WOE-Based Defect Analysis for OLED Fabrication Operations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In the manufacturing of display panels, particularly organic light emitting diode (OLED) displays, defects are difficult to trace due to the complex and integrated nature of the production process, often requiring manual data sorting based on experience, which is inefficient and unreliable.
Innovation Solution
A computer-implemented method for defect analysis that calculates weight-of-evidence (WOE) scores for device operations during fabrication, ranking them to identify operations highly correlated with defects, and an intelligent defect analysis system using distributed computing to perform algorithmic analysis and data visualization, enabling the identification of underlying defect causes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual data sorting based on experience is used for defect analysis, then analysis can be performed with simple tools, but the process is inefficient and unreliable
Solution Approach 1:
The patent replaces manual data sorting and experience-based analysis with an automated computer-implemented system that uses algorithms to calculate WOE scores and rank device operations. This substitution of mechanical/manual processes with automated computational methods directly resolves the contradiction by improving both efficiency (automation) and reliability (objective algorithmic analysis).
Solution Approach 2:
The system enables self-service defect analysis by automatically processing fabrication data, calculating correlations, and generating defect cause identifications without requiring manual intervention. The automated calculation of WOE scores and ranking of device operations allows the system to serve itself, improving productivity while maintaining consistent, reliable analysis.
2Device complexity
If the complex and integrated nature of the production process is maintained, then manufacturing capabilities are preserved, but defect tracing becomes difficult
Solution Approach 1:
The patent introduces WOE (Weight of Evidence) scores as an intermediary metric that mediates between the complex production process data and defect identification. The WOE score calculation system acts as a mediator that processes complex fabrication data from multiple devices and operations, translating it into ranked correlations that make defect tracing feasible despite the underlying process complexity.
Solution Approach 2:
The patent segments the complex production process into individual device operations, each with calculable WOE scores. By dividing the integrated manufacturing process into discrete, analyzable components (individual devices, operations, and their correlations with defects), the system makes defect tracing possible without simplifying the actual production process complexity.
3Loss of time
If automated defect analysis is implemented, then manual effort is reduced, but computational resources and system complexity increase
Solution Approach 1:
The patent transforms the defect analysis problem by changing parameters from manual assessment metrics to automated WOE score calculations. This parameter change enables automated processing that reduces manual effort time, while the standardized calculation methodology keeps the added system complexity manageable through consistent algorithmic approaches.
Data Source
AI summary
A computer-implemented method for defect analysis is provided. The computer-implemented method includes calculating a plurality of weight-of-evidence (WOE) scores respectively for a plurality of device operations with respect to detects occurred during a fabrication period, a higher WOE score indicating a higher correlation between a defect and a device operation; and ranking the plurality of WOE scores to obtain a list of selected device operations highly correlated with the defects occurred during the fabrication period, device operations in the list of selected device operations having a WOE score greater than a first threshold score. A respective one of the plurality of device operations is a respective device defined by a respective operation site at which the respective device perform a respective operation.