• Proceedings of the Korea Water Resources Association Conference
• /
• 2007.05a
• /
• pp.58-66
• /
• 2007

This paper introduces the new generic dynamic neuro-fuzzy local modeling system (DNFLMS) that is based on a dynamic Takagi-Sugeno (TS) type fuzzy inference system for complex dynamic hydrological modeling tasks. The proposed DNFLMS applies a local generalization principle and an one-pass training procedure by using the evolving clustering method to create and update fuzzy local models dynamically and the extended Kalman filtering learning algorithm to optimize the parameters of the consequence part of fuzzy local models. The proposed DNFLMS is applied to develop the inference model to forecast the flow of Waikoropupu Springs, located in the Takaka Valley, South Island, New Zealand, and the influence of the operation of the 32 Megawatts Cobb hydropower station on springs flow. It is demonstrated that the proposed DNFLMS is superior in terms of model accuracy, model complexity, and computational efficiency when compared with a multi-layer perceptron trained with the back propagation learning algorithm and well-known adaptive neural-fuzzy inference system, both of which adopt global generalization.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1999.03b
• /
• pp.62-65
• /
• 1999

To reduce the cost of finite element analyses for sheet forming a 3D hybrid membrance/sheel method has been developed to study the springback of anisotropic sheet metals. in the hybrid method the bending strains and stresses were analytically calculated as post-processing using incremental shapes of the sheet obtained previously from the membrane finite element analysis. To calculate springback a shell finite element model was used to unload the final shape of the sheet obtained from the membran code and the stresses and strains that were calculated analytically. For verification the hybrid method was applied to predict the springback of a 2036-T4 aluminum square blank formed into a cylindrical cup. the springback predictions obtained with the hybrid method was in good agreement with results obtained using a full shell model to simulateboth loading an unloading and the experimentally measured data. The CPU time saving with the hybrid method over the full shell model was 75% for the punch stretching problem.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.2
• /
• pp.179-186
• /
• 2012

In the automobile industry, reducing the weight is the most important objective for reducing air pollution and improving the fuel efficiency. For this reason, the application of aluminum sheets is increasing. When the sheets are applied to the automobile, using inappropriate variables for the material, product design, and press processing can generate tearing, wrinkling, and spring-back problems, which are the main types of failure in the manufacturing process. Therefore, it is necessary to reduce these failures by harmonizing the many variables and strictly managing the processes. In this research, we study the theoretical plasticity instability of Al5454 and obtain the forming limit diagram (FLD) using MATLAB. Moreover, we compare the theoretical FLD with an experimental FLD obtained from a stretching test.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.10
• /
• pp.1239-1249
• /
• 2013

In this study we establish a process to predict hardening behavior considering the Bauschinger effect for zircaloy-4 sheets. When a metal is compressed after tension in forming, the yield strength decreases. For this reason, the Bauschinger effect should be considered in FE simulations of spring-back. We suggested a suitable specimen size and a method for determining the optimum tightening torque for simple shear tests. Shear stress-strain curves are obtained for five materials. We developed a method to convert the shear load-displacement curve to the effective stress-strain curve with FEA. We simulated the simple shear forward/reverse test using the combined isotropic/kinematic hardening model. We also investigated the change of the load-displacement curve by varying the hardening coefficients. We determined the hardening coefficients so that they follow the hardening behavior of zircaloy-4 in experiments.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2010.09b
• /
• pp.21-31
• /
• 2010

Although it is important to reflect the accurate information of the ground condition in the tunnel design, the analysis and design are conducted by limited information because it is very difficult to get it practically on considering various geography and geotechnical condition. So construction management of information concept is required to manage immediately on the field condition because it is very time-consuming to establish the countermeasure of underground reinforcement and the pattern change of Bo. Therefore, when construction is on tunnel area, examination of accurate safety and prediction of behavior is performed to overcomes the limit of predicting behavior by using Artificial Neural Network(ANN) in this study. Firstly, the field data was secured. Secondly, suitable structure was made on multi-layer perceptrons among the ANN. Thirdly, learning algorithm-propagated applies to ANN. The data for the learn of field application using ANN was used by considering impact factors, which influenced the behavior of tunnel, and performing credibility analysis. crown displacement, spring displacement, subsurfacement, and rock bolt axial force are predicted at the tunnel construction and on-site application was confirmed by using ANN from analyzing and comparing with measurement value of on-site. In this study, the data from Seoul Highway $\bigcirc\bigcirc$ tunnel section was applied to the ANN Theory, and the analysis on the investigate value and the reasoning for the value associated with field application was performed.