Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
WSEAS Transactions on Systems and Control
Hi-index | 0.00 |
A leak of plasma chamber should be strictly monitored to maintain process quality as well as device yield. Using an Auto-Correlated Time Series Neural Network (A-NTS), a prediction model of chamber leak was developed. A total of 47 leak patterns were used to construct and test the monitoring efficacy of model. The validation errors for normal and abnormal data ranged between 51.9 and 61.7, and between 126.0 and 163.8, respectively. The validation errors for the abnormal data were more than two times larger than those for the normal data. This clearly indicates that the A-NTS model can accurately detect a leak from the chamber of plasma equipment.