• 한국정보처리학회논문지
• /
• 제6권3호
• /
• pp.710-721
• /
• 1999

In this paper, we have designed and implemented a parameter extraction system for analyzing Internet using SNMP. The extraction system has two modules; one is collection request module, and the other is analysis request module. The collection request module generates a polling script, which is used to collect management information from the managed system periodically. With this collected data, analysis request module extracts analysis parameters. These parameters are traffic flow analysis, interface traffic analysis, packet traffic analysis, and management traffic analysis parameter. For management activity, we have introduced two-step-analysis-view. One is Summary-View, which is used find out malfunction of a system among the entire managed systems. The Other is Specific-View. With this view we can analyze the specific system with all our analysis parameters. To show available data as indicators for line capacity planning, network redesigning decision making of performance upgrade for a network device and things like that.

• Design & Manufacturing
• /
• 제15권4호
• /
• pp.24-31
• /
• 2021

In this study, an artificial neural network model was constructed to convert CAE analysis data into similar experimental data. In the analysis and experiment, the injection molding data for 50 conditions were acquired through the design of experiment and random selection method. The injection molding conditions and the weight, height, and diameter of the product derived from CAE results were used as the input parameters for learning of the convert model. Also the product qualities of experimental results were used as the output parameters for learning of the convert model. The accuracy of the convert model showed RMSE values of 0.06g, 0.03mm, and 0.03mm in weight, height, and diameter, respectively. As the next step, additional randomly selected conditions were created and CAE analysis was performed. Then, the additional CAE analysis data were converted to similar experimental data through the conversion model. An artificial neural network model was constructed to predict the quality of injection molded product by using converted similar experimental data and injection molding experiment data. The injection molding conditions were used as input parameters for learning of the predicted model and weight, height, and diameter of the product were used as output parameters for learning. As a result of evaluating the performance of the prediction model, the predicted weight, height, and diameter showed RMSE values of 0.11g, 0.03mm, and 0.05mm and in terms of quality criteria of the target product, all of them showed accurate results satisfying the criteria range.

• 한국정밀공학회지
• /
• 제11권4호
• /
• pp.138-147
• /
• 1994

Performance management of computer networks is intended to improve a given network performance in order for more efficient information exchange between subsystems of an integrated large-scale system. Improtance of performance management is growing as many function of the large- scale system depend on the quality of communication services provided by the network. The role of performance management is to manipulate the adjustable protocol parameters on line so that the network can adapt itself to a dynamic environment. This can be divided into two subtasks : performance evaluation to find how changes in protocol parameters affect the network performance and decision making to detemine the magnitude and direction of parameter adjustment. This paper is the second part of the two papers focusing on conceptual design, development, and evaluation of performance management for token bus networks. This paper specifically deals with the task of decision making which utilizes the principles of stochastic optimization and learning automata. The developed algorithm can adjuxt four timer settings of a token bus protocol based on the result of performance evaluation. The overall performance management has been evaluated for its efficacy on a network testbed.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 추계학술대회 논문집 전기기기 및 에너지변환시스템부문
• /
• pp.125-127
• /
• 2001

Switched reluctance motor (SRM) has some advantages such as low cost, high torque density etc. However SRM has inevitably high torque ripple due to the double salient structure. To apply SRM to industrial field, we have to minimize torque ripple, which is the weak-Point of SRM. This paper presents optimal design process of SRM using numerical method such as 2D finite element method (FEM) and 3D equivalent magnetic circuit network method (EMCNM). The electrical and geometrical design parameters have been adopted as 2D design variables. The overhang structure of rotor has been also adopted as 3D design variable. From this work, we can obtain the optimal design, which minimize the torque ripple and maximize energy conversion loop.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.504-507
• /
• 1997

