• 한국전기전자재료학회논문지
• /
• 제23권11호
• /
• pp.831-836
• /
• 2010

In this paper, Plasma Enhanced Chemical Vapor Deposition (PECVD) $SiO_2$ film properties are modeled using statistical analysis and neural networks. For systemic analysis, Box-Behnken's 3 factor design of experiments (DOE) with response surface method are used. For characterization, deposited film thickness and film stress are considered as film properties and three process input factors including plasma RF power, flow rate of $N_2O$ gas, and flow rate of 5% $SiH_4$ gas contained at $N_2$ gas are considered for modeling. For film thickness characterization, regression based model showed only 0.71% of root mean squared (RMS) error. Also, for film stress model case, both regression model and neural prediction model showed acceptable RMS error. For sensitivity analysis, compare to conventional fixed mid point based analysis, proposed sensitivity analysis for entire range of interest support more process information to optimize process recipes to satisfy specific film characteristic requirements.

• 대한전기학회논문지:전기물성ㆍ응용부문C
• /
• 제55권12호
• /
• pp.601-605
• /
• 2006

The resistance-capacitance (RC) delay of signals through interconnection materials becomes a big hurdle for high speed operation of semiconductors which contain multi-layer interconnections in smaller scales with higher integration density. Low-k materials are applied to the inter-metal dielectric (IMD) materials in order to overcome the RC delay. Relaxation continuum (RCT) model that includes neutral-species transport model have developed to model the etching process in a capacitively coupled plasma (CCP) device. We present the parametric study of the modeling results of a two-frequency capacitively coupled plasma (2f-CCP) with $N_2/H_2$ gas mixture that is known as promising one for organic low-k materials etching. For the etching of low-k materials by $N_2/H_2$ plasma, N and H atoms have a big influence on the materials. Moreover the distributions of excited neutral species influence the plasma density and profile. We include the neutral transport model as well as plasma one in the calculation. The plasma and neutrals are calculated self-consistently by iterating the simulation of both species till a spatio-temporal steady state profile could be obtained.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2002년도 춘계학술대회 논문집 센서 박막재료 반도체재료 기술교육
• /
• pp.1-6
• /
• 2002

Plasma processing of semiconductor materials plays a dominant role in microelectronic technology. During last century, plasma have gone a way from laboratory phenomena to industrial applications due to intensive progress in both scientific and industrial trends. Improvement and development of new experience together with development of plasma theory and plasma diagnostics methods. A most parameters (pressure, flow rate, power density) and various levels of plasma system (energy distribution, volume gas chemistry, transport, heterogeneous effects) to understand the whole process mechanism. It will allow us to choose a correct ways for processes optimization.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.1485-1488
• /
• 1997

The capacity of memory chip has increased vert quickly and 64MDRAM becomes main product in semiconductor manufacturing lines consists of many sequential processes, including etching process. although it needs direct sensing of wafer state for the accurae detching, it depends on indirect esnsing and sample test because of the complexity of the plasma etching. This equipment receives the inner light of etch chamber through the viewport and convets it to the voltage inetnsity. In this paper, EDP voltage signal has a new role to detect etching failure. First, we gathered data(EPD sigal, etching time and etchrate) and then analyzed the relationships between the signal variatin and the etch rate using two neural network modeling. These methods enable to predict whether ething state is good or not per wafer. For experiments, it is used High Density Inductive coupled Plasma(HDICP) ethcing equipment. Experiments and results proved to be abled to determine the etching state of wafer on-line and analyze the causes by modeling and EPD signal data.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
• /
• pp.234-238
• /
• 1996

In this paper, Plasma-Enhanced Chemical Vapor Deposition (PECVD) modeling using Polynomial Neural Networks (PNN) has been introduced. The deposition of SiO2 was characterized via a 25-1 fractional factorial experiment, was used to train PNNs using predicted squared error (PSE). The optimal neural network structure and learning parameters were determined by means of a second fractional factorial experiment. The optimized networks minimized both learning and prediction error. From these PNN process models, the effect of deposition conditions on film properties has been studied. The deposition experiments were carried out in a Plasma Therm 700 series PECVD system. The models obtained will ultimately be used for several other manufacturing applications, including recipe synthesis and process control.

