• Journal of the Korean institute of surface engineering
• /
• v.41 no.6
• /
• pp.279-286
• /
• 2008

Numerical analysis is done to investigate which would be the most influencing process parameter in determining the uniformity of deposition thickness in TiN ICP-CVD(inductively coupled plasma chemical vapor deposition). Two configurations of ICP antenna are modeled; side and top planar. Side and top gas inlets are considered with each ICP antenna geometries. Precursor for TiN deposition was TDMAT(Tetrakis Diethyl Methyl Amido Titanium). Two step volume dissociation of TDMAT is used and absorption, desorption and deposition surface reactions are included. Most influencing factors are H and N concentration dissociated by electron impact collisions in plasma volume which depends on the relative positions of gas inlet and ICP antenna generated hot plasma region. Low surface recombination of N shows hollow type concentration, but H gives a bell type distribution. Film thickness at substrate edges is sensitive to gas flow rate and at high pressures getting more dependent on flow characteristics.

• Journal of Powder Materials
• /
• v.27 no.5
• /
• pp.365-372
• /
• 2020

Predicting the quality of materials after they are subjected to plasma sintering is a challenging task because of the non-linear relationships between the process variables and mechanical properties. Furthermore, the variables governing the sintering process affect the microstructure and the mechanical properties of the final product. Therefore, an artificial neural network modeling was carried out to correlate the parameters of the spark plasma sintering process with the densification and hardness values of Ti-6Al-4V alloys dispersed with nano-sized TiN particles. The relative density (%), effective density (g/㎤), and hardness (HV) were estimated as functions of sintering temperature (℃), time (min), and composition (change in % TiN). A total of 20 datasets were collected from the open literature to develop the model. The high-level accuracy in model predictions (>80%) discloses the complex relationships among the sintering process variables, product quality, and mechanical performance. Further, the effect of sintering temperature, time, and TiN percentage on the density and hardness values were quantitatively estimated with the help of the developed model.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.4
• /
• pp.315-319
• /
• 2007

A technique to model plasma processes was presented. This was accomplished by combining the backpropagation neural network (BPNN) and genetic algorithm (GA). Particularly, the GA was used to optimize five training factor effects by balancing the training and test errors. The technique was evaluated with the plasma etch data, characterized by a face-centered Box Wilson experiment. The etch outputs modeled include Al etch rate, AI selectivity, DC bias, and silica profile angle. Scanning electron microscope was used to quantify the etch outputs. For comparison, the etch outputs were modeled in a conventional fashion. GABPNN models demonstrated a considerable improvement of more than 25% for all etch outputs only but he DC bias. About 40% improvements were even achieved for the profile angle and AI etch rate. The improvements demonstrate that the presented technique is effective to improving BPNN prediction performance.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.1 no.1
• /
• pp.87-94
• /
• 2001

Silicon nitride films grown by plasma-enhanced chemical vapor deposition (PECVD) are useful for a variety of applications, including anti-reflecting coatings in solar cells, passivation layers, dielectric layers in metal/insulator structures, and diffusion masks. PECVD systems are controlled by many operating variables, including RF power, pressure, gas flow rate, reactant composition, and substrate temperature. The wide variety of processing conditions, as well as the complex nature of particle dynamics within a plasma, makes tailoring SiN film properties very challenging, since it is difficult to determine the exact relationship between desired film properties and controllable deposition conditions. In this study, SiN PECVD modeling using optimized neural networks has been investigated. The deposition of SiN was characterized via a central composite experimental design, and data from this experiment was used to train and optimize feed-forward neural networks using the back-propagation algorithm. From these neural process models, the effect of deposition conditions on film properties has been studied. A recipe synthesis (optimization) procedure was then performed using the optimized neural network models to generate the necessary deposition conditions to obtain several novel film qualities including high charge density and long lifetime. This optimization procedure utilized genetic algorithms, hybrid combinations of genetic algorithm and Powells algorithm, and hybrid combinations of genetic algorithm and simplex algorithm. Recipes predicted by these techniques were verified by experiment, and the performance of each optimization method are compared. It was found that the hybrid combinations of genetic algorithm and simplex algorithm generated recipes produced films of superior quality.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.20-20
• /
• 2000

Back-propagation neural network (BPNN) is the most prevalently used paradigm in modeling semiconductor manufacturing processes, which as a neuron activation function typically employs a bipolar or unipolar sigmoid function in either hidden and output layers. In this study, applicability of another linear function as a neuron activation function is investigated. The linear function was operated in combination with other sigmoid functions. Comparison revealed that a particular combination, the bipolar sigmoid function in hidden layer and the linear function in output layer, is found to be the best combination that yields the highest prediction accuracy. For BPNN with this combination, predictive performance once again optimized by incrementally adjusting the gradients respective to each function. A total of 121 combinations of gradients were examined and out of them one optimal set was determined. Predictive performance of the corresponding model were compared to non-optimized, revealing that optimized models are more accurate over non-optimized counterparts by an improvement of more than 30%. This demonstrates that the proposed gradient-optimized teaming for BPNN with a linear function in output layer is an effective means to construct plasma models. The plasma modeled is a hemispherical inductively coupled plasma, which was characterized by a 24 full factorial design. To validate models, another eight experiments were conducted. process variables that were varied in the design include source polver, pressure, position of chuck holder and chroline flow rate. Plasma attributes measured using Langmuir probe are electron density, electron temperature, and plasma potential.

