• Nuclear Engineering and Technology
• /
• 제39권4호
• /
• pp.337-348
• /
• 2007

A fuzzy neural network model is presented to predict residual stress for dissimilar metal welding under various welding conditions. The fuzzy neural network model, which consists of a fuzzy inference system and a neuronal training system, is optimized by a hybrid learning method that combines a genetic algorithm to optimize the membership function parameters and a least squares method to solve the consequent parameters. The data of finite element analysis are divided into four data groups, which are split according to two end-section constraints and two prediction paths. Four fuzzy neural network models were therefore applied to the numerical data obtained from the finite element analysis for the two end-section constraints and the two prediction paths. The fuzzy neural network models were trained with the aid of a data set prepared for training (training data), optimized by means of an optimization data set and verified by means of a test data set that was different (independent) from the training data and the optimization data. The accuracy of fuzzy neural network models is known to be sufficiently accurate for use in an integrity evaluation by predicting the residual stress of dissimilar metal welding zones.

• 대한산업공학회지
• /
• 제29권2호
• /
• pp.157-164
• /
• 2003

The amount of information increases rapidly when working in a distributed environment where multiple collaborative partners work together on a complex product. Today's PDM (product data management) systems provide good capabilities regarding the management of product data within a single company. However, taking into account the variety of systems used at partner sites in an engineering environment one can easily imagine problems regarding the interoperability and the data consistency. This paper presents a concept to improve the workflow management using the parameters network. It shows a parameter driven engineering workflow that is able to manage engineering task across company boarders. We introduce a mechanism of workflow management based on the engineering parameters and an architecture of the distributed workspace to apply it within a PDM system. For a parameter mapping between CAD and PDM system we developed an XML-based CATIA data interface module using CAA.

• 대한용접접합학회:학술대회논문집
• /
• 대한용접접합학회 2002년도 Proceedings of the International Welding/Joining Conference-Korea
• /
• pp.295-300
• /
• 2002

In this paper, an intelligent system to determine welding parameters for each pass and welding position in pipeline welding based on one database and FEM model, two BP neural network models and a C-NN model was developed and validated. The preliminary test of the system has indicated that the developed system could determine welding parameters for pipeline welding quickly, from which good weldments can be produced without experienced welding personnel. Experiments using the predicted welding parameters from the developed system proved the feasibility of interface standards and intelligent control technology to increase productivity, improve quality, and reduce the cost of system integration.

• 한국통신학회논문지
• /
• 제11권6호
• /
• pp.402-410
• /
• 1986

IEEE 802 Local Area Network(LAN) 기준 모델의 Media Access Control(MAC)방식에서 CSMA/CD, 토큰링, 토큰 버스방식을 포함하며, LAN성능의 척도인 Throughput에 영향을 주는 파라미터는 채널의 길이, 전송 속도, 패킷의 크기 및 스테이션 수이다. 본 논문에서는 이러한 파라미터를 정규화시켜 해석하므로 각 파라미터가 채널 Through-put에 미치는 영향을 검토하였으며 특히, 토큰 링방식과 토큰 버스방식에 대한 해석으로 각 파라미터와의 관계를 고찰하여 CSMA/CD방식과의 비교 검토를 하였다.

• 제어로봇시스템학회논문지
• /
• 제9권12호
• /
• pp.1048-1054
• /
• 2003

In laser surface hardening processes, the geometrical parameters such as the depth and the width of a hardened layer can be utilized to assess the hardened layer quality. However, accurate monitoring of the geometrical parameters for on-line process control as well as for on-line quality evaluation is very difficult because the hardened layer is formed beneath a material surface and is not visible. Therefore, temperature monitoring of a point of specimen surface has most frequently been used as a process monitoring method. But, a hardened layer depends on the temperature distribution and the thermal history of a specimen during laser surface hardening processing. So, this paper describes the estimation results of the geometric parameters using multi-point surface temperature monitoring. A series of hardening experiments were performed to find the relationships between the geometric parameters and the measured temperature. Estimation results using a neural network show the enhanced effectiveness of multi-point surface temperature monitoring compared to one-point monitoring.

• 한국정밀공학회지
• /
• 제19권10호
• /
• pp.147-155
• /
• 2002

In the stereolithography process, the accuracy of product depends on laser power, scan speed, scan width, scan pattern, layer thickness, resin characteristics and so on. Therefore, appropriate process parameters are required for an accurate prototype. This paper presents a method to determine the key process parameters, i.e., laser scan speed, hatching space, and layer thickness based on scan length, scan area, and layer slope. In order to determine these parameters, three neural networks are employed to represent operator’s experience and knowledge. Optimum values on scan speed, hatching space and layer thickness are recommended to improve the surface roughness and build time on the developed SLA machine.

• International Journal of Concrete Structures and Materials
• /
• 제5권1호
• /
• pp.29-33
• /
• 2011

This article employs Least Square Support Vector Machine (LSSVM) for determination of fracture parameters of concrete: critical stress intensity factor ($K_{Ic}^s$) and the critical crack tip opening displacement ($CTOD_c$). LSSVM that is firmly based on the theory of statistical learning theory uses regression technique. The results are compared with a widely used Artificial Neural Network (ANN) Models of LSSVM have been developed for prediction of $K_{Ic}^s$ and $CTOD_c$, and then a sensitivity analysis has been performed to investigate the importance of the input parameters. Equations have been also developed for determination of $K_{Ic}^s$ and $CTOD_c$. The developed LSSVM also gives error bar. The results show that the developed model of LSSVM is very predictable in order to determine fracture parameters of concrete.

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2005년도 동계학술발표대회 논문집
• /
• pp.45-50
• /
• 2005

The supply outdoor airflow rates are calculated and analyzed using a multizone network model in a high-rise residential apartment. The system parameters include parameters related to weather conditions, building conditions, operation conditions, and facility conditions. Simulations are conducted according to the method of design of experiments and analysis of variance is conducted to investigate the effects of parameters on ventilation rate. A correlation equation is derived to predict ventilation rates of the building depending on the various parameters.

• International Journal of Korean Welding Society
• /
• 제2권2호
• /
• pp.32-35
• /
• 2002

In this paper, an intelligent system to determine welding parameters for each pass and welding position in pipeline welding based on one database and FEM model, two BP neural network models and a C-NN model was developed and validated. The preliminary test of the system has indicated that the developed system could determine welding parameters fur pipeline welding quickly, from which good weldments can be produced without experienced welding personnel. Experiments using the predicted welding parameters from the developed system proved the feasibility of interface standards and intelligent control technology to increase productivity, improve quality, and reduce the cost of system integration.

• Earthquakes and Structures
• /
• 제25권1호
• /
• pp.15-26
• /
• 2023

It is of great importance to assess the residual displacement demand in the performance-based seismic design. In this paper, a hybrid deep learning model for predicting the residual displacement spectra under near-fault (NF) ground motions is proposed by combining the long short-term memory network (LSTM) and back-propagation (BP) network. The model is featured by its capacity of predicting the residual displacement spectrum under a given NF ground motion while considering the effects of structural parameters. To construct this model, 315 natural and artificial NF ground motions were employed to compute the residual displacement spectra through elastoplastic time history analysis considering different structural parameters. Based on the resulted dataset with a total of 9,450 samples, the proposed model was finally trained and tested. The results show that the proposed model has a satisfactory accuracy as well as a high efficiency in predicting residual displacement spectra under given NF ground motions while considering the impacts of structural parameters.