Sampling Data Processing Device for Yield Rate Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sampling inspection methods struggle to accurately estimate the number of product lots outside the product standard due to variations in measured characteristic values, which include both product and measurement system variations, leading to incorrect sorting of defective and non-defective products, and insufficient estimation accuracy when assuming a normal distribution.
Innovation Solution
A sampling data processing device and method that calculates standard deviations, confidence intervals, and defect rates based on control chart data to accurately estimate the number of product lots outside the product standard, accounting for both product and measurement variations, and determines the required number of samples for achieving a predetermined yield rate.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If sampling inspection is performed to reduce inspection cost, then inspection cost is reduced, but estimation accuracy of defective product lots deteriorates
Solution Approach 1:
The patent replaces conventional mechanical sampling inspection with a statistical estimation system that uses control chart data and probability distributions to estimate the number of defective product lots. This substitution allows accurate estimation without physically inspecting every product, thereby reducing inspection costs while maintaining or improving estimation accuracy through mathematical modeling of product characteristic distributions.
2Measurement precision
If normal distribution assumption is used for sampling inspection, then OC curve accuracy is enhanced, but estimation accuracy of actual product distribution deteriorates
Solution Approach 1:
The patent changes the fundamental parameter assumption from fixed normal distribution to a dynamic distribution model that adapts to actual product data. By using control chart data to estimate actual distribution parameters (mean, standard deviation) and applying probability density functions that match the observed data patterns, the system maintains OC curve accuracy while improving the reliability of product distribution estimation to reflect real-world variations.
3Measurement precision
If all products are screened for inspection, then estimation accuracy of defective products is improved, but inspection cost and time increase
Solution Approach 1:
The patent extracts only the essential information needed for defective product estimation from the product population, rather than inspecting every product. By taking out key parameters (characteristic values, control limits, distribution statistics) and using them in statistical models, the system achieves accurate defective product detection while maintaining high inspection efficiency through sampling-based estimation rather than complete screening.
Data Source
AI summary
Upper and lower limits of predetermined characteristic values of products contained in a plurality of product lots are stored in accordance with the product standard for a target product. An average value of standard deviations in the characteristic values is calculated based on a control chart for the product lots. An average value of the characteristic values is calculated, and an upper limit and a lower limit of an average value of the characteristic values in a 95% confidence interval is calculated. A measurement standard deviation representing a variation in a measuring instrument with regard to the characteristic values is estimated. One of an upper limit and a lower limit of the average value of the characteristic values in the confidence interval is updated as an average value of the characteristic values. A standard deviation in the characteristic values of the product is estimated, and an upper defect rate and a lower defect rate are calculated, so that a yield rate is calculated.