Manufacturing Abnormality Analysis Using Condition Similarity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for estimating abnormality causes in manufacturing processes have low accuracy due to not considering the similarity of manufacturing conditions, leading to prolonged identification of defective product causes and reduced yield.
Innovation Solution
A data analysis apparatus that designates conditions for target and comparison products, acquires factor data, computes index values for manufacturing condition contributions, and calculates similarity between these values to identify similar manufacturing conditions, thereby improving the accuracy of abnormality cause estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If the method of estimating abnormality cause by searching for abnormal cases with similar individual data is used, then the automation of abnormality detection is improved, but the accuracy of abnormality cause estimation deteriorates
Solution Approach 1:
The patent segments the abnormality analysis process into two distinct stages: (1) individual data-based abnormal case search, and (2) manufacturing condition-based similarity verification. By dividing the monolithic search process into sequential segments with different criteria, the system maintains automation while improving accuracy through multi-dimensional filtering.
Solution Approach 2:
The patent introduces manufacturing condition data as an intermediary layer between individual product data and abnormality cause determination. This intermediary enables the system to bridge the gap between automated detection and accurate cause estimation by adding a verification step that considers contextual manufacturing conditions.
2Productivity
If the period from abnormality occurrence to measure implementation is shortened, then the yield improvement is enhanced, but the time for data analysis is reduced
Solution Approach 1:
The patent performs preliminary action by pre-collecting and organizing manufacturing condition data in advance, and by establishing the similarity determination framework before abnormalities occur. This preparation enables rapid analysis when abnormalities are detected, reducing the time needed for cause identification without sacrificing analysis depth.
Solution Approach 2:
The patent implements skipping by directly comparing manufacturing conditions of current and past cases using established similarity criteria, rather than performing exhaustive analysis. This allows the system to rapidly identify relevant past cases and determine causes, accelerating the response time while maintaining accuracy.
Data Source
AI summary
According to one embodiment, a data analysis apparatus includes processing circuitry. The processing circuitry acquires first factor data indicative of first manufacturing conditions of a first product, and acquires second factor data indicative of second manufacturing conditions of a second product. The processing circuitry computes, based on the first factor data, a first index value relating to a degree by which each of the first manufacturing conditions contributes to an abnormality, and computes, based on the second factor data, a second index value relating to a degree by which each of the second manufacturing conditions contributes to an abnormality. The processing circuitry computes a similarity between the first index value and the second index value.