Machine Learning Workflow for Metal-Organic Framework Design
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current carbon capture technologies face challenges in achieving high CO2 capture capacity, selectivity over other gases, and reducing regeneration energy needs, particularly due to varying flue gas compositions and operating conditions, which can lead to costly system modifications when sorbent changes are necessary.
Innovation Solution
A workflow using machine learning and a MOF library to identify a Metal-Organic Framework (MOF) that matches the performance of a target sorbent, allowing direct replacement without modifying the capture system, leveraging AI to predict MOF properties and optimize design for improved capture rates, lifespan, and cost efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If solvent-based absorption technology using aqueous amine solvents is used for CO2 capture, then the technology is mature and can be deployed at industrial scale, but high energy costs are incurred due to solvent regeneration
Solution Approach 1:
The invention changes the fundamental parameters of the capture system by replacing liquid amine solvents with solid sorbent materials, fundamentally altering the phase and chemical nature of the capture medium to reduce regeneration energy requirements
Solution Approach 2:
The invention replaces the chemical absorption mechanism of aqueous amine solvents with physical or chemical adsorption mechanisms of solid sorbents, substituting one capture mechanism with another that requires less energy for regeneration
2Object-affected harmful factors
If solid sorbents are used for CO2 capture, then toxic gas emissions from solvents are reduced and equipment corrosion is alleviated, but the technology faces challenges with varying flue gas compositions and operating conditions
Solution Approach 1:
The invention creates dynamically adaptable sorbent systems that can adjust to varying operating conditions through selective catalyst design and process configuration, allowing the system to maintain performance across different flue gas compositions and temperatures
Solution Approach 2:
The invention develops sorbent materials with universal applicability to handle various flue gas compositions and operating conditions, making the technology versatile enough for different industrial applications without requiring complete system redesign
3Ease of manufacture
If a sorbent is selected at an early stage in development of a capture facility, then the system design is established, but changing the sorbent during or after development is costly or impractical due to changes in accompanying systems
Solution Approach 1:
The invention segments the sorbent into modular, replaceable units that can be independently changed without affecting the entire capture system, allowing flexibility in sorbent selection and replacement while maintaining system integrity
Solution Approach 2:
The invention creates a dynamically adaptable system where the sorbent can be changed without requiring changes to accompanying systems, enabling flexibility in sorbent selection while maintaining established system designs
4Productivity
If new sorbent materials are developed to improve CO2 capture capacity and selectivity, then capture performance is enhanced, but the development time and cost increase
Solution Approach 1:
The invention performs preliminary computational screening and modeling of sorbent materials before physical synthesis and testing, allowing researchers to identify promising candidates in silico and reduce the number of experimental iterations required
Solution Approach 2:
The invention uses computational models and simulations to create virtual replicas of sorbent materials and their performance, allowing researchers to evaluate multiple candidates digitally before committing to physical material synthesis and testing
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables efficient CO2 capture with reduced energy consumption and operational costs by identifying a MOF that matches the performance of existing sorbents, facilitating seamless integration and potential enhancements without system redesign.
Implementation Method 1
a machine learning algorithm is used to correlate MOF structures of the MOF training subset with the identified target sorbent features
Implementation Method 2
CO2 separation techniques using solid sorbents
Data Source
AI summary
Embodiments presented provide for a workflow to identify a proposed metal-organic framework (MOF) to directly replace a sorbent material within a carbon dioxide capture system. The workflow disclosed and described below identifies target sorbent features associated with a sorbent material based on target sorbent properties. A subset of MOFs is selected from a MOF library based on reaction parameters of the target sorbent, and a machine learning algorithm is used to correlate MOF structures of the MOF training subset with the identified target sorbent features. A proposed MOF structure is identified as the most similar to the target sorbent.