• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국내학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.212-217
• /
• 1993

In this paper, the hardening depth in Laser surface hardening process is estimated using a multilayered neural network. Input data of the neural network are surface temperature of five points, power and travelling speed of Laser beam. A FDM(finite difference method) is used for modeling the Laser surface hardening process. This model is used to obtain the network's training data sample and to evaluate the performance of the neural network estimator. The simulational results showed that the proposed scheme can be used to estimate the hardening depth on real time.

• 한국콘텐츠학회논문지
• /
• 제9권1호
• /
• pp.348-358
• /
• 2009

미만성 축삭손상(diffuse axonal injury)은 외상성 뇌손상의 일반적인 형태이며, 인지 장애의 주요 원인으로 생각되어 진다. 흔들린 아기 증후군(shaken baby syndrome)과 같이 뇌에 전단력이 심하게 가해졌을 때도 신체 장애 뿐만 아니라 인지 장애가 특징적으로 나타난다. 신체 활동은 건강 증진과 더불어 기억 및 학습과 관련된 해마의 기능 향상에도 영향을 미친다. 본 연구의 목적은 흰쥐를 대상으로 미만성 축삭 손상을 일으킨 후 반복적인 운동 훈련을 통해 운동 수행력을 관찰하고 해마에서 GAP-43의 발현을 통해 축삭 재생의 변화를 관찰하는 것이었다. 실험동물은 운동 훈련을 적용시키는 실험군과 대조군으로 구분하였고, 각각의 군을 다시 1일, 7일 및 14일군으로 구분하였다. 그 결과, 운동 훈련을 적용시킨 실험군이 대조군보다 운동 수행력의 향상이 더 유의했으며, 해마에서 GAP-43의 발현도 같은 양상을 나타냈다. 이러한 차이는 7일군과 14일군보다 1일군과 7일군 사이에 더 크게 나타났다. 그러므로 미만성 축삭손상 후 운동 훈련은 운동 수행력의 향상에 영향을 미치며, 인지와 관련된 해마의 구조적 변화도 야기 시키는 것으로 생각된다.

• 한국멀티미디어학회논문지
• /
• 제13권10호
• /
• pp.1547-1556
• /
• 2010

현재까지 유아나 장애인을 위한 컴퓨터 활용 교육 콘텐츠는 지각훈련, 인지훈련, 한글 교육 등 다양한 분야에서 개발되었으나 가장 큰 문제점은 컴퓨터 모니터 앞에서 장시간 마우스를 이용하여 교육을 할 경우 활동성이 저하된다는 점이다. 이것은 특히 왕성하게 운동 능력이 발달하는 시기의 유아와 운동 장애로 인해 활동 기회가 부족한 장애 아동에게 적잖은 문제점으로 지적되어 왔다. 이와 같은 문제점을 개선하고 활동성과 협동력, 몰입성을 강화시키는 콘텐츠를 개발하기 위해서는 터치스크린과 같은 스크린 상에서 인간의 동작을 인식하여 이를 대화식으로 보여주는 기술이 필요하다 본 연구에서는 기존의 컴퓨터 활용 콘텐츠의 단점을 보완하고, 사용자의 활동성을 강화하기 위해 위모트가 가지는 센서 기술을 활용하여 실시간으로 빔 프로젝터나 컴퓨터 스크린으로 교육콘텐츠를 제공하고 신체를 직접 움직이며 적외선 펜을 사용하여 자극에 반응하는 교육 콘텐츠를 개발하였다.

• Advances in aircraft and spacecraft science
• /
• 제7권4호
• /
• pp.353-369
• /
• 2020

This paper presents the flutter analysis and optimum design of axially functionally graded box beam cantilever wing section by considering various geometric and material parameters. The coupled dynamic equations of the continuous model of wing system in terms of material and cross-sectional properties are formulated based on extended Hamilton's principle. By expressing the lift and pitching moment in terms of plunge and pitch displacements, the resultant two continuous equations are simplified using Galerkin's reduced order model. The flutter velocity is predicted from the solution of resultant damped eigenvalue problem. Parametric studies are conducted to know the effects of geometric factors such as taper ratio, thickness, sweep angle as well as material volume fractions and functional grading index on the flutter velocity. A generalized surrogate model is constructed by training the radial basis function network with the parametric data. The optimized material and geometric parameters of the section are predicted by solving the constrained optimal problem using firefly metaheuristics algorithm that employs the developed surrogate model for the function evaluations. The trapezoidal hollow box beam section design with axial functional grading concept is illustrated with combination of aluminium alloy and aluminium with silicon carbide particulates. A good improvement in flutter velocity is noticed by the optimization.

