• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.91.5-91
• /
• 2001

This paper suggests that the immune algorithm can effectively be used in tuning of a PID controller. The artificial immune network always has a new parallel decentralized processing mechanism for various situations, since antibodies communicate to each other among different species of antibodies/B-cells through the stimulation and suppression chains among antibodies that form a large-scaled network. In addition to that, the structure of the network is not fixed, but varies continuously. That is, the artificial immune network flexibly self-organizes accord Eng to dynamic changes of external environment (meta-dynamics function). However, up to the present time, models based on the conventional crisp approach have been used to describe dynamic model relationship between antibody and antigen. Therefore, there are some problems ...

• 한국정밀공학회지
• /
• 제34권1호
• /
• pp.23-27
• /
• 2017

This paper aims to develop a prediction model for the product quality of a casting process. Prediction of the product quality utilizes an artificial neural network (ANN) in order to renovate the manufacturing technology of the root industry. Various aspects of the research on the prediction algorithm for the casting process using an ANN have been investigated. First, the key process parameters have been selected by means of a statistics analysis of the process data. Then, the optimal number of the layers and neurons in the ANN structure is established. Next, feed-forward back propagation and the Levenberg-Marquardt algorithm are selected to be used for training. Simulation of the predicted product quality shows that the prediction is accurate. Finally, the proposed method shows that use of the ANN can be an effective tool for predicting the results of the casting process.

• 한국안전학회지
• /
• 제15권2호
• /
• pp.36-45
• /
• 2000

Automated production system is composed of many complicated techniques and it become a very difficult task to control, monitor and diagnose this compound system. Moreover, it is required to develop an effective diagnosing technique and reduce the diagnosing time while operating the system in parallel under many faults occurring concurrently. This study develops a Modular Artificial Neural Network(MANN) which can perform a diagnosing function of multiple faults with the following steps: 1) Modularizing a complicated system into subsystems. 2) Formulating a hierarchical structure by dividing the subsystem into many detailed elements. 3) Planting an artificial neural network into hierarchical module. The system developed is implemented on workstation platform with $X-Windows^{(r)}$ which provides multi-process, multi-tasking and IPC facilities for visualization of transaction, by applying the software written in $ANSI-C^{(r)}$ together with $MOTIF^{(r)}$ on the fault diagnosis of PI feedback controller reactor. It can be used as a simple stepping stone towards a perfect multiple diagnosing system covering with various industrial applications, and further provides an economical approach to prevent a disastrous failure of huge complicated systems.

• 환경위생공학
• /
• 제16권1호
• /
• pp.102-107
• /
• 2001

This research was carried out investigate the removed T-P, T-N and anion surfactants using Autoclaved Lightweight Concrete(ALC) in wastewater treatment system. Effects of pH, TDS on aqueous solution was measured. Specific area which measured by BET was $27.66m^2/g$. The phosphorous, nitrogen and anion surfactants removal efficiencies were examined by using artificial waste water(T-P : 66~73mg/L, T-N : 56~136mg/L and anion surfactants : 10~31mg/L). The results showed that the ALC was effective material as a adsorbent due to the structure and porosity. It was found that anion surfactants removed was 85~95%, phosphate removed was 92% and nitrogen removed was 90% in artificial wastewater. Agitation process was more effective than aeration process in that case of nitrogen removal system using ALC.

• 한국지하수토양환경학회:학술대회논문집
• /
• 한국지하수토양환경학회 2003년도 총회 및 춘계학술발표회
• /
• pp.287-291
• /
• 2003

To delineate the internal structures of alluvial aquifer, high resolution seismic and GPR methods were adopted in Buyeo Gunsu-Ri area. The result of seismic refraction survey shows the water table of the aquifer and the result of seismic reflection reveals the basement and somewhat dominant internal structures of alluvial aquifer. The internal heterogeneity due to variations in channel behavior can be delineated using GPR survey. GPR profiles for the point bar deposits near Buyeo county reveals two different stratigraphic units the lower inclined heterogeneous strata and the upper horizontally stratified strata. According to the increase of demand for water resource using artificial recharge in alluvium, it is believed that the information acquired by high resolution geophysical methods will have an important roles for the effective and sustainable development and usage of groundwater in alluvial aquifer.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2011년도 정기 학술대회
• /
• pp.676-679
• /
• 2011

