Semiconductor Tool Throughput Model Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In semiconductor manufacturing, the complexity of process tools and frequent recipe changes make it difficult to accurately estimate and monitor the throughput of process tools, leading to undetected performance issues and inefficiencies.
Innovation Solution
A system and method for estimating throughput by analyzing tool messages at a high resolution to automatically generate throughput models, identifying functional entities and material flows, and determining process time intervals, enabling objective and robust throughput estimations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional throughput monitoring methods are used, then the system is simple to operate, but the measurement precision of throughput is insufficient due to complexity of process tools and frequent recipe changes
Solution Approach 1:
The system automatically generates throughput models by utilizing process data from the manufacturing execution system and tool event data from process tools. The automated model generation extracts functional entities, determines material flows, and calculates throughput parameters without requiring manual intervention, thereby maintaining high measurement precision while reducing operational complexity
Solution Approach 2:
The patent replaces traditional manual throughput monitoring methods with an automated information processing system. By substituting mechanical/manual operations with automated data extraction, processing, and model generation algorithms, the system achieves high throughput estimation accuracy while managing complexity through automation
2Productivity
If automated throughput monitoring is implemented, then the productivity of throughput estimation is improved, but the device complexity increases due to additional monitoring systems
Solution Approach 1:
The system achieves multi-functionality by using a single automated model generation platform that can handle multiple process tools, various recipe types, and different throughput scenarios. The throughput model generator serves universal purposes across diverse manufacturing contexts, improving productivity while managing complexity through standardized processes
Solution Approach 2:
The patent introduces an intermediary automated model generation system that bridges the gap between raw process data and throughput metrics. This intermediary layer processes data from multiple sources (MES, tool event data) and transforms it into meaningful throughput information, enhancing productivity while encapsulating complexity within the intermediary system
3Measurement precision
If detailed tool message analysis is performed, then the measurement precision of process time intervals is improved, but the loss of time for data processing increases
Solution Approach 1:
The system performs preliminary actions by continuously collecting and storing process data and tool event data in advance. This pre-processing allows the automated model generation to quickly retrieve and analyze relevant data when throughput estimation is needed, maintaining high measurement precision while minimizing real-time processing delays
Data Source
AI summary
The throughput of complex cluster tools of a semiconductor manufacturing environment may be determined for a desired manufacturing scenario on the basis of automatically generated throughput models. The throughput models may be established on the basis of rule messages with high statistical relevance.