Data-Driven Model for Chemical Synthesis Specification Generation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In the chemical industry, finding new chemical compositions that meet specific target application properties is complex and costly due to the large parameter space, especially when transitioning from commodity chemicals to customer-centric solutions.

Innovation Solution

A computer-implemented method generates a target synthesis specification for chemical products by using a data-driven model based on historical synthesis specifications and application properties, allowing for the determination of optimal chemical components and amounts, which reduces time and costs by leveraging generative models and neural networks to predict suitable chemical compositions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional experimental methods are used to find new chemical compositions, then expert knowledge and manual exploration can be applied, but the large parameter space makes the process very complex and costly

Engineering Contradiction:

Improvequality of chemical compositionVSAvoidcomplexity of finding synthesis specification

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces manual experimental exploration with an automated computer-implemented method. A data-driven model processes historical synthesis specifications and generates new compositions algorithmically, substituting the mechanical process of manual experimentation with computational automation. This reduces complexity by systematically exploring the parameter space through software rather than human-driven trial and error.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a virtual model (data-driven model) that copies and learns from historical synthesis specifications. This virtual representation allows the system to generate new compositions by processing patterns from existing data, eliminating the need for physical experimentation at each step and reducing overall process complexity.

Inventive Principle:

Principle #26Copying

2Reliability

If traditional experimental methods are used to find new chemical compositions, then expert knowledge can guide the process, but the large parameter space increases time and costs

Engineering Contradiction:

Improvequality of chemical compositionVSAvoidtime to find synthesis specification

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent performs preliminary action by training a data-driven model on historical synthesis specifications before actual composition generation. This pre-processing of knowledge allows the system to quickly generate new compositions without starting from scratch each time, significantly reducing the time required for future synthesis specification development while maintaining quality through learned patterns.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces time-consuming manual experimentation with automated computational processing. The computer-implemented method rapidly evaluates the large parameter space algorithmically, reducing the time required to find suitable chemical compositions while maintaining reliability through systematic data-driven approaches.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If traditional experimental methods are used, then manual exploration of parameter space can occur, but customization for customer-specific applications becomes increasingly costly

Engineering Contradiction:

Improvecustomization capabilityVSAvoidcost of customization

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent creates a universal data-driven model that can handle multiple customer-specific applications through a single system. The model processes historical data and generates customized compositions for different applications using the same computational framework, making the customization process scalable and cost-effective rather than requiring separate development efforts for each application.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent replaces costly manual customization processes with automated computational methods. The computer-implemented system can rapidly adapt to different customer requirements by processing their specific target properties through the trained model, reducing the cost of customization while maintaining high adaptability to various applications.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20240047014A1Formulation generation

Publication Date: 2024.02.08 BASF AUX CHEM

AI summary

A computer implemented method for generating synthesis specifications comprising the steps of providing to a computer processor via a communication interface a proposed target application property of the new synthesis specification; providing to the computer processor via the communication interface a data driven model, parametrized based on historical synthesis specifications comprising historical list of components, historical amounts for each of the components and historical target criteria, determining via the computer processor a target synthesis specification based on the data driven model and the target application property providing to an output unit via the communication interface the target synthesis specification, comprising a list of target components and the amount of each of the components.