It is well known that Variable Structure Controller(VSC) is robust to parameters variation and disturbance but its performance depends on the design parameters such as switching gain and slope of sliding surface. This paper proposes a more robust VSC that is composed of local VSC's. Each local VSC considers the local system dynamics with narrow parameter variation and disturbance. First we optimize the local VSC's by use of Evolution Strategy, and next we use Artificial Neural Network to generalize the local VSC's and construct the overall VSC in order to cover the whole range of parameter variation and disturbance. Simulation on BLDC motor current control shows that the proposed VSC is superior to the conventional VSC.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2001년도 춘계학술대회 논문집(한국공작기계학회)
• /
• pp.208-213
• /
• 2001

Objective of this paper is to develop a new approach involving the use of an Artificial Neural Network(ANN) and multiple regression methods in the prediction of process parameters on bead height for GMA welding process. Using a series of robotic are welding, multi-pass butt welds carried out in order to verify the performance of the neural network estimator and multiple regression methods. To verify the developed system, the design parameters of the neural network estimator are selected from an estimation error analysis. The experimental results show that the proposed models can predict the bead height with reasonable accuracy and guarantee the uniform weld quality.

• 한국공작기계학회논문집
• /
• 제15권3호
• /
• pp.45-52
• /
• 2006

Burrs formed during face milling operations can be very difficult to characterize since there exist several parameters which have complex combined effects that affect the cutting process. Many researchers have attempted to predict burr characteristics including burr size and shape, using various experimental parameters such as cutting speed, feed rate, in-plane exit angle, and number of inserts. However, the results of these studies tend to be limited to a specific process parameter range and to certain materials. In this paper, the Taguchi method, a systematic optimization method for design and analysis of experiments, is introduced to acquire optimum cutting conditions for burr minimization. In addition, an in process monitoring scheme using an artificial neural network is presented for the prediction of burr types.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1997년도 추계학술대회
• /
• pp.439-442
• /
• 1997

In our research, we will extract diagnostic parameters by LPC method and wavelet transform. Then, we will design artificial neural network which is based on RBF that can express input features in terms of fuzzy. Because PVC(Premature Ventricular Contraction) has possibility to cause heart attack, the detection of PVC is a very significant problem. To deal with this problem, LPC method which gives different coefficients or different morphologies and wavelet transform which has superior localization nature of time-frequency, are used to extract effective parameters or classification of normal and PVC. Because RBF network can allocate an input feature to the membership degree of each category, total system will be more flexible.

• 동력기계공학회지
• /
• 제9권4호
• /
• pp.194-201
• /
• 2005

In this paper, we propose an adaptive mechanism based on humoral immune algorithm and neural network identifier technique. It is also applied for an autonomous guided vehicle (AGV) system. When the immune algorithm is applied to the PID controller, there exists the case that the plant is damaged due to the abrupt change of PID parameters since the parameters are almost adjusted randomly. To slove this problem, we use the neural network identifier technique for modeling the plant humoral immune algorithm (HIA) which performs the parameter tuning of the considered model, respectively. Finally, the experimental results for control of steering and speed of AGV system illustrate the validity of the proposed control scheme. Also, these results for the proposed method show that it has better performance than other conventional controller design method such as PID controller.

• 한국정보기술학회 영문논문지
• /
• 제9권1호
• /
• pp.127-134
• /
• 2019

In terms of deep Reinforcement Learning (RL), exploration can be worked stochastically in the action of a state space. On the other hands, exploitation can be done the proportion of well generalization behaviors. The balance of exploration and exploitation is extremely important for better results. The randomly selected action with ε-greedy for exploration has been regarded as a de facto method. There is an alternative method to add noise parameters into a neural network for richer exploration. However, it is not easy to predict or detect over-fitting with the stochastically exploration in the perturbed neural network. Moreover, the well-trained agents in RL do not necessarily prevent or detect over-fitting in the neural network. Therefore, we suggest a novel design of a deep RL by the balance of the exploration with drop-out to reduce over-fitting in the perturbed neural networks.