Semiconductor Step Grouping for Abnormality Trend Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting abnormalities in semiconductor manufacturing apparatuses using time series information charts are inefficient and lack reliability in identifying patterns across different processing steps.
Innovation Solution
An information processing apparatus that generates a step catalog grouping processing steps by setting values, extracts relevant steps before an abnormality, and displays trend graphs for analysis, improving reliability by focusing on steps with identical settings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If time series information charts are used to detect abnormalities in semiconductor manufacturing apparatuses, then abnormality detection capability is provided, but the detection efficiency and reliability are insufficient due to inability to identify patterns across different processing steps
Solution Approach 1:
The patent segments processing steps with different setting values into separate groups. By dividing the overall processing into distinct segments based on setting values, the system can analyze patterns within each segment independently, improving both detection reliability through focused analysis and efficiency by avoiding cross-contamination of different setting conditions in the analysis
Solution Approach 2:
The patent changes the analysis parameter from raw time series data to grouped data organized by setting values. This parameter transformation allows the system to identify patterns specific to each setting condition, thereby improving detection reliability while the automated grouping process maintains efficiency
2Reliability
If all processing steps are analyzed without grouping by setting values, then comprehensive monitoring is achieved, but data integrity is compromised due to mixing different setting conditions
Solution Approach 1:
The patent segments the data analysis process into distinct groups based on setting values. This segmentation ensures that data from different setting conditions are analyzed separately, maintaining data integrity by preventing mixing of incompatible conditions, while the systematic grouping approach manages complexity through organized structure
Solution Approach 2:
The patent introduces a new parameter dimension (setting value grouping) to organize the analysis. This parameter change transforms the analysis from a flat structure to a hierarchical one, preserving data integrity through separation while managing complexity through structured organization
Data Source
AI summary
An information processing apparatus includes a grouping information generation unit that acquires a setting value for each processing step executed by a semiconductor manufacturing apparatus according to the setting value, and generates information for grouping processing steps executed according to the same setting value; a data extraction unit that extracts at least one second processing step that has a setting value identical to a setting value of a first processing step and that is executed before the first processing step when the setting value of the first processing step specified from a time when an abnormality occurred is included in the information for grouping; an analysis target section setting unit that sets the first processing step and the second processing step as an analysis target section; and a display control unit that displays a graph indicating an analysis result of the analysis target section.