• Title/Summary/Keyword: Neural Network Modeling

Search Result 749, Processing Time 0.038 seconds

Modeling of Plasma Etch Non-Uniformity by Using OES Information and Neural Network (OES 정보와 신경망을 이용한 플라즈마 식각들 비균일도의 모델링)

  • Kwon, Min-Ji;Kim, Byung-Whan
    • Proceedings of the KIEE Conference
    • /
    • 2007.10a
    • /
    • pp.403-404
    • /
    • 2007
  • 소자 수율을 향상시키기 위해서는 웨이퍼 전체에 걸쳐 플라즈마 공정특성이 균일하게 분포되어야 한다. 본 연구에서는 Actinomeric 광 반사분광기 (Otical Emission Spectroscopy) 정보를 이용하여 식각률 비균일도에 대한 모델을 개발하였다. 제안된 기법은 Oxide 식각공정에서 수집한 데이터에 적용하였으며, 체계적인 모델링을 위해 공정데이터는 통계적 실험계획 법을 적용하여 수집되었다. 신경망의 예측성능은 유전자 알고리즘을 이용해서 증진시켰다. OES의 차수를 줄이기 위해 주인자 분석을 세 종류의 분산(100, 99, 98%)에 대해서 적용하였다. 개발된 모델은 발표된 이전의 모델에 비해 17% 증진된 예측성능을 보였다.

  • PDF

Algorithm of Thermal Error Compensation for the Line Center - System Interface - (CNC공작기계의 열변형 오차보정 (II) - 알고리즘 및 시스템 인터폐이스 중심 -)

  • 이재종;최대봉;박현구;류길상
    • Proceedings of the Korean Society of Machine Tool Engineers Conference
    • /
    • 2002.10a
    • /
    • pp.417-422
    • /
    • 2002
  • One of the major limitations of productivity and quality in metal cutting is the machining accuracy of machine tools. The machining accuracy is affected by geometric errors, thermally-induced errors, and the deterioration of the machine tools. Geometric and thermal errors of machine tools should be measured and compensated to manufacture high quality products. In metal cutting, the machining accuracy is more affected by thermal errors than by geometric errors. In this study, the compensation device and temperature-based algorithm have been implemented on the machining center in order to compensate thermal error of machine tools under the real-time. The thermal errors are predicted using the neural network and multi-regression modeling methods. In order to compensate thermal characteristics under several operating conditions, experiments performed with five gap sensors and manufactured compensation device on the horizontal machining center.

  • PDF

Modeling of Secondary Path in an Active Noise Control Using Time Delay Neural Network (시간 지연 신경 회로망을 이용한 능동 소음 제어 시스템의 2차 경로 모델링)

  • 이병도;이민호
    • The Journal of the Acoustical Society of Korea
    • /
    • v.17 no.8
    • /
    • pp.19-24
    • /
    • 1998
  • 이 논문에서는 능동 소음 제어 시스템을 구성하는 요소들인 증폭기와 저주파 필터 와 같은 소자들의 비선형 특성과 공간에서의 주파수 대역에 따른 비선형 특성을 보상하여, 보다 효과적인 능동 소음 제어기를 설계하기 위해 시간 지연 신경 회로망을 이용하는 새로 운 방법을 제안한다. 공간을 포함한 2차 경로 함수를 모델링하여 보다 나은 성능을 갖는 능 동 소음 제어기를 구성하기 위한 기존의 최소 자승 오차 알고리듬에 기반한 filtered-x least mean square(LMS) 알고리듬과 오차 역전달 학습 알고리듬을 갖는 시간 지연 다층 구조 인 식자를 이용한 결과를 간단한 실험을 통하여 그 성능을 비교 분석한다.

  • PDF

Sensitivity analysis of skull fracture

  • Vicini, Anthony;Goswami, Tarun
    • Biomaterials and Biomechanics in Bioengineering
    • /
    • v.3 no.1
    • /
    • pp.47-57
    • /
    • 2016
  • Results from multiple high profile experiments on the parameters influencing the impacts that cause skull fractures to the frontal, temporal, and parietal bones were gathered and analyzed. The location of the impact as a binary function of frontal or lateral strike, the velocity, the striking area of the impactor, and the force needed to cause skull fracture in each experiment were subjected to statistical analysis using the JMP statistical software pack. A novel neural network model predicting skull fracture threshold was developed with a high statistical correlation ($R^2=0.978$) and presented in this text. Despite variation within individual studies, the equation herein proposes a 3 kN greater resistance to fracture for the frontal bone when compared to the temporoparietal bones. Additionally, impacts with low velocities (<4.1 m/s) were more prone to cause fracture in the lateral regions of the skull when compared to similar velocity frontal impacts. Conversely, higher velocity impacts (>4.1 m/s) showed a greater frontal sensitivity.

Surrogate Modeling for Optimization of a Centrifugal Compressor Impeller

  • Kim, Jin-Hyuk;Choi, Jae-Ho;Kim, Kwang-Yong
    • International Journal of Fluid Machinery and Systems
    • /
    • v.3 no.1
    • /
    • pp.29-38
    • /
    • 2010
  • This paper presents a procedure for the design optimization of a centrifugal compressor. The centrifugal compressor consists of a centrifugal impeller, vaneless diffuser and volute. And, optimization techniques based on the radial basis neural network method are used to optimize the impeller of a centrifugal compressor. The Latin-hypercube sampling of design-of-experiments is used to generate the thirty design points within design spaces. Three-dimensional Reynolds-averaged Navier-Stokes equations with the shear stress transport turbulence model are discretized by using finite volume approximations and solved on hexahedral grids to evaluate the objective function of the total-to-total pressure ratio. Four variables defining the impeller hub and shroud contours are selected as design variables in this optimization. The results of optimization show that the total-to-total pressure ratio of the optimized shape at the design flow coefficient is enhanced by 2.46% and the total-to-total pressure ratios at the off-design points are also improved significantly by the design optimization.

