Autonomous Tool Parameter Impact Identification for Semiconductor Fabrication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional semiconductor fabrication systems struggle to effectively leverage inter-relationships among various measurement data for advanced optimization of fabrication processes, leading to inefficient maintenance and reduced yields due to the complex dimensionality of tool parameters.
Innovation Solution
A parameter impact identification system that analyzes tool parameter data and performance data to autonomously identify critical tool parameters influencing specific performance metrics, ranking them by relative impact and generating simplified functions to focus maintenance efforts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional fabrication systems analyze all tool parameters independently, then comprehensive coverage of parameters is achieved, but analysis complexity and time consumption increase significantly
Solution Approach 1:
The system segments the complex multi-parameter analysis problem into multiple single-parameter analysis sub-problems. For each tool parameter, the system independently analyzes its impact on tool performance indicators separately, rather than attempting to analyze all parameters simultaneously. This segmentation reduces the dimensional complexity of the analysis while maintaining comprehensive coverage of all parameters.
Solution Approach 2:
The system introduces an intermediary computational layer that processes individual parameter impacts and aggregates them to determine overall parameter importance. This intermediary layer calculates the impact of each parameter on performance indicators and uses these calculations to rank parameters by importance, simplifying the overall analysis process.
2Reliability
If all tool parameters are monitored and analyzed, then complete performance assessment is achieved, but maintenance focus becomes diluted across too many parameters
Solution Approach 1:
The system applies local quality by differentiating the importance level of different tool parameters based on their actual impact on performance. Instead of treating all parameters equally, the system identifies and highlights the most critical parameters that have the greatest influence on tool performance, allowing maintenance personnel to focus their efforts where they are most needed.
Solution Approach 2:
The system changes the parameter representation from a flat list of all parameters to a ranked hierarchy based on calculated impact scores. By computing the relative impact of each parameter on performance indicators and sorting them accordingly, the system transforms the data structure to emphasize critical parameters while de-emphasizing less important ones.
3Measurement precision
If complex multi-parameter functions are used to model tool performance, then modeling accuracy is improved, but computational burden and difficulty of interpretation increase
Solution Approach 1:
The system segments the complex multi-parameter performance modeling into multiple single-parameter impact analyses. Instead of fitting one complex function relating all parameters to performance, the system analyzes each parameter's impact separately and aggregates these individual impacts to determine overall parameter importance and generate simplified performance models.
Data Source
AI summary
A system and method autonomously determines the impact of respective tool parameters on tool performance in a semiconductor manufacturing system. A parameter impact identification system receives tool parameter and tool performance data for one or more process runs of the semiconductor fabrication system and generates a separate function for each tool parameter characterizing the behavior of a tool performance indicator in terms of a single one of the tool parameters. Each function is then scored according to how well the function predicts the actual behavior of the tool performance indicator, or based on a determined sensitivity of the tool performance indicator to changes in the single tool parameter. The tool parameters are then ranked based on these scores, and a reduced set of critical tool parameters is derived based on the ranking. The tool performance indicator can then be modeled based on this reduced set of tool parameters.