INCREASING PROFITABILITY AND IMPROVING SEMICONDUCTOR MANUFACTURING THROUGHPUT USING EXPERT-SYSTEMS

This paper describes a new procedure for using a machine-learning clas sification technique coupled with an expert system to increase profita bility and improve throughput in a semiconductor manufacturing environ ment. The authors show how to use this procedure to identify relations hips between work-in-process data (information obtained during semicon ductor fabrication) and potential integrated circuit yield. The relati onships, in the form of IF-THEN rules, are extracted from databases of previously fabricated integrated circuits and final yield. It is furt her shown that these rules, when incorporated into expert systems, can advise the human operator as to which batches of circuits are likely to produce submarginal yield if processed to completion, thereby provi ding a basis for developing or enhancing a quality control strategy. T hese rules also identify the parameters and values which have historic ally provided the highest and lowest final wafer yields. A cost analys is is given to illustrate the cost-effectiveness of this procedure. An introduction to semiconductor manufacturing and a glossary are provid ed.