인공신경망(Artificial Neural Network)을 이용하여 RC Mock-up 구조물의 손상위치 및 손상정도를 단계적으로 추정하였다. 대상 구조물은 가진실험을 통하여 구조물의 응답을 취득하고 구조물식별기법(Structural System Identification)을 통하여 구조물의 동특성을 찾았다. 유한요소해석프로그램을 사용하여 동특성이 계측치와 가장 유사한 기본해석모델을 만든 후 이 기본해석모델을 이용하여 학습데이터를 생성하였다. 기존 인공신경망을 이용한 손상탐지를 개선하고자 본 연구에서는 인공신경망 학습데이터를 분석하였고 효과적인 손상탐지를 위하여 학습데이터를 가공하였다. 가공된 학습데이터를 사용하여 단계별 손상탐지를 실시하였고 기존 손상탐지 방법보다 좋은 결과를 유도하였다.

• The Journal of the Acoustical Society of Korea
• /
• 제18권4E호
• /
• pp.31-36
• /
• 1999

Circulant Feedback Delay Networks (CFDN's), whose feedback matrix is circulant to control the stability of system and time-frequency response easier than unitary one, were recently proposed. However, the drawback of this structure is that the flatness of the frequency response of CFDN's is not enough and it is difficult to adjust the placement of zeros to decrease this problem. Therefore, we propose Modified CFDN's (MCFDN's) consisted of a general recursive filter and CFDN's to maintain maximally the impulse response of CFDN's and improve the flatness of frequency response without adjusting the placement of zeros. The delay unit of a general recursive filter's feedback loop is replaced by CFDN's, are omitted the direct path. We represent the usefulness of MCFDN's to build artificial reverberators and the main parameter to determine characteristics of MCFDN's in this paper.

• Macromolecular Research
• /
• 제10권1호
• /
• pp.13-17
• /
• 2002

An artificial neural network (ANN) was used to study the relationship between the glass transition temperature (T$_{g}$) and the structure of homopolymers. The input is very important for the ANN. In this paper, six kinds of input vectors were designed for the ANN. Of the six approaches, the best one gave the is T$_{g}$ of 251 polymers with a standard deviation of 8 K and a maximum error of 29 K. The trained ANN also predicted the T$_{g}$ of 20 polymers which are not included in the 251 polymers with a standard deviation of 7 K and a maximum error of 21 K. 21 K.

• 한국농공학회:학술대회논문집
• /
• 한국농공학회 2000년도 학술발표회 발표논문집
• /
• pp.384-389
• /
• 2000

A artificial neural network model was developed to analyze and forecast the flow fluctuation at small streams in the Balan watershed. Backpropagation neural networks were found to perform very well in forecasting daily streamflows. In order to deal with slow convergence and an appropriate structure, two algorithms were proposed for speeding up the convergence of the backpropagation method, and the Bayesian Information Criterion(BIC) was proposed for obtaining the optimal number of hidden nodes. From simulations using daily flows at the HS#3 watershed of the Balan Watershed Project, which is 412,5 ㏊ in size and relatively steep in landscape, it was found that those algorithms perform satisfactorily.

• 한국전산유체공학회:학술대회논문집
• /
• 한국전산유체공학회 2002년도 춘계 학술대회논문집
• /
• pp.2-7
• /
• 2002

Flow in the blood sac of the Korean artificial heart is numerically simulated by finite element method. Fluid-structure interaction algorithm is employed to compute the 3D blood flow interacting with the sac material. The motion of the actuator is simplified by a time-varying pressure boundary condition imposed on the outer surface of the sac. Numerical solutions show that there are a strong flow into the outlet and a stagnation flow near the inlet during systole. Shear stress distribution is also delineated to assess the possibility of thrombus formation.