As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
To provide a reference for the fault detection of a dynamic random access memory (DRAM) manufacturing process, we propose a yield-rate predictor using an artificial neural network (ANN). The inputs to the ANN are the machining parameters in each step of the manufacturing process for a DRAM wafer, and the output is the yield rate of the corresponding wafer. In this study, a three-layer feed-forward back propagation ANN is used and trained by input-output pairs of data collected from real manufacturing process. We have tested the proposed ANN for five cases, and each case has different size of training data set. The test results show that the average of the absolute prediction errors in all five cases are very small, and as the size of the training data set increases, the prediction accuracy increases and the associated standard deviation decreases.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.