt oils

Engineering Contradiction:

Improveevaluation model consistencyVSAvoidoil suitability prediction accuracy

Core Design Contradiction:

Stability of the object's compositionVSMeasurement precision

Solution Approach 1:

The patent creates a dynamic evaluation model using hierarchical logistic regression that adapts to different oil types and refining conditions. Unlike the static Heukelon diagram with fixed assumptions, the probabilistic model can accommodate varying oil compositions including pre-salt oils by learning from historical data across different conditions, providing context-appropriate evaluations

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS20230196252A1Method for evaluation of oil lists for asphalt production

Publication Date: 2023.06.22 PETROLEO BRASILEIRO SA PETROBRAS

AI summary

The present invention addresses to a predictive method that determines the favorability of a certain list of oils for the production of oil asphalt cement (OAC), according to the requirements of the Brazilian asphalt specification of the ANP. The method was developed using an artificial intelligence algorithm, based on thousands of industrial data collected, by means of queries in BI, during the OAC campaigns of the producing refineries of the system. With a very high predictive capacity, the method is able to determine the probability of a given list of oils producing asphalt, considering both the fundamental properties of the oils that compose the same, as well as operational aspects and production route, since it was calibrated with industrial data from OAC campaigns in real magnitude. Such a model can be implanted in a web application and in an electronic spreadsheet.The application of the method of this invention allows flexibility in the allocation of oils, reduction of OAC campaign times and operating costs, in addition to providing greater reliability in the production of asphalts and being easy to use.