Printed Device Fabrication Feedback for Roll-to-Roll Quality Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High-speed manufacturing processes like roll-to-roll systems face challenges in efficiently monitoring device quality and making real-time adjustments to ensure consistent device performance, particularly due to variations in the coating of ion-selective membranes in sensors.
Innovation Solution
Implementing physics-based models and machine learning algorithms to predict device performance in real-time by acquiring physical characteristics during fabrication, allowing for adjustments to the manufacturing process to ensure quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If high-speed roll-to-roll manufacturing processes are used to produce printed devices, then productivity and manufacturing efficiency are improved, but the ability to monitor device quality in real-time and ensure consistent performance deteriorates due to variations in coating uniformity
Solution Approach 1:
The patent implements a feedback control system where machine learning models predict device performance based on physical characteristics acquired during fabrication. The predictions are fed back to adjust fabrication process parameters in real-time, creating a closed-loop system that maintains coating uniformity despite high-speed variations. This resolves the contradiction by enabling quality monitoring and adjustment at speeds compatible with high-speed manufacturing.
Solution Approach 2:
The system dynamically changes fabrication process parameters based on real-time predictions of device performance. By adjusting parameters such as coating speed, temperature, or material flow rates in response to measured variations, the system maintains consistent coating quality while operating at high speeds, thus resolving the contradiction between productivity and manufacturing precision.
2Manufacturing precision
If real-time monitoring and adjustment systems are implemented during high-speed fabrication, then manufacturing precision and device quality are improved, but device complexity and system cost increase
Solution Approach 1:
The patent replaces complex mechanical monitoring and adjustment systems with machine learning-based predictive models that process physical characteristic data. Instead of implementing numerous physical sensors and actuators throughout the fabrication line, the system uses computational models to predict performance and guide adjustments, reducing mechanical complexity while maintaining precision.
Solution Approach 2:
The system creates virtual models or digital twins of the devices during fabrication, using machine learning to predict final performance based on intermediate physical characteristics. This virtual copying allows for quality assessment and adjustment without requiring complex physical testing equipment, thereby improving precision while limiting the increase in system complexity.
3Productivity
If post-manufacturing testing is eliminated to reduce costs and increase productivity, then productivity and cost-effectiveness are improved, but reliability and quality assurance deteriorate
Solution Approach 1:
The patent performs quality prediction and assessment during the fabrication process itself, rather than after manufacturing is complete. By using machine learning models to predict device performance based on physical characteristics acquired during fabrication, the system ensures quality assurance upfront, eliminating the need for post-manufacturing testing and maintaining both productivity and reliability.
Solution Approach 2:
The fabrication system performs self-verification through machine learning-based performance prediction. Instead of requiring separate testing equipment and procedures to assure quality, the system uses its own fabrication data and predictive models to self-assess device quality, maintaining reliability while avoiding the productivity losses associated with post-manufacturing testing.
Data Source
AI summary
Methods for fabricating printed devices and monitoring one or more performance characteristics of the printed devices during their fabrication in a high-speed process. Such a method includes developing a physics-based model of at least a first component of the printed devices, fabricating the printed devices with the high-speed process using fabrication steps that comprise depositing the first components, acquiring a physical characteristic of a plurality of the first components of a plurality of the printed devices following the depositing of the first components, predicting a performance characteristic of the printed devices based on the physics-based model of the first component and the physical characteristic acquired of the plurality of the first components; and then modifying at least one of the fabrication steps performed during the fabricating of a subsequently-fabricated group of the printed devices to adjust the performance characteristic of the subsequently-fabricated group of the printed devices.