An intelligent and automatic fault detection & classification in semiconductor photolithography process

To improve yield rate and decrease production cost, wafer fabrication factory puts emphasis on the method of its process control and analysis. In recent years, many semiconductor foundries have invested a large sum of capital in Advanced Process Control (APC). In the field of APC, the induction and development of Fault Detection & Classification (FDC) is definitely one of the important parts. FDC can rapidly detect abnormal situation of operation machine, so as to improve the yield rate. This research developed an FDC system consisting of fuzzy inference system and decision tree to monitor and analyze heating curve of soft bake in photolithography process. Characteristics of heating curves are extracted to establish the fuzzy inference system. The classification and regression trees (CART) is then utilized to classify possible anomalistic heating curves. Experiment results showed that all the 42 anomalistic curves from testing samples could be successfully identified by the system. Only 13 curves out of the 368 normal curves are incorrectly identified as anomalistic heating curves. The resultant anomalistic heating curves can then be classified into different types with the presented system.