MODELING DEVICE AND MODEL ANALYSIS METHOD, SYSTEM AND METHOD FOR PROCESS ABNORMALITY DETECTION/CLASSIFICATION, MODELING SYSTEM, AND MODELING METHOD, AND FAILURE PREDICTING SYSTEM AND METHOD OF UPDATING MODELING APPARATUS

摘要

PROBLEM TO BE SOLVED: To provide a modeling apparatus that can easily make a model of correlation between process data and result data in a semiconductor manufacturing process.

SOLUTION: The modeling apparatus acquires time series process data by collecting such process condition data in a constant cycle that is obtained when the process is performed, and it extracts a process characteristic quantity from the process data by a process data editing part 10a and stores it in a process characteristic quantity data storage 10i. The ID of a product is used as a key, the process characteristic quantity data, a test data and a failure data are combined, and data for analysis that are generated by deleting invalid data in a data filter 10c is analyzed through data mining by an analysis part 10d to create a model.

COPYRIGHT: (C)2004,JPO&NCIPI