• International Journal of Concrete Structures and Materials
• /
• 제1권1호
• /
• pp.63-73
• /
• 2007

Optimum multi-layered feed-forward neural network (NN) models using a resilient back-propagation algorithm and early stopping technique are built to predict the shear capacity of reinforced concrete deep and slender beams. The input layer neurons represent geometrical and material properties of reinforced concrete beams and the output layer produces the beam shear capacity. Training, validation and testing of the developed neural network have been achieved using 50%, 25%, and 25%, respectively, of a comprehensive database compiled from 631 deep and 549 slender beam specimens. The predictions obtained from the developed neural network models are in much better agreement with test results than those determined from shear provisions of different codes, such as KBCS, ACI 318-05, and EC2. The mean and standard deviation of the ratio between predicted using the neural network models and measured shear capacities are 1.02 and 0.18, respectively, for deep beams, and 1.04 and 0.17, respectively, for slender beams. In addition, the influence of different parameters on the shear capacity of reinforced concrete beams predicted by the developed neural network shows consistent agreement with those experimentally observed.

• 음성과학
• /
• 제8권4호
• /
• pp.17-33
• /
• 2001

In this paper, we implement the large variable vocabulary speech recognition system, which is characterized by no additional pre-training process and no limitation of recognized word list. We have designed the system in order to achieve the high recognition rate using the decision tree based state tying algorithm and in order to reduce the processing time using the gaussian selection based variable flooring algorithm, the limitation algorithm of the number of nodes and ENNS algorithm. The gaussian selection based variable flooring algorithm shows that it can reduce the total processing time by more than half of the recognition time, but it brings about the reduction of recognition rate. In other words, there is a trade off between the recognition rate and the processing time. The limitation algorithm of the number of nodes shows the best performance when the number of gaussian mixtures is a three. Both of the off-line and on-line experiments show the same performance. In our experiments, there are some differences of the recognition rate and the average recognition time according to the distinction of genders, speakers, and the number of vocabulary.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2013년도 추계학술대회 논문집
• /
• pp.320-324
• /
• 2013

A crack identification method using an equivalent bending stiffness for cracked beam and committee of neural networks is presented. The equivalent bending stiffness is constructed based on an energy method for a straight thin-walled pipe, which has a through-the-thickness crack, subjected to bending. Several numerical analysis for a steel cantilever pipe using the equivalent bending stiffness are carried out to extract the natural frequencies and mode shapes of the cracked beam. The extracted modal properties are used in constructing a training patterns of a neural network. The input to the neural network consists of the modal properties and the output is composed of the crack location and size. Multiple neural networks are constructed and each individual network is trained independently with different initial synaptic weights. Then, the estimated crack locations and sizes from different neural networks are averaged. Experimental crack detection is carried out for 3 damage cases using the proposed method, and the identified crack locations and sizes agree reasonably well with the exact values.

• 한국자동차공학회논문집
• /
• 제14권6호
• /
• pp.190-194
• /
• 2006

This research investigates vehicle structure acceleration and vehicle deformation with RCAR crash test. To investigate vehicle damage characteristics in an individual case, it is possible to RCAR low speed crash test. In this study, two tests were conducted to evaluate difference between RCAR new condition and RCAR old condition. A two large vehicles were subjected to a frontal crash test at a speed of 15km/h with an offset of 40% $10^{\circ}$ angle barrier and flat barrier. The results of the 15km/h with an offset of 40% $10^{\circ}$ angle barrier revealed high acceleration value on the vehicle structure and high repair cost compared to the RCAR 15km/h with an offset of 40% flat barrier. So in order to improve damage characteristics in low speed crash of vehicle structure and body component of the monocoque type passenger vehicles, the end of front side member and front back beam should be designed with optimum level and to supply the end of front side member as a partial condition approx 300mm.

• 한국자동차공학회논문집
• /
• 제13권2호
• /
• pp.108-113
• /
• 2005

The damageability and repairability of similar platform type vehicles could be very concerned with design optimization. In all the vehicles crash tested, small size passenger vehicles were weakness in aspect of damageability and repairability. The most critical area appears to be repair cost considering that parts cost is the largest portion of total repair cost segments. Besides repair cost, attaching method of front sidemember and subframe are placed special importance for impact energy absorption and damageability and repairability. So in order to improve damageability and repairability of vehicle structure and body component of the monocoque type passenger vehicles, the end of front side member and front back beam should be designed with optimum level and to supply the end of front side member as a partial condition approx 300mm. The effectiveness of design concept on the 40% offset frontal impact characteristics of the passenger vehicle structure is investigated and summarized.

• 제어로봇시스템학회논문지
• /
• 제16권7호
• /
• pp.711-719
• /
• 2010

Heliostat, as a concentrator reflecting the incident solar energy to the receiver located at the tower, is the most important system in the tower-type solar thermal power plant, since it determines the efficiency and performance of solar thermal plower plant. Thus, a good sun tracking ability as well as its good optical property are required. In this paper, we propose a method to compensate the heliostat sun tracking error. We first model the sun tracking error, which could be measured using BCS (Beam Characterization System), by multilayered neural network. Then the extended Kalman filter was employed to train the neural network. Finally the model is used to compensate the sun tracking errors. Simulated result shows that the method proposed in this paper improve the heliostat sun tracking performance dramatically. It also shows that the training of neural network by the extended Kalman filter provides faster convergence property, more accurate estimation and higher measurement noise rejection ability compared with the other training methods like gradient descent method.