ANN Processing Tool Control for Semiconductor Drift Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Semiconductor processing tools experience performance degradation between preventive maintenances, leading to reduced quality and yield of electronic devices, and variations in performance across tools result in inconsistent device performance.
Innovation Solution
Implementing an artificial neural network (ANN) to monitor and adjust parameters in real-time, ensuring performance consistency by dynamically adjusting manipulated variables based on R&D and production data, reducing the need for frequent preventive maintenances.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If preventive maintenance is performed periodically, then reliability is improved, but productivity deteriorates due to downtime and recovery time
Solution Approach 1:
The system continuously monitors processing parameters and compares them against target values, using feedback loops to detect performance degradation early and trigger adjustments before failures occur, replacing periodic PM with continuous adaptive control
Solution Approach 2:
The processing tool automatically adjusts its own parameters using the ANN model to maintain optimal performance without external intervention, enabling self-correction of degradation and eliminating the need for scheduled maintenance downtime
Solution Approach 3:
The system dynamically changes processing parameters based on real-time conditions and ANN predictions, adjusting multiple parameters simultaneously to compensate for tool degradation and maintain consistent performance without physical maintenance
2Manufacturing precision
If processing tool performance is maintained through frequent PM, then manufacturing precision is improved, but loss of time increases due to maintenance interruptions
Solution Approach 1:
The ANN model predicts parameter drift and performance degradation before they affect manufacturing quality, allowing preemptive adjustments to be made while the tool is still operating, preventing quality issues before they occur
Solution Approach 2:
The system maintains continuous processing operation by automatically adjusting parameters in real-time, eliminating interruptions and ensuring the useful action of manufacturing continues without pause while maintaining precision
3Productivity
If multiple processing tools are used to increase productivity, then productivity is improved, but manufacturing precision deteriorates due to performance variations between tools
Solution Approach 1:
The ANN model is designed to be tool-agnostic and can be deployed across multiple different processing tools, providing universal performance management that adapts to each tool's specific characteristics while maintaining consistent output quality across the entire manufacturing line
Solution Approach 2:
Each processing tool adjusts its own unique set of parameters based on its specific performance characteristics and degradation patterns, allowing customization to each tool while maintaining overall consistency through the same ANN methodology
Data Source
AI summary
One or more first parameters associated with an electronic device manufacturing process are monitored. An artificial neural network associated with the one or more first parameters is determined. One or more second parameters are determined using the artificial neural network. The one or more first parameters are adjusted using the one or more second parameters.