CMP Top Ring Vibration and Sound Analysis for Substrate Slip-Out Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
It is challenging to accurately monitor and predict the state of a substrate during or after chemical mechanical polishing, particularly due to the complex interactions between the top ring and polishing table operations, making it difficult to prevent substrate slip-out.
Innovation Solution
An information processing apparatus that acquires polishing condition information, including top-ring vibration and sound data, and uses a machine-learning model to predict substrate slip-out information, thereby enabling appropriate prediction of substrate lip-out during or after chemical mechanical polishing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensors are directly attached to each substrate to detect substrate state, then measurement precision is improved, but device complexity and cost increase significantly
Solution Approach 1:
The patent introduces an intermediary system consisting of sensors on the top ring and polishing table that indirectly measure substrate state through the mechanical interactions during CMP. Instead of direct substrate sensing, the system measures vibration, sound, and operational parameters of the polishing equipment to infer substrate conditions and predict slip-out events.
2Measurement precision
If multiple sensors and direct monitoring of substrate are implemented, then substrate state monitoring accuracy is improved, but ease of operation deteriorates due to complex sensor management
Solution Approach 1:
The patent creates a virtual model or copy of the substrate state by analyzing data from equipment sensors rather than requiring physical sensors on the substrate. The machine learning model generates a digital representation of substrate conditions based on correlated equipment parameters, simplifying operation while maintaining monitoring accuracy.
3Reliability
If complex analysis of multiple operating states is performed to accurately predict substrate slip-out, then prediction accuracy is improved, but difficulty of detecting and measuring increases
Solution Approach 1:
The patent replaces complex mechanical analysis and direct physical measurement of substrate-state correlations with a machine learning-based computational system. The ML model automatically processes sensor data from the top ring and polishing table to predict substrate slip-out, substituting complex analytical mechanics with data-driven pattern recognition.
Solution Approach 2:
The system implements feedback by continuously monitoring top ring vibration and sound during CMP, comparing real-time data against patterns learned during training, and providing predictive feedback about impending substrate slip-out events. This enables proactive adjustment of polishing parameters to prevent slip-out.
Data Source
AI summary
An information processing apparatus (5) includes: an information acquisition section (500) configured to acquire polishing condition information including top-ring vibration information indicating vibration of a top ring in chemical mechanical polishing of the substrate and top-ring sound information indicating sound generated from the top ring in the chemical mechanical polishing of the substrate performed by a substrate processing apparatus including a polishing table rotatably supporting the polishing pad and the top ring configured to press the substrate against the polishing pad; and a state prediction section (501) configured to predict substrate slip-out information for the polishing condition information by inputting the polishing condition information acquired by the information acquisition section (500) to a learning model (10A) that has been generated by machine learning that causes the learning model to learn a correlation between the polishing condition information and the substrate slip-out information indicating occurrence of slip out of the substrate on which the chemical mechanical polishing is performed.