KEYWORDS: Data conversion, Machine learning, Inspection, Electronic design automation, Manufacturing, Photomasks, Data modeling, Education and training, Image classification, Data processing
In the photomask manufacturing industry, photomask source design data needs to be converted into several different target formats, such as MEBES fracture, writer file, die-to-database inspection data etc. Due to the various conversion needs in the manufacturing flow, different EDA tools from different software vendors are employed during conversion. Two different EDA tools that are given the same input can result in slight differences in the output pattern and this will lead to causation of CD errors relative to the underlying pattern tolerances and/or specifications. During the photomask production process, it is very challenging to identify and classify these small differences in the output pattern caused by the conversion of data. In this study, we developed a novel solution to alert on pattern discrepancy by utilizing the classification generated by the application of machine leaning techniques and Smart-MRC tools. A Convolutional Neural Network (CNN) model is being introduced in this study and is trained by learning pre-classified data and classification result would be generated after inputting data to the CNN model. This new Mask Data Preparation (MDP) technique is expected to reduce the use of human resources in the classification process and will bring significant enhancement to our data validation steps to ensure pattern integrity across the entire photomask manufacturing tool chain. Furthermore, the risk of anomalies introduced by updating EDA software tools and their respective version is also mitigated.
In the back-end process of mask manufacturing, AIMS™ plays a crucial role to evaluate defect printing and verify the results of repair. Comparing the difference of luminous intensity between defect and reference regions, the influence of defect could be taken into control accurately. Nevertheless, providing reference images for computation would be a tough task while performing on single die photomasks. Hence, we have developed a methodology for reference searching which take advantage of the pattern matching function in Smart-MRC. By setting up criteria with results of pattern matching, identical or extremely similar reference locations would be point out. It is more dependable and efficient than manual operation on the whole mask. With this Mask Data Preparation technique, the workflow of back-end process becomes smoothly, and the quality of photomask can be guarantee.
Mask Data Preparation, MDP contains comprehensive contents such as reticle layout, mask fracturing, manufacture rule check, etc. We have demonstrated a MDP application on KLA DB inspection. In order to calculate the rendering compensation, Pre-Swath Calibration, PSC is performed before DB inspection. We have built a rule on PSC point searching function which combines the density function of Smart MRC with algorithm. The result shows that this function could save the PSC selection time and also improvement the fail rate of PSC selection. A well-prepared inspection recipe could be done by automation tool. Therefore, the setup time on DB inspection could be minimized, also could save inspection resource as well.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.