Method for detecting out-of-specification quality of product and estimating actually measured value of product

A product quality, actual measurement technology, applied in the direction of comprehensive factory control, comprehensive factory control, electrical program control, etc., can solve problems such as undetectable, detected, and quality exceeding specifications

Active Publication Date: 2010-06-16
NAT CHENG KUNG UNIV
View PDF5 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, unless the abnormal workpiece is sampled, it is impossible to detect the abnormal workpiece by only monitoring the process parameter value of the production machine.
[0003] On the other hand, many abnormal situations may occur in the quality of the product, for example: the process data parameter values ​​of the production workpiece are all within the specification (normal), but its quality (actual measurement value) is out of specification
However, existing methods cannot detect the aforementioned phenomenon

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for detecting out-of-specification quality of product and estimating actually measured value of product
  • Method for detecting out-of-specification quality of product and estimating actually measured value of product
  • Method for detecting out-of-specification quality of product and estimating actually measured value of product

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention is mainly to provide the quality index (DQI) of process data X ) model, measurement data quality indicator (DQI y ) model and product quality out of specification detection (FD) model, where DQI X The model is used to calculate the process data quality index value (DQI) of the process data for manufacturing a certain workpiece. X value); DQI y The model is used to calculate the measurement data quality indicator value of the actual measurement value of a certain workpiece; the FD model is used to detect whether the product is invalid or not in real time on the production line through the normal process data collected during the production process. defective. The present invention is based on principal component analysis (PCA) and Euclidean distance (ED) to establish DQI X model, and use the leave-one-out principle in cross-validation to determine the process data quality threshold DQI was established according to Adaptive Resonance Theory 2 (...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention is a method for detecting out-of-specification quality of a product and estimating actually measured value of the product. The method for detecting the out-of-specification quality of the product is to construct a fault detection (FD) model representing the relationship between technological parameters and the out-of-specification of the product by applying a classification and regression tree (CART) method so as to detect the condition that the process data parameters are all in the specification (normal) but the product quality goes beyond the specification on a production line in real time. The method for estimating the actually measured value of the product is to establish a measured data quality index (DQIy) model according to an adaptive resonance theory 2 (ART2) and normalized variability (NV).

Description

technical field [0001] The present invention relates to a method for detecting product quality out-of-spec (Out Of Specification; OOS) and evaluating the actual measurement value of the product, in particular to a method that can detect whether the product quality is out-of-spec and evaluate the product in real time during the production process quality approach. Background technique [0002] In the manufacturing process of semiconductor and thin film transistor-liquid crystal display (TFT-LCD), it is generally necessary to conduct on-line (On- line) quality control to ensure the quality of products made from workpieces. The workpieces are called wafers in semiconductor factories and glass in TFT-LCD factories. In the prior art, the measurement quality of products is evaluated by means of Statistical Process Control (SPC). In the existing statistical process control method, it is first necessary to collect a piece of historical measurement data, and calculate the control c...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G05B19/418
CPCY02P90/02
Inventor 郑芳田黄宜婷
Owner NAT CHENG KUNG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products