• The Journal of Korean Association of Computer Education
• /
• v.6 no.3
• /
• pp.47-56
• /
• 2003

We describe a new method for removing non-linear phased array antenna aberration called "squint" problem. To develop a compensation scheme. theoretical antenna and artificial neural networks were used. The purpose of using the artificial neural networks is to develop an antenna system model that represents the steering function of an actual array. The artificial neural networks are also used to implement an inverse model which when concatenated with the antenna or antenna model will correct the "squint" problem. Combining the actual steering function and the inverse model contained in the artificial neural network, alters the steering command to the antenna so that the antenna will point to the desired position instead of squinting. The use of an artificial neural network provides a method of producing a non-linear system that can correct antenna performance. This paper demonstrates the feasibility of generating an inverse steering algorithm with artificial neural networks.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.5 s.176
• /
• pp.1175-1182
• /
• 2000

Diffraction systematically causes error in acoustic measurements. Most probes are designed to reduce this phenomenon. On the contrary, this paper proposes a spherical probe a] lowing acoustic inten sity measurements in three dimensions to be made, which creates a diffracted field that is well-defined, thanks to analytic solution of diffraction phenomena. Six microphones are distributed on the surface of the sphere along three rectangular axes. Its measurement technique is not based on finite difference approximation, as is the case for the ID probe but on the analytic solution of diffraction phenomena. In fact, the success of sound source identification depends on the inverse models used to estimate inverse diffraction phenomena, which has nonlinear properties. In this paper, we propose the concept of nonlinear inverse diffraction modeling using a neural network and the idea of 3 dimensional sound source identification with better performances. A number of computer simulations are carried out in order to demonstrate the diffraction phenomena under various angles. Simulations for the inverse modeling of diffraction phenomena have been successfully conducted in showing the superiority of the neural network.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.124-126
• /
• 1989

Inverse kinematic problem is a crucial point for robot manipulator control. In this paper, to implement the Jacobian control technique we used the Hopfield(Tank)'s neural network. The states of neurons represent joint veocities, and the connection weights are determined from the current value of the Jacobian matrix. The network energy function is constructed so that its minimum corresponds to the minimum least square error. At each sampling time, connection weights and neuron states are updated according to current joint position. Inverse kinematic solution to the planar redundant manipulator is solved by computer simulation.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1996.11a
• /
• pp.21-26
• /
• 1996

The identification of radioactive source in a medium with a limited number of external detectors is introduced as an inverse radiation transport problem. This kind of inverse problem is usually ill-posed and severely under-determined, however, its applications are very useful in manu fields including medical diagnosis and nondestructive assay of nuclear materials. Therefore, it is desired to develop efficient and robust solution algorithms. As an approach to solving inverse problems, an artificial neural network is proposed. We develop a modified version of the conventional Hopfield neural network and demonstrate its efficiency and robustness.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.7 s.178
• /
• pp.1753-1762
• /
• 2000

An inverse method is presented to obtain material's flow properties by using small punch test. This procedure employs, as the objective function of inverse analysis, the balance of measured load-di splacement response and calculated one during deformation. In order to guarantee convergence to global minimum, simulated annealing method was adopted to optimize the current objective function. In addition, artificial neural network was used to predict the load-displacement response under given material parameters which is the most time consuming and limits applications of global optimization methods to these kinds of problems. By implementing the simulated annealing for optimization along with calculating load-displacement curve by neural network, material parameters were identified irrespective of initial values within very short time for simulated test data. We also tested the present method for error-containing experimental data and showed that the flow properties of material were well predicted.

• Structural Engineering and Mechanics
• /
• v.46 no.5
• /
• pp.673-693
• /
• 2013

This paper presents a systematic design and training procedure for the feed-forward back-propagation neural network (NN) modeling of both forward and inverse behavior of a rotary magnetorheological (MR) damper based on experimental data. For the forward damper model, with damper force as output, an optimization procedure demonstrates accurate training of the NN architecture with only current and velocity as input states. For the inverse damper model, with current as output, the absolute value of velocity and force are used as input states to avoid negative current spikes when tracking a desired damper force. The forward and inverse damper models are trained and validated experimentally, combining a limited number of harmonic displacement records, and constant and half-sinusoidal current records. In general the validation shows accurate results for both forward and inverse damper models, where the observed modeling errors for the inverse model can be related to knocking effects in the measured force due to the bearing plays between hydraulic piston and MR damper rod. Finally, the validated models are used to emulate pure viscous damping. Comparison of numerical and experimental results demonstrates good agreement in the post-yield region of the MR damper, while the main error of the inverse NN occurs in the pre-yield region where the inverse NN overestimates the current to track the desired viscous force.

