Yield Prediction Feedback for Equipment Engineering Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional Yield Management Systems (YMS) lack the capability to provide predicted yield information to subsystems of Equipment Engineering Systems (EES) and do not perform automated actions in response to yield predictions, limiting proactive measures for yield optimization in manufacturing environments.
Innovation Solution
A method and apparatus that generate end-of-line yield predictions based on manufacturing process data, sending them to EES components, where a strategy engine compares the predictions to rules and instructs actions to perform automated responses, such as adjusting R2R controllers, scheduling maintenance, or routing products through manufacturing machines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If yield prediction is implemented in conventional YMS, then yield engineers can detect potential yield problems before product completion, but there is no mechanism to provide predicted yield information to EES subsystems and no automated actions can be performed
Solution Approach 1:
The patent implements a feedback mechanism where end-of-line yield predictions are generated and fed back to EES subsystems. The strategy engine receives yield predictions, compares them against rules, and automatically executes actions based on the comparison results, creating a closed-loop system that transforms static yield information into dynamic automated responses.
Solution Approach 2:
The strategy engine serves as an intermediary component between the yield prediction system and EES subsystems. It receives yield predictions, processes them through rule-based logic, and translates them into actionable commands for various EES components, enabling automated responses without direct integration between prediction and execution systems.
2Reliability
If manual yield analysis is performed by yield engineers, then potential yield problems can be detected, but proactive automated actions cannot be taken to mitigate yield excursions
Solution Approach 1:
The system implements self-service automation where the strategy engine autonomously performs yield analysis, rule comparison, and action execution without requiring manual intervention from yield engineers. The system serves itself by automatically detecting yield problems and executing mitigation actions, transforming manual analysis into automated self-managing functionality.
Solution Approach 2:
The patent enables preliminary automated actions to be taken based on yield predictions before actual yield excursions occur. By analyzing predicted yield data and executing preventive actions in advance, the system proactively mitigates potential yield problems rather than reacting to them after they manifest.
3Extent of automation
If yield predictions are generated and sent to EES components, then automated responses can be performed, but system complexity increases with strategy engine and rule management
Solution Approach 1:
The strategy engine is segmented into distinct functional modules: yield prediction reception, rule-based comparison logic, and action execution. This segmentation allows each component to perform a specific function independently, making the overall complex system more manageable, maintainable, and easier to debug while preserving automated capabilities.
Data Source
AI summary
A yield prediction is received by a strategy engine. The strategy engine compares the end-of-line yield prediction to a plurality of rules. The strategy engine then instructs a component of an equipment engineering system to perform an action included in a rule that corresponds to the end-of-line yield prediction.