Adaptive Nuisance Filter for Dynamic Semiconductor Inspection Stability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing semiconductor inspection processes rely on static inspection recipes that cannot be dynamically adjusted, leading to instability with respect to nuisance rates and inability to monitor process variations effectively.
Innovation Solution
A system and method for generating inspection results using an adaptive nuisance filter, which includes an energy source, detector, and computer subsystems that acquire and classify inspection data, modify nuisance filter parameters based on classification results, and apply the modified filter to generate final inspection results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a static inspection recipe is used indefinitely, then the inspection process is simple to operate, but the inspection stability with respect to nuisance rate deteriorates and cannot adapt to process variations
Solution Approach 1:
The patent implements dynamic adjustment of nuisance filter parameters by continuously monitoring inspection results and automatically retuning the filter based on observed nuisance rates and defect characteristics, transforming the static recipe into an adaptive system that maintains optimal performance across process variations
Solution Approach 2:
The system incorporates feedback mechanisms where inspection results are analyzed to determine whether nuisance filter parameters should be modified, creating a closed-loop control system that automatically adjusts filter settings based on actual performance metrics and process conditions
2Adaptability or versatility
If manual monitoring and re-tuning of inspection recipes is performed, then the inspection can adapt to some extent, but the productivity decreases and the system cannot respond dynamically to process variations
Solution Approach 1:
The inspection system performs self-tuning of nuisance filter parameters by automatically analyzing inspection results and adjusting filter settings without requiring manual intervention, enabling the system to adapt to process variations while maintaining high productivity through autonomous operation
Solution Approach 2:
The system performs preliminary classification of events and generates samples of events with feature values closer to nuisance filter parameters before final inspection, preparing data in advance to enable faster and more accurate dynamic adjustment of filter settings during production
3Measurement precision
If the nuisance filter parameters are fixed, then the device complexity is low, but the ability to detect defects of interest deteriorates when process variations occur
Solution Approach 1:
The system dynamically changes nuisance filter parameters based on observed process variations and defect characteristics, adjusting filter settings to maintain optimal defect detection precision across different process conditions while managing complexity through automated parameter optimization
Data Source
AI summary
Methods and systems for generating inspection results for a specimen with an adaptive nuisance filter are provided. One method includes selecting a portion of events detected during inspection of a specimen having values for at least one feature of the events that are closer to at least one value of at least one parameter of the nuisance filter than the values for at least one feature of another portion of the events. The method also includes acquiring output of an output acquisition subsystem for the sample of events, classifying the events in the sample based on the acquired output, and determining if one or more parameters of the nuisance filter should be modified based on results of the classifying. The nuisance filter or the modified nuisance filter can then be applied to results of the inspection of the specimen to generate final inspection results for the specimen.