Manufacturing Process Snapshot Modeling for Missing Data Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In semiconductor manufacturing, poor yield due to limited access to process data hinders thorough fault and failure analysis, especially when manufacturing is performed by a third party, as they may provide redacted data streams preventing complete analysis of issues like margin and process variations, photolithography errors, and wafer defects.
Innovation Solution
A computer-implemented method models a manufacturing process using snapshots of the system, including time and state, to identify possible transition paths and predict times of state changes, allowing for analysis of issues such as margin and process variations, photolithography errors, and wafer defects, even with limited data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If third party manufacturing is used to produce semiconductor devices, then production capacity and expertise are improved, but access to process data is restricted preventing thorough fault and failure analysis
Solution Approach 1:
The patent introduces an intermediary system that receives redacted data streams from third party manufacturers and reconstructs the original process parameters. This intermediary acts as a mediator between the restricted data source and the analysis system, enabling thorough fault analysis without requiring direct access to proprietary manufacturing data.
Solution Approach 2:
The system creates copies of the manufacturing process data in reconstructed form. By generating synthetic process parameter data that mirrors the actual manufacturing conditions, the system enables complete fault and failure analysis while working within the constraints of redacted data streams from third party manufacturers.
2Object-affected harmful factors
If redacted data streams are provided to protect process specifics, then proprietary information security is improved, but complete manufacturing analysis to identify issues like margin and process variation is prevented
Solution Approach 1:
The reconstruction system serves as an intermediary that receives redacted data streams and transforms them into complete process parameter information. This intermediary layer enables manufacturing analysis without compromising the security of proprietary information held by third party manufacturers.
Solution Approach 2:
The system changes the parameters of the data by reconstructing process parameters from redacted data streams. It transforms restricted data into comprehensive process information, enabling complete fault and failure analysis while maintaining the redacted state of original proprietary data.
3Loss of information
If snapshots of system state are used instead of complete process data, then data accessibility is improved, but completeness of manufacturing analysis is reduced
Solution Approach 1:
The system performs preliminary reconstruction of complete process parameters from snapshots before conducting fault and failure analysis. By pre-reconstructing the full process data from limited snapshots, it enables comprehensive manufacturing analysis that would otherwise be impossible with snapshot data alone.
Solution Approach 2:
The system creates reconstructed copies of complete process parameters from snapshot data. These synthetic process parameter copies enable thorough manufacturing analysis while working within the constraints of having only snapshot information available from third party manufacturers.
Data Source
AI summary
A computer-implemented method, system and computer program product for modeling a manufacturing process. Snapshots of the system are received, where each snapshot includes a time that the snapshot was taken and a state of the system at that time. Possible transitions paths in a state diagram exhibited by the system are then identified based on the snapshots. A transition path out of the identified transition paths that most likely corresponds to the sequence of state changes exhibited by the system is selected based on information pertaining to a typical time taken by the system from one state to another. A predicted time that the system entered each state of the selected transition path between selected states of the snapshots is determined based on such information as well as the time at which the snapshots were taken. An issue related to the manufacturing process is predicted based on such predicted times.