• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.15 no.4
• /
• pp.22-28
• /
• 2006

Detection of exit burr is very important in manufacturing automation. In this paper, acoustic emission(AE) was used to detect the burr formation during milling. By using wavelet transformation, AE data was compressed without unnecessary details. Then the transformed data were used as selected features (inputs) of a back-propagation artificial neural net. In order to validate the proposed scheme, the wavelet based ANN results were compared with cutting condition(cutting speed, feed, depth of cut, etc.) based ANN results.

• Structural Engineering and Mechanics
• /
• v.51 no.2
• /
• pp.299-313
• /
• 2014

In the first part of this paper, the influences of some of crack parameters on natural frequencies of a cracked cantilever Functionally Graded Beam (FGB) are studied. A cantilever beam is modeled using Finite Element Method (FEM) and its natural frequencies are obtained for different conditions of cracks. Then effect of variation of depth and location of cracks on natural frequencies of FGB with single and multiple cracks are investigated. In the second part, two Multi-Layer Feed Forward (MLFF) Artificial Neural Networks (ANNs) are designed for prediction of FGB's Cracks' location and depth. Particle Swarm Optimization (PSO) and Back-Error Propagation (BEP) algorithms are applied for training ANNs. The accuracy of two training methods' results are investigated.

• Structural Engineering and Mechanics
• /
• v.46 no.6
• /
• pp.853-868
• /
• 2013

The comparison of the effectiveness of artificial neural network (ANN) and linear regression (LR) in the prediction of strain in tie section using experimental data from eight high-strength-self-compact-concrete (HSSCC) deep beams are presented here. Prior to the aforementioned, a suitable ANN architecture was identified. The format of the network architecture was ten input parameters, two hidden layers, and one output. The feed forward back propagation neural network of eleven and ten neurons in first and second TRAINLM training function was highly accurate and generated more precise tie strain diagrams compared to classical LR. The ANN's MSE values are 90 times smaller than the LR's. The correlation coefficient value from ANN is 0.9995 which is indicative of a high level of confidence.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2003.04a
• /
• pp.269-278
• /
• 2003

In this study, the method of the finite element modeling for free vibration control of beam-type smart structures with bonded plate-type piezoelectric sensors and actuators is proposed. Constitutive equations for the direct piezoelectric effect and converse piezoelectric effect of piezoelectric materials are considered. By using the variational principle, the equations of motion for the smart beam finite element are derived, The proposed 2-node beam finite element is an isoparametric element based on Timoshenko beam theory. Therefore, by analyzing beam-type smart structures with smart beam finite elements, it is possible to simulate the control of the structural behavior by applying voltages to piezoelectric actuators and monitoring of the structural behavior by sensing voltages of piezoelectric sensors. By using the smart beam finite element and constant-gain feed back control scheme, the formulation of the free vibration control for the beam structures with bonded plate-type piezoelectric sensors and actuators is proposed.

• Journal of Educational Research in Mathematics
• /
• v.12 no.1
• /
• pp.109-124
• /
• 2002

This study investigated various effects of WBD(web-based discussion) on mathematical communication, interaction and problem solving in the classroom. We developed a web site including BBS and chat room in order to encourage students' mathematical curiosities and self-studies. The web site had been operated for 6 months. Five classes of 1st grade students were selected from an middle school in Daejon. Moreover, we analyzed several cases for interactional behavior and effect. WBD promote dialogue between a teacher and students. Analysis of feed-back from BBS revealed that student's negative attitudes could be changed to positive ones by step-by-step discussions. Moreover, collaborative learning is enhanced by on-line discussion. But the effects of WBD are affected by the character and ability of a student.

• Journal of the Korean Society for Precision Engineering
• /
• v.34 no.1
• /
• 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.

• Proceedings of the KIEE Conference
• /
• 1995.11a
• /
• pp.527-530
• /
• 1995

In this paper, traffic modeling and control design was considered to analyze and improve the stability of train diagram in the open-loop Metro line. A complete discrete-event traffic model describing the natural instability of open-loop metro line is analyzed. The traffic stability properties are introduced and easy-to-implement state feed back traffic control algorithms are designed, which satisfied with system stability.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.60 no.1
• /
• pp.19-26
• /
• 2011

In this paper, we designed Interpolation FIR(Finite Impulse Response) filter and 1-bit SDM(Sigma- Delta Modulator) for small digital audio speaker, which has low power consumption and high output characteristics. In order to achieve high linearity and low distortion performance of the systems, we adopt Type I Chevychev FIR filter which has equiripple characteristics in the pass band and proposed high efficient FIR filter structure. SDM is the most efficient modulation technique among the noise shaping techniques. In this paper, we implemented SDM using CIFB(Cascade of Intergrators, Feed-Back) which is generally used in DAC of small digital audio speakers. The proposed SDM structure can achieve high SNR, high-efficiency characteristics and low power consumption in mobile devices. Also considering manufacture of SoC(System on Chip), we performed simulation with Matlab and Verilog HDL to obtain optimal number of operational bits and verified a good experimental results.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.1142-1143
• /
• 2008

As well known, the maximum power point tracking (MPPT) is an important role in photovoltaic (PV) power systems. MPPT finds and maintains the operation of PV at the maximum power point when the irradiation and cell-temperature change. In this paper, the studied system includes a PV array, a Buck-Boost DC/DC converter, a DC/AC inverter and it is connected to the three phase power system. The solar array operates as a non-linear voltage source. The P&O algorithm with power feed-back is used to control the operating point of PV array at the maximum power point. The effects of irradiation and cell-temperature on the dynamic responses are also considered.

• Asian-Australasian Journal of Animal Sciences
• /
• v.11 no.6
• /
• pp.774-780
• /
• 1998

This report includes an extensive bibliography of research articles investigating various facets of rearing neonatal piglets using liquid diets, and includes historical publications dating back to the 1940's. However, in order to provide concise and timely focus for application in modem swine production, only a selected number of recent findings are reviewed in detail. Collectively, the data presented illustrate that growth of piglets fed liquid diets can greatly exceed that of littermates fed dry diets and can even exceed growth rates of sow-reared controls (by up to 160%). The central questions that remain unanswered are: 1) Can this improved performance be obtained routinely and economically under applied farm conditions? and if so, 2) Does improved growth during the early-weaning period translate into improved net economic returns overall? Unfortunately, due to the current practical management constraints related to liquid-diet feeding (i.e., lack of an easy-to-manage feed delivery system), limited data are available which examine the efficacy of liquid-diet feeding under practical, commercial farm conditions.