• 제어로봇시스템학회논문지
• /
• 제4권4호
• /
• pp.506-516
• /
• 1998

In this paper, an algorithm is proposed to detect the malfunction of plasma-etching characteristics using EPD signal trajectories. EPD signal trajectories offer many information on plasma-etching process state, so they must be considered as the most important data sets to predict the wafer states in plasma-etching process. A recent work has shown that EPD signal trajectories were successfully incorporated into process modeling through critical parameter extraction, but this method consumes much effort and time. So Principal component analysis(PCA) can be applied. PCA is the linear transformation algorithm which converts correlated high-dimensional data sets to uncorrelated low-dimensional data sets. Based on this reason neural network model can improve its performance and convergence speed when it uses the features which are extracted from raw EPD signals by PCA. Wafer-state variables, Critical Dimension(CD) and uniformity can be estimated by simulation using neural network model into which EPD signals are incorporated. After CD and uniformity values are predicted, proposed algorithm determines whether malfunction values are produced or not. If malfunction values arise, the etching process is stopped immediately. As a result, through simulation, we can keep the abnormal state of etching process from propagating into the next run. All the procedures of this algorithm can be performed on-line, i.e. wafer to wafer.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.108-110
• /
• 2006

A prediction model of charge concentration of silicon nitride (SiN) thin films was constructed by using neural network and genetic algorithm. SIN films were deposited by plasma enhanced chemical vapor deposition and the deposition process was characterized by means of $2^{6-1}$ fractional factorial experiment. Effect of five training factors on the model prediction performance was optimized by using genetic algorithm. This was examined as a function of the learring rate. The root mean squared error of optimized model was 0.975, which is much smaller than statistical regression model by about 45%. The constructed model can facilitate a Qualitative analysis of parameter effects on the charge concentration.

• 반도체디스플레이기술학회지
• /
• 제18권2호
• /
• pp.48-52
• /
• 2019

Virtual metrology, which is one of APC techniques, is a method to predict characteristics of manufactured films using machine learning with saving time and resources. As the photoresist is no longer a mask material for use in high aspect ratios as the CD is reduced, hard mask is introduced to solve such problems. Among many types of hard mask materials, amorphous carbon layer(ACL) is widely investigated due to its advantages of high etch selectivity than conventional photoresist, high optical transmittance, easy deposition process, and removability by oxygen plasma. In this study, VM using different machine learning algorithms is applied to predict the thickness of ACL and trained models are evaluated which model shows best prediction performance. ACL specimens are deposited by plasma enhanced chemical vapor deposition(PECVD) with four different process parameters(Pressure, RF power, $C_3H_6$ gas flow, $N_2$ gas flow). Gradient boosting regression(GBR) algorithm, random forest regression(RFR) algorithm, and neural network(NN) are selected for modeling. The model using gradient boosting algorithm shows most proper performance with higher R-squared value. A model for predicting the thickness of the ACL film within the abovementioned conditions has been successfully constructed.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2000년도 추계학술대회논문집B
• /
• pp.720-725
• /
• 2000

To remove harmful gases from combustion exhaust gases. fundamental study on NOx removal using pulse corona discharge has been performed through experiments and simulations. The energy consumption should be decreased in order to apply non-thermal plasma technology to industry process. This work summarized the effects of $H_2O$ and Hydrocarbon additive in NOx removal efficiency. The Radical program is used to simulate high voltage discharge and the process of NOx removal. At last, experimental results were compared with simulation results to verify the reliability of this program.

• Journal of Welding and Joining
• /
• 제28권4호
• /
• pp.67-72
• /
• 2010

The purpose of this paper is to understand the behavior of GHTAW process under the space environment with the experimental and numerical analysis. Gas Hollow Tungsten Arc Welding (GHTAW) using a hollow tungsten electrode was adopted, since the ignition and discharge of a conventional GTAW process is not appropriate to the space environment due to low pressure in space. In order to clarify the phenomena of GHTAW under space environment, an investigation of thermal and physical properties of the GHTAW arc plasma was experimentally performed under low pressure conditions. Furthermore, the molten pool behavior and weldment of GHTAW were understood by CFD-based numerical analysis, based on the models of GHTA heat source, arc pressure and electromagnetic force induced by arc plasma, the characteristics of which were obtained by the captured images of a CCD camera.