About cookies on this site Our websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising. For more information, please review your options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.
Paper
Rule-based data mining for yield improvement in semiconductor manufacturing
Abstract
We describe an automated system for improving yield, power consumption and speed characteristics in the manufacture of semiconductors. Data are continually collected in the form of a history of tool usage, electrical and other real-valued measurements-a dimension of tens of thousands of features. Unique to this approach is the inference of patterns in the form of binary regression rules that demonstrate a significantly higher or lower performance value for tools relative to the overall mean for that manufacturing step. Results are filtered by knowledge-based constraints, increasing the likelihood that empirically validated rules will prove interesting and worth further investigation. This system is currently installed in the IBM 300 mm fab, manufacturing game chips and microprocessors. It has detected numerous opportunities for yield and performance improvement, saving many millions of dollars. © 2009 Springer Science+Business Media, LLC.