Fault isolation during semiconductor manufacturing using automated discovery from wafer tracking databases

S. Saxena
Proceedings of 9th IEEE Conference on Artificial Intelligence for Applications  
This paper describes the use of automated discovery from databases for diagnosing the causes of rotsprocessing during semiconductor manufacturing. The database eonlains the historl/ of the semieonduc4or wafers as theTI undergo various processing steps. A gener~ste-and-test approach is to3cen for using such a database for automated diagnosis. Based on prior maaual use of such databases, classes of queries to the database useful for fault isolation are identified. Patterns in the responses to
more » ... e queries that are useful for fault isolation are also identified. Automated diagnosis is accomplished bll automating query generation and the detection of potentially useful paflergs. A prototllpe ~stem was implemented and tested on a database from a wafer grinding and polishin 9 facility. In addition to identifying pre~iousll/ lmoum faults, the system also identified pre~iousil/ unknoum faults.
doi:10.1109/caia.1993.366594 fatcat:h5nimpaycraqjlqdiqz6upxbiu