Automated Polymer Screening via Active Mixing and In-Situ ML

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Polymer materials formulation and optimization are limited by the need for high throughput screening, particularly for multi-materials with disparate viscosities, as existing methods are slow and inefficient, lacking a systematic approach for rapid analysis and modification of material characteristics.

Innovation Solution

An automated platform combining active mixing direct-ink-write additive manufacturing with in-situ characterization and machine learning for rapid screening and optimization of polymer materials, enabling the printing of multiple films with varying constituents and real-time data analysis to inform subsequent formulations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional hand mixing methods are used for polymer materials formulation, then the process is simple to operate, but the screening speed is slow and productivity is low

Engineering Contradiction:
Improvescreening speedVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system segments the materials screening process into distinct functional modules: active mixing unit, direct-ink-write printing unit, in-situ characterization unit, and machine learning analysis unit. Each module handles a specific aspect of the formulation process, enabling high-throughput screening while maintaining operational clarity through modular architecture

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The machine learning system automatically analyzes characterization data and generates feedback for formulation optimization without manual intervention. The system self-regulates by using collected data to dictate the next batch of films to be printed, eliminating the need for human analysts to interpret each result and enabling continuous autonomous operation

Inventive Principle:
Principle #25Self-service

2Stability of the object's composition

If multi-materials with disparate viscosities are mixed using conventional methods, then material compatibility is difficult to achieve, but the mixing process becomes more complex

Engineering Contradiction:
Improvematerial compatibilityVSAvoidmixing system complexity
Core Design Contradiction:
Stability of the object's compositionVSDevice complexity

Solution Approach 1:

The active mixing system dynamically adjusts mixing parameters such as shear rate, mixing time, and rotor-stator speed based on the viscosity characteristics of the materials being combined. This parameter optimization enables effective mixing of materials with disparate viscosities while maintaining a relatively simple device architecture

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system replaces conventional mechanical mixing with direct-ink-write additive manufacturing technology, which uses precisely controlled material deposition and in-situ mixing. This substitution eliminates the need for complex pre-mixing equipment and enables direct fabrication of multi-material structures with controlled composition

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If rapid analysis and modification of material characteristics is implemented, then productivity increases, but the extent of automation and system complexity increases

Engineering Contradiction:
Improvescreening throughputVSAvoidautomation level
Core Design Contradiction:
ProductivityVSExtent of automation

Solution Approach 1:

The system implements closed-loop feedback where in-situ characterization data is immediately analyzed by machine learning algorithms, which then automatically dictate the formulation parameters for the next batch of films. This feedback mechanism enables rapid iterative optimization while maintaining controlled automation levels through interpretable AI decision-making

Inventive Principle:
Principle #23Feedback

Data Source

PatentUS20240096454A1High Throughput Materials Screening
Publication Date: 2024.03.21 LAWRENCE LIVERMORE NAT SECURITY LLC
  • US20240096454A1 patent drawing
  • US20240096454A1 patent drawing
  • US20240096454A1 patent drawing

AI summary

The present disclosure relates to systems and methods for screening a formulation of a material being printed in an additive manufacturing process, in situ, to enable rapid analysis, modeling and modification of at least one characteristic associated with the material formulation. In one embodiment the system includes a computer and an experimental planning software module that includes a historical database of sample material test results, a machine learning software module, and a new batch formulation generation software module. The experimental planning software module enables new material formulations to be determined in situ and in real time, using one or more machine learning models, and new material samples to be printed in accordance with newly determined material formulations, for closer inspection and evaluation of at least one desired characteristic of the sample materials.