Quality Control Apparatus for Production Facility Abnormality Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing quality control systems in production lines, such as surface mounting lines, face inefficiencies due to excessive checks and erroneous reports of abnormalities, as they rely on inspection results from intermediate processes to determine defect causes, which can be complex and multifactorial, leading to unpredictable final product quality and reduced production line efficiency.
Innovation Solution
A quality control apparatus that includes a facility information obtaining unit, a product information obtaining unit, a storage unit, a determination unit, and an abnormality detection unit, which compares product and facility state values to determine abnormalities, reducing erroneous reports by considering both product and facility states in relation to acceptable article distributions, and updates these distributions based on actual operation data to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If determination criteria for inspection items are adjusted based on inspection results from subsequent processes, then defect detection capability is improved, but excessive checks occur leading to reduced production efficiency
Solution Approach 1:
The patent changes the parameters used for defect determination from simple inspection results to a composite index combining product state values and facility state values. This allows the system to maintain high defect detection capability while reducing excessive checks by considering both product quality and facility operational status together
Solution Approach 2:
The patent implements feedback by using post-reflow inspection results to adjust and update the determination criteria for intermediate process inspections. The system continuously learns from actual defect cases and refines the index thresholds, enabling accurate defect prediction without excessive checks
2Reliability
If strict determination criteria are applied in intermediate processes, then defect detection is improved, but acceptable articles are erroneously rejected and production facilities are falsely flagged as abnormal
Solution Approach 1:
The patent transforms the determination approach by introducing a composite index that combines multiple product state values and facility state values. This multi-parameter approach provides a more comprehensive assessment, reducing false positives while maintaining high defect detection accuracy
Solution Approach 2:
The system dynamically adjusts determination criteria based on accumulated inspection data and actual defect cases. The index thresholds and weightings are continuously optimized through machine learning, allowing the system to adapt to varying production conditions and minimize erroneous abnormality reports
Data Source
Figure 1
Figure 2A~2D
Figure 3A~3D
AI summary
A quality control apparatus includes a facility information obtaining unit, which obtains data about a facility state value indicating a state of a production facility observed when the production facility processes a product, and a product information obtaining unit, which obtains data about a product state value indicating a state of the product measured from the product processed by the production facility. For a product determined to be a defective article, the quality control apparatus determines whether a product state value of the defective article is an abnormal value by comparing the product state value with an acceptable article distribution of product state values, and determines whether a facility state value observed when the defective article is processed is an abnormal value by comparing the facility state value with an acceptable article distribution of facility state values, and determines that the production facility has an abnormality when the product state value and the facility state value of the defective article are both determined to be abnormal values.