Speed control of AC Servo Motor with Neuro-Fuzzy Controller (뉴로-퍼지 제어기를 이용한 교류 서보 전동기의 속도제어)

  • Kim, Jong-Hyun;Kim, Sang-Hoon;Ko, Bong-Un;Kim, Lark-Kyo
    • Proceedings of the KIEE Conference
    • /
    • 2001.07d
    • /
    • pp.2018-2020
    • /
    • 2001
  • In this study, a Neuro-Fuzzy Controller which has the characteristic of Fuzzy control and Artificial Neural Network is designed. A fuzzy rule to be applied is automatically selected by the allocated neurons. The neurons correspond to Fuzzy rules are created by an expert. To adapt the more precise modeling is implemented by error back propagation learning of adjusting the link-weight of fuzzy membership function in the Neuro-Fuzzy controller. The more classified fuzzy rule is used to include the property of dual mode method. In order to verify the effectiveness of an algorithm designed above, an operating characteristic of a AC servo motor is investigated.

  • PDF

Power Flow Control of Grid-Connected Fuel Cell Distributed Generation Systems

  • Hajizadeh, Amin;Golkar, Masoud Aliakbar
    • Journal of Electrical Engineering and Technology
    • /
    • v.3 no.2
    • /
    • pp.143-151
    • /
    • 2008
  • This paper presents the operation of Fuel Cell Distributed Generation(FCDG) systems in distribution systems. Hence, modeling, controller design, and simulation study of a Solid Oxide Fuel Cell(SOFC) distributed generation(DG) system are investigated. The physical model of the fuel cell stack and dynamic models of power conditioning units are described. Then, suitable control architecture based on fuzzy logic and the neural network for the overall system is presented in order to activate power control and power quality improvement. A MATLAB/Simulink simulation model is developed for the SOFC DG system by combining the individual component models and the controllers designed for the power conditioning units. Simulation results are given to show the overall system performance including active power control and voltage regulation capability of the distribution system.

Neural Network Modeling for HDP-CVD Process Optimization of $SiO_2$ Thin Film Deposition (HDP-CVD로 증착된 실리콘 산화막 공정조건 최적화를 위한 신경망 모델링)

  • Park, In-Hye;Yu, Gyeong-Han;Seo, Dong-Seon;Hong, Sang-Jin
    • Proceedings of the Korean Institute of Surface Engineering Conference
    • /
    • 2006.10a
    • /
    • pp.2-3
    • /
    • 2006
  • 본 논문에서는 신경망 모델링을 통하여 HDP-CVD를 이용한 실리콘 산화막 형성에 영향을 주는 다섯 가지 공정 장비 변수와 그에 따른 두 가지 출력 파라미터 Deposition rate과 Uniformity와의 관계를 동시에 고려한 특성결과를 분석하고, 최적의 recipe를 Genetic Algorithm을 통해 제시하였다. 실험계획법을 사용하여, 필요한 실험의 횟수를 최소화 하였으며 그 실험결과를 신경망 모델링을 통하여 입력변수와 출력파라미터의 관계를 3차원의 반응표면 곡선으로 분석하였다. 이 과정을 통해 Deposition rate과 Uniformity을 동시에 고려한 두 출력파라미터를 만족하는 최적의 입력변수 값들을 제시하였다.

  • PDF

Design a System for Analysis of Distributing Board with Grounding Resistance (배전반 접지저항 해석을 위한 시스템 설계)

  • Ko, Bong-Woon;Boo, Chang-Jin;Choi, Seung-Joon;Jeong, Kwang-Ja
    • Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
    • /
    • 2009.05a
    • /
    • pp.380-383
    • /
    • 2009
  • The grounding system of the subsurface should ensure the safe and reliable operation of power systems, and guarantee a human being's safety in the situation of grounding fault in the power system. The safety of power apparatus in the subsurface can be reached by decreasing grounding resistance and grounding potential rise of subsurface. This paper presents a method based on the design of an artificial neural network(ANN) model for modeling and predicting the relationship between the grounding resistance and temperature-humidity in the subsurface.

  • PDF

Charge Density Modeling of Silion Nitride Thin Films Using Neural Network (신경망을 이용한 실리콘 나이트라이드 박막의 전하밀도 모델링)

  • Gwon, Sang-Hui;Kim, Byeong-Hwan
    • Proceedings of the Korean Institute of Surface Engineering Conference
    • /
    • 2007.11a
    • /
    • pp.114-115
    • /
    • 2007
  • 플라즈마 응용화학기상법을 이용하여 Silicon Nitride (SiN) 박막을 증착하였다. PECVD 공정은 Box Wilson 실험계획표를 이용하여 수행하였다. SiN박막의 전하밀도를 신경망과 유전자 알고리즘을 이용하여 모델링하였다. 개발된 모델을 이용하여 전하밀도에의 $N_2$$NH_3$의 영향을 다양한 온도에서 고찰하였다. $N_2$ (or $NH_3$)의 증가에 따라 전하밀도는 증가하였으며, 이는 전하밀도의 [N-H]에의 강하게 의존하고 있음을 보인다. 전하밀도는 고온에서의 $NH_3$의 증가, 또는 높은 $NH_3$ 유량에서의 온도의 증가에 따라 급격히 증가하였다. 굴절률 모델과 비교할 때, 이 같은 현상이 [N-H]의 증가에 기인하는 것으로 해석되었다.

  • PDF