AI Chemical Formulation Prediction Across Variable Test Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The selection and development of specialty chemicals for oil and gas production, such as demulsifiers, corrosion inhibitors, scale inhibitors, and defoamers, is typically an empirical process due to complicated formulation and application scenarios, lacking a systematic and efficient approach.
Innovation Solution
A computing device with a data preparation module and chemistry composition prediction module that normalizes historical test results and trains machine learning models to predict chemical components and optimize formulations based on specified conditions and performance indicators, using modules for data normalization, chemical composition prediction, and formula optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If empirical process is used for specialty chemical development, then flexibility in handling complicated formulation scenarios is maintained, but development time is extended and efficiency is reduced
Solution Approach 1:
The patent replaces the empirical mechanical process of chemical formulation with an AI-based predictive system. The chemistry composition prediction module uses machine learning models to predict optimal chemical components and formulations, substituting traditional trial-and-error empirical methods with data-driven computational approaches, thereby improving development efficiency while handling complex formulation scenarios.
Solution Approach 2:
The patent transforms the development process by changing key parameters from qualitative empirical judgments to quantitative AI-predicted values. The system predicts chemical composition parameters, performance indicators, and formulation ratios based on trained models, converting the empirical process into a parameter-driven systematic approach that accelerates development while managing complexity.
2Loss of time
If traditional empirical methods are used, then systematic approach is avoided, but development time is significantly reduced
Solution Approach 1:
The patent implements preliminary action by pre-training AI models on historical chemical test data before actual formulation development. The data preparation module normalizes historical data, and the chemistry composition prediction module trains models in advance, so that when new formulations are needed, the AI system can rapidly predict optimal compositions without starting from scratch, thereby reducing development time while maintaining systematic rigor.
Solution Approach 2:
The patent uses copying by creating virtual representations of chemical formulations and their performance through AI models. Instead of physically testing every formulation combination, the system creates computational copies and predictions of formulation outcomes based on normalized historical data, allowing rapid evaluation of multiple scenarios before actual manufacturing, thus reducing time while establishing a systematic process.
3Measurement precision
If AI models are trained on raw historical test data, then model accuracy may be compromised, but data processing time is reduced
Solution Approach 1:
The patent applies preliminary action by normalizing historical test data before training AI models. The data preparation module performs data cleaning, standardization, and normalization in advance, transforming raw historical test results into a consistent format with standardized performance indicators. This pre-processing ensures high prediction accuracy when models are trained, while the one-time nature of this preliminary step does not significantly impact overall development time.
4Reliability
If comprehensive historical test data is used for training, then model robustness is improved, but data normalization complexity increases
Solution Approach 1:
The patent implements universality by creating a standardized normalization framework that handles diverse historical test data from multiple sources and conditions. The data preparation module develops universal normalization rules and performance indicator standards that can process various types of chemical test data (corrosion rates, scale inhibition, demulsification) through a single systematic approach, thereby ensuring model robustness while managing normalization complexity through standardization.
Data Source
AI summary
Technologies for specialty chemical development and testing include devices and methods for normalizing historical specialty chemical test results and training a chemical composition predictor to predict chemical components of a formulation given a test condition and a normalized performance indicator based on the normalized test results. The specialty chemical may be a corrosion indicator, and the normalized performance indicator may be corrosion rate. The devices and methods may predict a predicted composition with the trained chemical composition predictor. the devices and methods may filter the normalized test results based on the predicted composition and train a formulation optimization predictor to predict a normalized performance indicator based on the filtered test results. The devices and methods may generate multiple candidate chemical formulations based on the predicted composition and predict a normalized performance indicator for each candidate chemical formulation with the trained formulation optimization predictor.