• Transactions of Materials Processing
• /
• v.27 no.1
• /
• pp.28-36
• /
• 2018

Electromagnetic forming is a type of high-speed forming process to deform a workpiece through a Lorentz force. As the high strain rate in an electromagnetic-forming simulation causes infeasibility in determining constitutive parameters, we employed inverse parameter estimation in the previous study. However, the inverse parameter estimation process required us to spend considerable time, which leads to an increase in computational cost. To overcome the computational obstacle, in this research, we applied two types of surrogate modeling methods and compared them to each other to evaluate which model is best for the electromagnetic-forming simulation. We exploited an artificial neural network and we reduced-order modeling methods. During the construction of a reduced-order model, we extracted orthogonal bases with proper orthogonal decomposition and predicted basis coefficients by utilizing an artificial neural network. After the construction of the surrogate models, we verified the artificial neural network and reduced-order models through training and testing samples. As a result, we determined the artificial neural network model is slightly more accurate than the reduced-order model. However, the construction of the artificial neural network model requires a considerably larger amount of time than that of the reduced-order model. Thus, a reduced order modeling method is more efficient than an artificial neural network for estimating the electromagnetic forming and for the rapid approximation of structural simulations which needs repetitive runs.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.14-19
• /
• 1993

In this paper, we proposed an indirect learning and direct adaptive control schemes using neural networks, i.e., composite adaptive neural control, for a class of continuous nonlinear systems. With the indirect learning method, the neural network learns the nonlinear basis of the system inverse dynamics by a modified backpropagation learning rule. The basis spans the local vector space of inverse dynamics with the direct adaptation method when the indirect learning result is within a prescribed error tolerance, as such this method is closely related to the adaptive control methods. Also hash addressing technique, similar to the CMAC functional architecture, is introduced for partitioning network hidden nodes according to the system states, so global neuro control properties can be organized by the local ones. For uniform stability, the sliding mode control is introduced when the neural network has not sufficiently learned the system dynamics. With proper assumptions on the controlled system, global stability and tracking error convergence proof can be given. The performance of the proposed control scheme is demonstrated with the simulation results of a nonlinear system.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.39 no.9
• /
• pp.985-996
• /
• 1990

An inverse kinematic solution of a robot manipulator using multilayer perceptrons is proposed. Neural networks allow the solution of some complex nonlinear equations such as the inverse kinematics of a robot manipulator without the need for its model. However, the back-propagation (BP) learning rule for multilayer perceptrons has the major limitation of being too slow in learning to be practical. In this paper, a new algorithm named Dynamically Reconfiguring BP is proposed to improve its learning speed. It uses a modified version of Kohonen's Self-Organizing Feature Map (SOFM) to partition the input space and for each input point, select a subset of the hidden processing elements or neurons. A subset of the original network results from these selected neuron which learns the desired mapping for this small input region. It is this selective property that accelerates convergence as well as enhances resolution. This network was used to learn the parity function and further, to solve the inverse kinematic problem of a robot manipulator. The results demonstrate faster learning than the BP network.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2188-2190
• /
• 2004

This paper presents an implementation of power system stabilizer using inverse dynamic neuro controller. Traditionally, mutilayer neural network is used for a universal approximator and applied to a system as a neuro-controller. In this case, at least two neural networks are used and continuous tuning of neuro-controller is required. Moreover, training of neural network is required considering all possible disturbances, which is impractical in real situation. In this paper, Taylor Model Based Inverse Dynamic Neuro Model (TMBIDNM) is introduced to avoid this problem. Inverse Dynamic Neuro Controller (IDNC) consists of TMBIDNM and Error Reduction Neuro Model (ERNM). Once the TMBIDNM is trained, it does not require retuning for cases with other types of disturbances. The controller is tested for one machine and infinite-bus power system for various operating conditions.