No abstract

We have developed a gate oxide thickness controller for a plasma etch reactor. This controller is for a 0.9 um technology currently being manufactured in our Orlando CMOS fab line. By monitoring certain process signatures aren feeding them forward into a neural network trained by the backpropagation method, it is possible to predict in real time the correct over etch time on a wafer-by-wafer basis. Computer simulations indicate that the neural network is equivalent to humans for this task.The uniqueness of this controllere is compared with a previous controller for a 1.25 um technology gate etch process.

No abstract

No abstract