• 제어로봇시스템학회:학술대회논문집
• /
• 1995.10a
• /
• pp.252-258
• /
• 1995

The purpose of this study is to provide the integrated process control system, utilizing neural network modeling, to search for the appropriate choice input, and to keep the process output within the desired rang in the real etch process.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.211-213
• /
• 2006

In this study, plasma etching process was modeled by using support vector machine (SVM). The data used in modeling were collected from the etching of silica thin films in inductively coupled plasma. For training and testing neural network, 9 and 6 experiments were used respectively. The performance of SVM was evaluated as a function of kernel type and function type. For the kernel type, Epsilon-SVR and Nu-SVR were included. For the function type, linear, polynomial, and radial basis function (RBF) were included. The performance of SVM was optimized first in terms of kernel type, then as a function of function type. Five film characteristics were modeled by using SVM and the optimized models were compared to statistical regression models. The comparison revealed that statistical regression models yielded better predictions than SVM.

• ETRI Journal
• /
• v.26 no.4
• /
• pp.297-306
• /
• 2004

A plasma is a collection of charged particles and on average is electrically neutral. In fabricating integrated circuits, plasma etching is a key means to transfer a photoresist pattern into an underlayer material. To construct a predictive model of plasma-etching processes, a polynomial neural network (PNN) is applied. This process was characterized by a full factorial experiment, and two attributes modeled are its etch rate and DC bias. According to the number of input variables and type of polynomials to each node, the prediction performance of the PNN was optimized. The various performances of the PNN in diverse environments were compared to three types of statistical regression models and the adaptive network fuzzy inference system (ANFIS). As the demonstrated high-prediction ability in the simulation results shows, the PNN is efficient and much more accurate from the point of view of approximation and prediction abilities.

• Journal of information and communication convergence engineering
• /
• v.3 no.4
• /
• pp.187-190
• /
• 2005

High aspect ratio via-hole etching process has emerged as one of the most crucial means to increase component density for ULSI devices. Because of charge accumulation in via-hole, this sophisticated and important process still hold several problems, such as etching stop and loading effects during fabrication of integrated circuits. Indeed, the concern actually depends on accumulated charge. For monitoring accumulated charge during plasma etching process, charge-up monitoring sensor was fabricated and tested under some plasma conditions. This paper presents a neural network-based technique for analyzing and modeling several electrical performance of plasma charge-up monitoring sensor.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.303-306
• /
• 2005

High aspect ration via-hole etching process has emerged as one of the most crucial means to increase component density for ULSI devices. Because of charge accumulation in via hole, this sophisticated and important process still hold several problems, such as etching stop, loading effects during fabrication of integrated circuits. Indeed, the concern actually depends on accumulated charge. For monitoring accumulated charge during plasma etching process, charge-up monitoring sensor was fabricated and tested under some plasma conditions. This paper presents a neural network-based technique for analyzing and modeling several electrical performance of plasma charge-up monitoring sensor.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.18 no.1
• /
• pp.1-5
• /
• 2005

A new model of plasma etch process was constructed by using a radial basis function network (RBFN). This technique was applied to an etching of silicon carbide films in a NF$_3$ inductively coupled plasma. Experimental data to train RBFN were systematically collected by means of a 2$^4$ full factorial experiment. Appropriateness of prediction models was tested with test data consisted of 16 experiments not pertaining to the training data. Prediction performance was optimized with variations in three training factors, the number of pattern units, width of radial basis function, and initial weight distribution between the pattern and output layers. The etch responses to model were an etch rate and a surface roughness measured by atomic force microscopy. Optimized models had the root mean-squared errors of 26.1 nm/min and 0.103 nm for the etch rate and surface roughness, respectively. Compared to statistical regression models, RBFN models demonstrated an improvement of more than 20 % and 50 % for the etch rate and surface roughness, respectively. It is therefore expected that RBFN can be effectively used to construct prediction models of plasma processes.

