When the high aspect ratio contact, called as HARC, hole dry etching process with a high degree of difficulty is carried out in the high performance memory manufacturing process, there is a problem that the sensitivity of the optical signal detection is low due to the small open ratio and the high aspect ratio of the hole when detecting the etching end point signal using the plasma light emission. In particular, due to the fluorocarbon polymer characteristics of fluorocarbon gas, such as C4F6, C4F8, C3F8, and CH2F2, which is mainly used in the HARC hole dry etching process, the viewport, which is a part to which the optical lens is connected to measure the plasma light emitting signal with optical emission spectroscopy, called as OES, can be contaminated with the fluorocarbon polymer coating. As a result of this viewport clogging phenomenon, the intensity of the optical signal collected gradually decreases during the process (∼4%), and thus the sensitivity of the etching end point signal indicating that the etching process is terminated gradually decreases. In this study, a xenon flashlamp for optical signal compensation was additionally applied to the existing OES structure to improve the detection of the etching end point during the HARC hole dry etching process. This can improve the detection sensitivity of the OES etching end point by monitoring the viewport clogging phenomenon in real time and compensating for the reduction of the collected OES signal. The pattern wafer for testing used to verify the effect of the etching end point consists of a structure in which a mold layer sequentially stacked with Si3N4, SiO2, and SiO2 are mixed as a single layer, and as a result of the experiment, it was confirmed that the detection sensitivity of the etching end point applied with the optical signal compensation method was 18% improved from the signal measured only by the existing OES. The method is expected to improve the detection sensitivity of etching end point during the next generation high difficulty HARC hole etching process to improve the plasma etching process control method.

As semiconductor device structures become more complex and sophisticated, the formation of finer and deeper patterns is required. To achieve a higher yield for mass production as the number of process steps increases and process variables become more diverse, process optimization requires extensive engineering effort to meet the target process requirements, such as uniformity. In this study, we propose an efficient process design framework that can efficiently search for optimal process conditions by combining deep learning (DL) with plasma simulations. To establish the DL model, a dataset was created using a two-dimensional (2D) hybrid plasma equipment model (HPEM) code for an argon inductively coupled plasma (ICP) system under a given process window. The DL model was implemented and trained using the dataset to learn the functional relationship between the process conditions and their consequential plasma states, which was characterized by 2D field data. The performance of the DL model was confirmed by comparison of the output with the ground truth, validating its high consistency. Moreover, the DL results provide a reasonable interpretation of the fundamental features of plasmas and show a good correlation with the experimental observations in terms of the measured etch rate characteristics. Using the designed DL, an extensive exploration of process variables was conducted to find the optimal processing condition using the multi-objective particle swarm optimization (MOPSO) algorithm for the given objective functions of high etch rate and its uniform distribution. The obtained optimal candidates were evaluated and compared to other process conditions experimentally, demonstrating a fairly enhanced etch rate and uniformity at the same time. The proposed computational framework substantially reduced trial-and-error repetitions in tailoring process conditions from a practical perspective. Moreover, it will serve as an effective tool to narrow the processing window, particularly in the early stages of development for advanced equipment and processes.