• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.119-122
• /
• 2001

This paper discusses the peg-in-hole task of chamferless parts using force/moment/vision sensors. The directional error occurring during the task are categorized into two cases according to the degree of initial errors, And different Mechanical analysis has been accomplished for each cases. This paper proposes an algorithm which enables to reduce intial directional error using digital Images acquired from hand-eyed vision sensor, And to continue the task even with the large directional error by adjusting the error using digital image processing. The effectiveness of the algorithm has been demonstrated through experimentation using 5-axis robot equipped with a developed controller force/moment sensor and color digital camera on its hand.

• 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.

• Journal of Mechanical Science and Technology
• /
• v.19 no.spc1
• /
• pp.255-264
• /
• 2005

In this paper, a practical bushing model is proposed to improve the accuracy of the vehicle dynamic analysis. The results of the rubber bushing are used to develop an empirical bushing model with an artificial neural network. A back propagation algorithm is used to obtain the weighting factor of the neural network. Since the output for a dynamic system depends on the histories of inputs and outputs, Narendra algorithm of 'NARMAX' form is employed to consider these effects. A numerical example is carried out to verify the developed bushing model. Then, a full car dynamic model with artificial neural network bushings is simulated to show the feasibility of the proposed bushing model.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.3 no.6
• /
• pp.145-153
• /
• 1995

An algorithm for the automatic generation of quadrilateral shell elements on three-dimensional sculptured surfaces has been developed, which is one of the key issues in the finite element analysis of structures with complex shapes such as automobile structures. Mesh generation on sculptured surfaces is performed in three steps. First a sculptured surface is transformed to a projection plane, on which the loops are subdivided into subloops by using the best split lines, and with the use of 6-node/8-node loop operators and a layer operator, quadrilateral finite elements are constructed on this plane. Finally, the constructed mesh is transformed back to the original sculptured surfaces. The proposed mesh generation scheme is suited for the generation of non-uniform meshes so that it can be effectively used when the desired mesh density is available. Sample meshes are presented to demonstrate the versatility of the algorithm.

• Proceedings of the KSME Conference
• /
• 2004.04a
• /
• pp.864-869
• /
• 2004

In this paper, a blackbox approach is carried out to model the nonlinear dynamic bushing model. One-axis durability test is performed to describe the mechanical behavior of typical vehicle elastomeric components. The results of the tests are used to develop an empirical bushing model with an artificial neural network. The back propagation algorithm is used to obtain the weighting factor of the neural network. Since the output for a dynamic system depends on the histories of inputs and outputs, Narendra's algorithm of 'NARMAX' form is employed in the neural network bushing module. A numerical example is carried out to verify the developed bushing model.

• Proceedings of the KIEE Conference
• /
• 2009.04b
• /
• pp.222-224
• /
• 2009

This paper proposes analysis data of generation efficiency with tracking method for solar tracking. Tracking algorithm of PV generation is divided the sensor method and program method. Generation efficiency is analyzed the three cases 1-high insolation, 2-low insolation, 3-rapidly changing insolation. Proposed data is possible to apply for development of novel algorithm with hybrid tracking method in this paper. Hereby, This paper is proved the benefit of analyzed data.

• Journal of Power Electronics
• /
• v.10 no.6
• /
• pp.717-723
• /
• 2010

This paper proposes a new torque control algorithm for BLDC motors to get the maximum torque in the high speed region. The delay of the phase currents is severe due to the stator reactance. The torque fluctuations of BLDC motors increase and the average torque is decreases due to a slow rise in the phase current when compared to the back EMF. In this paper, the phase current of BLDC motors under the high speed condition is analyzed and a torque maximization control is developed on the basis of using numerical analysis. Computer simulations and experimental results show the usefulness of the proposed control algorithm.

• Structural Engineering and Mechanics
• /
• v.8 no.1
• /
• pp.1-18
• /
• 1999

Procedures are investigated by which nonlinear finite element shell analysis algorithms can be simplified to provide more cost effective approximate analyses of orthogonally-reinforced concrete flat plate structures. Two alternative effective stiffness formulations, and an unbalanced force formulation, are described. These are then implemented into a nonlinear shell analysis algorithm. Nonlinear geometry, three-dimensional layered stress analyses, and other general formulations are bypassed to reduce the computational burden. In application to standard patch test problems, these simplified approximate analysis procedures are shown to provide reasonable accuracy while significantly reducing the computational effort. Corroboration studies using various simple and complex test specimens provide an indication of the relative accuracy of the constitutive models utilized. The studies also point to the limitations of the approximate formulations, and identify situations where one should revert back to full nonlinear shell analyses.

• Structural Engineering and Mechanics
• /
• v.26 no.3
• /
• pp.251-262
• /
• 2007

This paper examines the application of artificial neural networks (ANN) to the response prediction of geometrically nonlinear truss structures. Two types of analysis (deterministic and probabilistic analyses) are considered. A three-layer feed-forward backpropagation network with three input nodes, five hidden layer nodes and two output nodes is firstly developed for the deterministic response analysis. Then a back propagation training algorithm with Bayesian regularization is used to train the network. The trained network is then successfully combined with a direct Monte Carlo Simulation (MCS) to perform a probabilistic response analysis of geometrically nonlinear truss structures. Finally, the proposed ANN is applied to predict the response of a geometrically nonlinear truss structure. It is found that the proposed ANN is very efficient and reasonable in predicting the response of geometrically nonlinear truss structures.

• Structural Engineering and Mechanics
• /
• v.18 no.3
• /
• pp.303-314
• /
• 2004

An artificial neural network (ANN) application is presented for flexural and axial vibration analysis of elastic beams with various support conditions. The first three natural frequencies of beams are obtained using multi layer neural network based back-propagation error learning algorithm. The natural frequencies of beams are calculated for six different boundary conditions via direct solution of governing differential equations of beams and Rayleigh's approximate method. The training of the network has been made using these data only flexural vibration case. The trained neural network, however, had been tested for cantilever beam (C-F), and both end free (F-F) in case the axial vibration, and clamped-clamped (C-C), and Guided-Pinned (G-P) support condition in case the flexural vibrations which were not included in the training set. The results found by using artificial neural network are sufficiently close to the theoretical results. It has been demonstrated that the artificial neural network approach applied in this study is highly successful for the purposes of free vibration analysis of elastic beams.