AI Process Parameter Planning for Component Carrier Yield
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing complexity and miniaturization of component carriers with multiple electronic components pose challenges in heat removal and mechanical robustness, leading to yield loss and inefficiencies in manufacturing due to the need for precise control of process parameters.
Innovation Solution
A method utilizing an AI-based system that ranks and selects relevant process parameters to determine an action plan for manufacturing component carriers, optimizing parameters such as trace width, insulator thickness, and lamination conditions to achieve desired final product properties like thermal expansion and land coplanarity, using a neural network for predictive modeling and continuous improvement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional engineering planning methods are used for manufacturing component carriers, then the manufacturing process can be carried out with standard procedures, but yield loss occurs due to undesired properties of manufactured component carriers
Solution Approach 1:
The patent applies parameter changes by using an AI module to determine optimized process parameters for manufacturing component carriers. The system evaluates multiple process parameters (such as lamination conditions, trace width, insulator thickness) and adjusts them to optimal values based on their impact on final product properties, thereby improving yield and reducing manufacturing defects.
Solution Approach 2:
The patent implements feedback through an AI-based system that continuously learns from manufacturing data. The system receives process parameters and final product properties, analyzes the relationships between them, and provides feedback for optimizing future manufacturing processes. This closed-loop approach enables continuous improvement of manufacturing precision and yield.
2Manufacturing precision
If the number of process parameters to be controlled is increased to achieve precise manufacturing, then manufacturing precision improves, but device complexity and manufacturing effort increase
Solution Approach 1:
The patent applies the extraction principle by using the AI module to identify and extract only the most critical process parameters that have the highest impact on final product properties. Instead of controlling all possible process parameters, the system ranks them by importance and focuses optimization efforts on the top-ranked parameters, thereby reducing manufacturing complexity while maintaining precision.
Solution Approach 2:
The system transforms the complex set of process parameters into an optimized subset by evaluating their individual and combined impacts on final product properties. The AI module determines optimal values for each parameter and identifies the most influential ones, effectively reducing the dimensionality of the control problem while improving manufacturing precision.
3Adaptability or versatility
If miniaturization of electronic components and increased component density is implemented, then product functionality increases, but heat removal becomes increasingly difficult and mechanical robustness decreases
Solution Approach 1:
The patent addresses heat removal challenges by optimizing process parameters that affect thermal properties of component carriers. The AI system adjusts parameters such as material selection, layer thickness, and structural design during manufacturing to improve heat dissipation capabilities while maintaining miniaturization and component density requirements.
4Adaptability or versatility
If miniaturization of electronic components is implemented, then product functionality increases, but mechanical robustness and electrical reliability decrease
Solution Approach 1:
The patent optimizes mechanical robustness by adjusting manufacturing process parameters such as lamination conditions, material properties, and structural design. The AI system determines optimal parameter values that enhance the mechanical strength and durability of miniaturized component carriers, ensuring they can withstand harsh operating conditions while maintaining high functionality.
Data Source
Figure 1
Figure 2~4
Figure 5
AI summary
A method of planning manufacture of component carriers (100), wherein the method comprises defining a set of final product parameters (Y) as a target for component carriers (100) to be manufactured, wherein the product parameters (Y) are influenceable by a set of process parameters (X) being settable during the manufacturing method, ranking the process parameters (X) concerning their impact on the final product parameters (Y), selecting a subset of higher ranked process parameters (X), inputting the selected subset of process parameters (X) for processing by an artificial intelligence module (102), and determining an action plan (152) for the manufacturing method based on an output of the artificial intelligence module (102).