• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.25 no.4
• /
• pp.485-495
• /
• 2001

This paper presents a similarity solution for the directional casting of binary peritectic alloys in the presence of shrinkage-induced flow. The present model retains essential ingredients of alloy solidification, such as temperature-solute coupling, macrosegregation, solid-liquid property differences, and finite back diffusion in the primary phase. An algorithm for simultaneously determining the peritectic and liquidus positions is newly developed, which proves to be more efficient and stable than the existing scheme. Sample calculations are performed for both hypo- and hyper-peritectic compositions. The results show that the present analysis is capable of properly resolving the solidification characteristics of peritectic alloys so that it can be used for validating numerical models as a test solution.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.11
• /
• pp.113-117
• /
• 1997

In this paper we detected the thrombosis formation by spectral analysis and neural network. Using microphone and amplifier, we measured the sound from the mechanical valve which is attached to the pneumatic ventricular assist device. The sound was sampled by A/D converter and the periodogram is the main algorithm or obtaining spectrum. We made the valvular thrombosis models using pellethane and silicon and they are thrombosis model on the disk, around the sewing ring and fibrous tissue growth across the orifice of valve. The spectrum of normal and 5 kinds of thrombotic valve were obtained and primary and secondary peak appeared in each spectrum waveform. So to distinguish the secondary peak of normal and thrombotic valve quantatively, 3 layer back propagation neural network.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.17 no.3
• /
• pp.1-7
• /
• 2008

This paper describes the kinematics which is a new type of parallel manipulator, and the neural network is applied to solving the forward kinematics problem. The parallel manipulator called it as a Stewart platform has an easy and unique solution about the inverse kinematics. However, the forward kinematics is difficult to get a solution because of the lack of an efficient algorithm caused by its highly nonlinearity. This paper proposes the neural network scheme of an Newton-Raphson method alternatively. It is found that the neural network can be improved its accuracy by adjusting the offset of the obtained result.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.10
• /
• pp.141-150
• /
• 1997

분산은 확률모델을 표현하는 유용한 변수중 하나이다. 입력변수에 대한 함수로 표현되는 조건부 분산을 학습하는 신경회로망에 대한 많은 연구가 있어왔다. VALEAN이라는 신경회로망 역시 이러한 많은 연구중 하나인데 이것은 기본적으로 feedforward 다층 퍼셉트론 구조를 가지며 새롭게 제시된 에너지 함수를 사용하고 있다. 이 논문에서는 이 에너지 모델에 의해 결정되는 피드백에러(델타)가 신경망의 transient, steady state에서 미치는 영향을 다루었다. 과도 상태 분석에서는 델타와 수렴성, 안정성에 관한 내용을 다루고 모의 실험을 하였으며 정상 상태 분석에서는 신경회로망의 정상상태 에러의 크기와 델타의 크기사이의 상관관계에 대하여 다루었다. 학습 알고 리듬이 확률적이므로 정상상태 역시 확률적인 상태를 나타낸다. 따라서 델타의 크기에 따른 정상 상태 에러의 최대치는 확률적인 모델을 가지게 된다. 여기서는 이 확률 관계를 분석적으로 규명하고 이에 따라 원하는 신뢰도로 정상 상태 에러를 제어하기 위해 필요한 델타의 크기를 예측할 수 있는 이론적 배경을 마련하게 된다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.780-783
• /
• 2002

This paper proposes an approximate LCA methodology fur the conceptual design stage by grouping products according to their environmental characteristics and by mapping product attributes Into impact driver (ID) index. The relationship Is statistically verified by exploring the correlation between total impact indicator and energy impact category. Then an artificial neural network model is developed to predict an approximate LCA of grouping products in conceptual design stage. The training is generalized by using identified product attributes for an ID In a group as well as another product attributes for another IDs in other groups. The neural network model with back propagation algorithm is used and the results are compared with those of multiple regression analysis. The proposed approach does not replace the full LCA but it would give an approximate LCA results for design concepts.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.4
• /
• pp.220-227
• /
• 2005

This paper presents hybrid artificial intelligent(HAI) controller based on the vector controlled IPMSM drive system. And it is based on artificial technologies that adaptive neural network fuzzy(A-NNF) is to speed control and artificial neural network(ANN) is to speed estimation. The salient feature of this technique is the HAI controller The hybrid action tolerates any inaccuracies in the fuzzy logic assignment rules or in the neural network stationary weights. Speed estimators using feedforward multilayer and artificial neural network(ANN) are compared. The back-propagation algorithm is easy to derived the estimated speed tracks precisely the actual motor speed. This paper presents the theoretical analysis as well as the simulation results to verify the effectiveness of the new hybrid intelligent control.

• Proceedings of the KIEE Conference
• /
• 2001.04a
• /
• pp.156-159
• /
• 2001

This Paper analysis variable characteristics of inductance profiles and basic magnetic fields for Switched Reluctance Motors(SRM). The varying Inductance and flux linkage on operating control condition are very important for developing control algorithm and SRM accurate drive system. Therefore, we have analytical model for varying inductance and flux linkage with simulation and experimental mothed, and to find an analytical expression for the SRM coenergy. There are shown some good results that comparison of simulated and analytical inductance, flux linkage and current waves.

• Proceedings of the KIEE Conference
• /
• 1997.07c
• /
• pp.897-899
• /
• 1997

The analysis of distribution line faults is essential to the proper protections of the power system. A high impedance fault does not make enough current to cause conventional protective devices. It is well known that undesirable operating conditions and certain types of faults on electric distribution feeders cannot be detected by using conventional protection system. This paper describes an algorithm using back-propagation neural network for pattern recognition and detection of high impedance faults. Fractal dimensions are estimated for distinction between random noise and chaotic behavior in the power system. The fractal dimension of the line current is also used as a indication of the high impedance fault.

• Journal of Sensor Science and Technology
• /
• v.13 no.6
• /
• pp.454-461
• /
• 2004

We have designed a portable electronic nose (e-nose) system using an array of commercial gas sensors and personal digital assistants (PDA) for the recognition and analysis of volatile organic compounds (VOC) in the field. Field screening of pollutants has been a target of instrumental development during the past years. A portable e-nose system was advantageous to localize the special extent of a pollution or to find pollutants source. The employment of PDA improved the user-interface and data transfer by Internet from on-site to remote computer. We adapted the Lavenberg-Marquardt algorithm based on the back-propagation and proposed the method that could predict the concentration levels of VOC gases after classification by separating neural network into two parts.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.176-180
• /
• 2004

In this paper we introduce a bandwidth allocation algorithm and admission control policy for IEEE 802.16 broadband wireless access standard. The proposed mechanism is practical and compatible to the IEEE 802.16. Our scheme provides QoS support to high priority traffic and high throughput in low priority traffic. The simulation show that the proposed scheme includes QoS support for real-time traffic and we presented that BS determine a efficient contention mini-slot size. We have shown the relationship between traffic size and its QoS requirements and the network performance.