Manufacturing Setting Selection for Semiconductor Tools
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing manufacturing processes for integrated circuits face inefficiencies due to the lack of historical data for new tools, leading to reduced productivity and increased resource utilization, as conventional methods rely heavily on historical data for tool calibration and operation.
Innovation Solution
A method is introduced to identify non-candidate tools without historical data and determine if available historical data from other tools can predict the performance of these tools, allowing for the selection of manufacturing settings for candidate tools based on historical data, thereby enabling the use of tools not previously represented in the data set.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional manufacturing processes rely on historical data for tool calibration, then manufacturing quality is improved, but new tools without historical data cannot be used, reducing productivity
Solution Approach 1:
The patent copies manufacturing settings from similar tools that have historical data to new tools without historical data. The system identifies tools with similar characteristics and replicates their successful manufacturing parameters, allowing new tools to be used immediately without requiring their own historical data, thus maintaining manufacturing quality while enabling productivity improvement
Solution Approach 2:
The patent introduces an intermediary system that acts as a bridge between historical data and new tools. This intermediary (the manufacturing settings selection system) transfers relevant manufacturing parameters from tools with historical data to new tools, enabling the new tools to operate effectively without direct historical data while preserving manufacturing quality standards
2Reliability
If send-ahead wafers are used to initialize new tools, then tool calibration is improved, but time and resource consumption increase
Solution Approach 1:
The patent performs preliminary action by pre-selecting and transferring manufacturing settings from tools with historical data before the new tool is put into production. This eliminates the need for send-ahead wafers, as the new tool receives ready-to-use calibrated settings in advance, maintaining tool calibration reliability while eliminating the time and resource waste associated with send-ahead wafer processes
Solution Approach 2:
The system copies proven manufacturing settings from established tools to new tools, replacing the need for send-ahead wafers. By replicating successful configurations from historical data, the system achieves reliable tool calibration without consuming additional wafers and time, directly resolving the contradiction between calibration quality and resource efficiency
3Productivity
If non-threaded controllers import historical data from similar tools, then the need for send-ahead wafers is reduced, but the device cannot determine if sufficient data is available, reducing usefulness
Solution Approach 1:
The patent implements feedback mechanisms that allow the non-threaded controller to evaluate the quality and sufficiency of imported historical data. The system assesses whether the transferred manufacturing settings are appropriate for the new tool's specific characteristics and provides feedback on data adequacy, enabling the controller to make informed decisions about whether to use imported settings or require additional calibration, thus restoring ease of operation while maintaining productivity benefits
Data Source
AI summary
Methods according to the disclosure include: identifying at least one non-candidate tool which previously processed at least one prior semiconductor wafer, and represented in a set of historical data, the set of historical data including manufacturing settings for performing an operation on the at least one prior semiconductor wafer, and a candidate tool which has not previously performed the operation on at least one prior semiconductor wafer, the candidate tool not being represented in the set of historical data; determining whether the set of historical data predicts the performing of the operation with the candidate tool based on the manufacturing settings for performing the operation on the at least one prior semiconductor wafer; and in response to the set of historical data predicting the performing of the operation with the candidate tool, selecting a manufacturing setting for the candidate tool based on the set of historical data.