• Transactions on Control, Automation and Systems Engineering
• /
• v.2 no.4
• /
• pp.268-273
• /
• 2000

Plasma models are crucial to equipment design and process optimization. A radial basis function network(RBFN) in con-junction with statistical experimental design has been used to model a process plasma. A 2$^4$ full factorial experiment was employed to characterized a hemispherical inductively coupled plasma(HICP) in characterizing HICP, the factors that were varied in the design include source power, pressure, position of shuck holder, and Cl$_2$ flow rate. Using a Langmuir probe, plasma attributes were collected, which include typical electron density, electron temperature. and plasma potential as well as their spatial uniformity. Root mean-squared prediction errors of RBEN are 0.409(10(sup)12/㎤), 0.277(eV), and 0.699(V), for electron density, electron temperature, and Plasma potential, respectively. For spatial uniformity data, they are 2.623(10(sup)12/㎤), 5.704(eV) and 3.481(V), for electron density, electron temperature, and plasma potential, respectively. Comparisons with generalized regression neural network(GRNN) revealed an improved prediction accuracy of RBFN as well as a comparable performance between GRNN and statistical response surface model. Both RBEN and GRNN, however, experienced difficulties in generalizing training data with smaller standard deviation.

• Proceedings of the KIPE Conference
• /
• 2006.06a
• /
• pp.470-474
• /
• 2006

This dissertation discuses about a ferrite core plasma source using low operating frequency without sputtering problem by the stored electric field. Compared with the conventional RF power system with 13.56MHz switching frequency, the proposed plasma power system is only separated at 400kHz, so that it makes possible to use of low cost switching elements, PWM control and soft switching. Moreover, it could improve the coupling efficiency for plasma and antenna by using the ferrite core in order to transfer the energy of the load This dissertation tried to analyze new plasma generation method for the plasma generation system by modeling the plasma load and grafting the concept of impedance matching in order to interpret it with the formula This dissertation verified the ferrite core inductive coupling plasma source authorized for 400kHz of low frequency power by applying to the semi-conductor ash process thru the measurement of ash capacity and uniformed plasma distribution on the actual wafer.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2003.07a
• /
• pp.58-62
• /
• 2003

Silicon carbide (SiC) was etched in a $NF_3/CH_4$ inductively coupled plasma. The etch process was modeled by using a neural network called generalized regression neural network (GRNN). For modeling, the process was characterized by a $2^4$ full factorial experiment with one center point. To test model appropriateness, additional test data of 16 experiments were conducted. Particularly, the GRNN predictive capability was drastically improved by a genetic algorithm (GA). This was demonstrated by an improvement of more than 80% compared to a conventionally obtained model. Predicted model behaviors were highly consistent with actual measurements. From the optimized model, several plots were generated to examine etch rate variation under various plasma conditions. Unlike the typical behavior, the etch rate variation was quite different depending on the bias power Under lower bias powers, the source power effect was strongly dependent on induced dc bias. The etch rate was strongly correated to the do bias induced by the gas ratio. Particularly, the etch rate variation with the bias power at different gas ratio seemed to be limited by the etchant supply.

• Journal of the Korean Society of Industry Convergence
• /
• v.6 no.4
• /
• pp.277-289
• /
• 2003

This study proposes a mathematical model to characterize the removal of nitrogen oxides in a dielectric barrier discharge plasma process. As well as the reactions between nitrogen oxides, water vapor, oxygen and nitrogen, the model takes into account the effect of ethylene often used as a chemical additive to reduce the power consumption of the process on the removal of nitrogen oxides. Since the concentrations of the radicals concerned in the main reactions including O, OH, H and N should be calculated to predict the removal efficiency of nitrogen oxides, they were theoretically derived. The parameters affecting the removal of nitrogen oxides, such as initial concentration, discharge power, humidity, and ethylene concentration were experimentally evaluated, which were compared with the calculated results to verify the validity of the model proposed. The predicted concentrations of several byproducts formed in this process were also presented and discussed. The effects of several parameters mentioned above on the removal of nitrogen oxides were reasonable described by the proposed model.