AI-Optimized Printed Electronics Parameter Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for optimizing inkjet printing in printed electronics are time-consuming and inefficient, as they focus solely on piezoelectric waveform without considering other critical factors, limiting the ability to obtain optimal printing parameters in real-world scenarios.
Innovation Solution
An artificial intelligence-assisted printed electronics self-guided optimization method that integrates machine learning to determine optimal printing parameters by analyzing six key variables, including the number of jetting holes, printing speed, substrate temperature, and inkjet intensity, through experimental groups and data characterization, thereby improving printing quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional piezoelectric waveform adjustment method is used to optimize printing parameters, then printing quality can be improved, but the optimization process is time-consuming and cannot consider multiple factors simultaneously
Solution Approach 1:
The patent applies parameter changes by systematically varying six key printing parameters (piezoelectric waveform, number of jetting holes, printing speed, substrate temperature, nozzle-substrate distance, and inkjet intensity) across multiple experimental groups. Instead of adjusting one parameter at a time, the invention changes multiple parameters simultaneously in controlled combinations, enabling comprehensive optimization of printing quality while reducing the total number of experiments needed compared to traditional sequential adjustment methods.
2Manufacturing precision
If comprehensive analysis of multiple printing factors is conducted to achieve optimal printing parameters, then printing quality improves, but the complexity of experimentation increases significantly
Solution Approach 1:
The patent applies segmentation by dividing the comprehensive parameter optimization into six distinct parameter groups, each containing specific levels (e.g., piezoelectric waveform with different slew rates and pulse durations, number of jetting holes with values 1-6, printing speed with four levels, etc.). This segmentation allows systematic exploration of multiple factors while maintaining manageable experimental complexity through structured grouping and hierarchical analysis of results.
Solution Approach 2:
The patent applies universality by creating a multi-functional experimental framework that simultaneously evaluates six different printing parameters and their interactions. The experimental design enables one set of experiments to provide information about multiple factors affecting printing quality, making the optimization process more efficient and reducing the need for separate studies for each parameter.
3Ease of manufacture
If limited experimental groups are used to analyze printing parameters, then experimentation is simpler, but the ability to obtain optimal parameters in actual situations is limited
Solution Approach 1:
The patent applies dimensionality change by expanding the experimental design from traditional single-factor or two-factor analyses to a six-dimensional parameter space. Each dimension represents a different printing parameter with multiple levels, creating a comprehensive experimental matrix that captures complex interactions between factors. This multi-dimensional approach enables the model to generalize better to actual printing situations while maintaining systematic experimental control.
Data Source
AI summary
The present invention provides an artificial intelligence-assisted printed electronics self-guided optimization method, which integrates machine learning technology with printed electronics. According to variables that impact printing quality of a microelectronic printer, a user sets up experimental groups, prints samples with the microelectronic printer according to parameters in the experiment groups, characterizes printing effects, and evaluates the printing quality. The characterization result is analyzed by machine learning, and printing parameters that correspond to a best printing effect are obtained; then, the parameters are fed back to the user, and the user configures the printer according to the fed-back parameters, thereby improving printing quality. By using the present invention, optimal printing parameters can be obtained by simply setting up a few simple experiments according to a number of factors that impact printing effects, which reduces the time for a printer user to test out printing effects in an early stage, and provides a good practicability.