• Journal of Korean Institute of Industrial Engineers
• /
• v.20 no.4
• /
• pp.113-134
• /
• 1994

A radial basis hybrid neural network (RHNN) is presented for an on-line detection of machine condition change. Two-phase modeling by RHNN is designed for describing a machine condition process and for predicting future signal. A moving block procedure is also designed for detecting a process change. A fast on-line learning algorithm, the recursive least square estimation, is introduced. Experimental results showed the RHNN could be utilized efficiently for on-line machine condition monitoring.

• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.963-965
• /
• 1999

A linear chromosome combined with a grid-based representation of the network and a new crossover operator allow the evolution of the architecture and the weights simultaneously. In our approach there is no need for a separate weight optimization procedure and networks with more than one type of activation function can be evolved. In this paper one evolutionary' strategy of a given dual neural controller was introduced and the simulation results were described in detail through applications to a stabilization control of an Inverted Pendulum System.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.18 no.34
• /
• pp.91-97
• /
• 1995

This paper presents a possible application of artificial neural network in CM system design. CM systems can be designed based on product lines, part characteristics or part routines. GT(Group Technology) which uses part characteristics to design cells is widely applied, however, the identification of the part-machine families is the fundamental problem in the design process. A heuristic procedure using SOFM which requires only part-machine incidence matrix is proposed in this research. Comparison studies on ZODIAC and ROC with SOFM model are done and the results are discussed and summarized in this paper.

• The Journal of Information Technology
• /
• v.7 no.3
• /
• pp.11-18
• /
• 2004

Learning procedure in the neural network is updating of weights between neurons. Unadequate initial learning coefficient causes excessive iterations of learning process or incorrect learning results and degrades learning efficiency. In this paper, adaptive learning algorithm is proposed to increase the efficient in the learning algorithms of Self-Organization Neural Networks. The algorithm updates the weights adaptively when learning procedure runs. To prove the efficiency the algorithm is experimented to classification of strokes which is the reference handwritten character. The result shows improved classification rate about 1.44~3.65% proposed method compare with Kohonan and Mao's algorithms, in this paper.

• Transactions on Control, Automation and Systems Engineering
• /
• v.3 no.1
• /
• pp.43-50
• /
• 2001

In this paper, we propose the design procedure of advance Polynomial Neural Networks(PNN) architecture for optimal model identification of complex and nonlinear system. The proposed PNN architecture is presented as the generic and advanced type. The essence of the design procedure dwells on the Group Method of Data Handling(GMDH). PNN is a flexible neural architecture whose structure is developed through learning. In particular, the number of layers of the PNN is not fixed in advance but is generated in a dynamic way. In this sense, PNN is a self-organizing network. With the aid of three representative numerical examples, compari-sons show that the proposed advanced PNN algorithm can produce the model with higher accuracy than previous other works. And performance index related to approximation and generalization capabilities of model is evaluated and also discussed.

• The Journal of Information Technology
• /
• v.5 no.2
• /
• pp.17-26
• /
• 2002

On this paper, we propose SOSL(Self-Organized Supervised Learning) and it's architecture SOSL is hybrid type neural network. It consists of several CBP (Component Back Propagation) neural networks, and a modified PCA neural networks. CBP neural networks perform supervised learning procedure in parallel to clustered and complex input patterns. Modified PCA networks perform it's learning in order to transform dimensions of original input patterns to lower dimensions by clustering and local projection. Proposed SOSL can effectively apply to neural network learning with large input patterns results in huge networks size.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2923-2925
• /
• 1999

The objective of camera calibration is to determine the internal optical characteristics of camera and 3D position and orientation of camera with respect to the real world. Calibration procedure applicable to general purpose cameras and lenses. The general method to revise the accuracy rate of calibration is using mathematical distortion of lens. The effective og calibration show big difference in proportion to distortion of camera lens. In this paper, we propose the method which calibration distortion model by using neural network. The neural network model implicity contains all the distortion model. We can predict the high accuracy of calibration method proposed in this paper. Neural network can set properly the distortion model which has difficulty to estimate exactly in general method. The performance of the proposed neural network approach is compared with the well-known Tsai's two stage method in terms of calibration errors. The results show that the proposed approach gives much more stable and acceptabke calibration error over Tsai's two stage method regardless of camera resolution and camera angle.

• Smart Structures and Systems
• /
• v.15 no.1
• /
• pp.227-244
• /
• 2015

This study develops a two stage procedure to identify the structural damage based on the optimized artificial neural networks. Initially, the modal strain energy index (MSEI) is established to extract the damaged elements and to reduce the computational time. Then the genetic algorithm (GA) and artificial neural networks (ANNs) are combined to detect the damage severity. The input of the network is modal strain energy index and the output is the flexural stiffness of the beam elements. The principal component analysis (PCA) is utilized to reduce the input variants of the neural network. By using the genetic algorithm to optimize the parameters, the ANNs can significantly improve the accuracy and convergence of the damage identification. The influence of noise on damage identification results is also studied. The simulation and experiment on beam structures shows that the adaptive parameter selection neural network can identify the damage location and severity of beam structures with high accuracy.

• Nuclear Engineering and Technology
• /
• v.55 no.6
• /
• pp.2305-2314
• /
• 2023

The governing equations of atmospheric dispersion most often taking the form of a second-order partial differential equation (PDE). Currently, typical computational codes for predicting atmospheric dispersion use the Gaussian plume model that is an analytic solution. A Gaussian model is simple and enables rapid simulations, but it can be difficult to apply to situations with complex model parameters. Recently, a method of solving PDEs using artificial neural networks called physics-informed neural network (PINN) has been proposed. The PINN assumes the latent (hidden) solution of a PDE as an arbitrary neural network model and approximates the solution by optimizing the model. Unlike a Gaussian model, the PINN is intuitive in that it does not require special assumptions and uses the original equation without modifications. In this paper, we describe an approach to atmospheric dispersion modeling using the PINN and show its applicability through simple case studies. The results are compared with analytic and fundamental numerical methods to assess the accuracy and other features. The proposed PINN approximates the solution with reasonable accuracy. Considering that its procedure is divided into training and prediction steps, the PINN also offers the advantage of rapid simulations once the training is over.

• Smart Structures and Systems
• /
• v.6 no.2
• /
• pp.147-165
• /
• 2010

Impact damage detection in composite structures has gained a considerable interest in many engineering areas. The capability to detect damage at the early stages reduces any risk of catastrophic failure. This paper compares two advanced signal processing methods for impact location in composite aircraft structures. The first method is based on a modified triangulation procedure and Genetic Algorithms whereas the second technique applies Artificial Neural Networks. A series of impacts is performed experimentally on a composite aircraft wing-box structure instrumented with low-profile, bonded piezoceramic sensors. The strain data are used for learning in the Neural Network approach. The triangulation procedure utilises the same data to establish impact velocities for various angles of strain wave propagation. The study demonstrates that both approaches are capable of good impact location estimates in this complex structure.