MODELING AND CONTROL OF A SEMICONDUCTOR MANUFACTURING PROCESS WITH ANAUTOMATA NETWORK - AN EXAMPLE IN PLASMA ETCH PROCESSING

A neural network model of a plasma gate etch process is described and compared with a statistical model. The neural network model has a corr elation of 0.68 while the statistical model has a correlation of 0.45. From our model we deduce that the flow rate of the etching gases and the induced d.c.-bias are the key factors driving the etching and thus the remaining oxide thickness at the end of the etch. An adaptive neu ral network controller for wafer-to-wafer plasma etch control is also described. It uses real time process signatures and historical data fr om a relational database for a computation of the overetch time for th e current wafer etching within the reactor. For an MOS gate etch the s tandard deviation of the oxide thickness between the gate and the sour ce (or drain) is in the range of 10 Angstrom. This is comparable to op en-loop control or timed etch where the operator selects the ideal ove retch time. The controller has thus achieved better than human equival ence. Copyright (C) 1996 Elsevier Science Ltd