3D-NAND flash memory is currently essential in the semiconductor industry due to the interference issue between memory cells of the conventional planar type. To vertically stack the memory, an oxide-nitride (ON) stack structure is formed using plasma enhanced chemical vapor deposition (PECVD) equipment. Thereafter, a part of the silicon nitride (Si3N4) layer is removed by wet etching using phosphoric acid (H3PO4) to make a space for the memory cell. It is important to selectively wet etch only the Si3N4 film while protecting the silicon oxide (SiO2).
The storage capacity of 3D-NAND flash memory has been enhanced by the multi-layer dielectrics. The deposition process has become more challenging due to the tight process margin and the demand for accurate process control. To reduce product costs and ensure successful processes, process diagnosis techniques incorporating artificial intelligence (AI) have been adopted in semiconductor manufacturing. Recently there is a growing interest in process diagnosis, and numerous studies have been conducted in this field.