• Journal of the Korean institute of surface engineering
• /
• v.48 no.4
• /
• pp.179-184
• /
• 2015

Quadrupole Mass Spectrometers (QMS) is a very useful tool in vacuum process diagnosis. Tungsten filament based ion sources are vulnerable to contamination from process gas monitoring. Common symptoms of quadrupole mass spectrometer malfunction is appearance of unwanted contaminant mass peaks or no detection of any ion peaks. We disassembled used quadrupole mass spectrometer and found out black insulating deposits on inside of ion source parts. Five steps of cleaning procedure were applied and almost full restoration of functions were confirmed in two types of closed ion source quadrupole mass spectrometer. By using a numerical modeling (CFD-ACE+) technique, the electric potential profile of ion source with/without insulating deposit was calculated and showed the possibility of quadrupole mass spectrometer malfunction by the deterioration of designed potential profile inside the ion source.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.99-101
• /
• 2006

Auto-Cross Correlated time series (ACTS) model was constructed by using the backpropagation neural network. The performance of ACTS model was evaluated with sensor information collected from a large volume, industrial plasma-enhanced chemical vapor deposition system. A total of 18 sensor information were collected. The effect of inclusion of past and future information were examined. For all but three sensor information with a large data variance demonstrated a prediction error less than 3%. By integrating ACTS model into equipment software, process quality can be more stringently monitored while improving device throughput.

• Transactions on Electrical and Electronic Materials
• /
• v.6 no.6
• /
• pp.262-271
• /
• 2005

In order to achieve timely and accurate fault detection of plasma etching process, neural network based time series modeling has been applied to reactive ion etching (RIE) using two different in-situ plasma-monitoring sensors called optical emission spectroscopy (OES) and residual gas analyzer (RGA). Four different subsystems of RIE (such as RF power, chamber pressure, and two gas flows) were considered as potential sources of fault, and multiple degrees of faults were tested. OES and RGA data were simultaneously collected while the etching of benzocyclobutene (BCB) in a $SF_6/O_2$ plasma was taking place. To simulate established TSNNs as incipient fault detectors, each TSNN was trained to learn the parameters at t, t+T, ... , and t+4T. This prediction scheme could effectively compensate run-time-delay (RTD) caused by data preprocessing and computation. Satisfying results are presented in this paper, and it turned out that OES is more sensitive to RF power and RGA is to chamber pressure and gas flows. Therefore, the combination of these two sensors is recommended for better fault detection, and they show a potential to the applications of not only incipient fault detection but also incipient real-time diagnosis.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.3
• /
• pp.70-79
• /
• 1996

In off-line process optimization, process parameters are controlled such that the process is robust against changes in equipment conditions and incoming materials. The off-line methods, however, are not effective when the changes are so large that process parameters need to be adjusted. On-line control can respond to such large changes, but process uniformity has not been controlled on-line due to the difficulties in modeling. This paper is aimed at developing a new on-line control methodology where the uniformity is controlled effectively. The process variability is categorized based on the physical considerations, and the process parameters are classi- fied considering their effects on the categorized process variabilities. On-line control is performed with the properly selected process parameters so that robustness may not be degraded. The developed methodology is applied to the single wafer plasma etching processes, which resulted in both higher within-a-wafer uniformity and compens- ation of the incoming material non-uniformity.

• Journal of the Korean Vacuum Society
• /
• v.19 no.3
• /
• pp.190-198
• /
• 2010

Asymmetric model for plasma uniformity by Ar and $CF_4$ was modeled by the antenna structure, the diameter of chamber, and the distance between source and substrate for the development of plasma equipment for 450 mm wafer. The aspect ratio of chamber was divided by diameter, distance from substrate, and pumping port area. And we found the condition with the optimized plasma uniformity by changing the antenna structure. The drift diffusion and quasi-neutrality for simplification were used, and the ion energy function was activated for the surface recombination and etching reaction. The uniformity of plasma density on substrate surface was improved by being far of the distance between substrate wall and chamber wall, and substrate and plasma source. And when the antenna of only 2 turns was used, the plasma uniformity can improve from 20~30% to 4.7%.