In the semiconductor industry, run-to-run (R2R) control is an important technique to improve process capability and further enhance the production yield. As the dimension of electronic devices shrink increasingly, wafer-to-wafer (W2W) advanced process control (APC) becomes essential for the critical stages of production processes. W2W APC requires the metrology values of each wafer; however, it will be highly time and cost consuming to obtain actual metrology values from each wafer by physical measurement. Recently, an efficient and cost-effective approach denoted "virtual metrology (VM)" was proposed to substitute the actual metrology. To implement VM in W2W APC, both conjecture-accuracy and real-time requirements need to be considered. In this paper, various VM algorithms, including back-propagation neural networks (BPNN), simple recurrent neural networks (SRNN), and multiple regression (MR), are evaluated to see whether they can meet the accuracy and real-time requirements of W2W APC or not. The fifth generation TFT-LCD chemical-vapor deposition process is used to test and verify the requirements. Test results show that both one-hidden-layered BPNN and SRNN VM algorithms achieve acceptable conjecture accuracy and meet the real-time requirements of semiconductor and TFT-LCD W2W APC applications.
All Science Journal Classification (ASJC) codes