• Transactions on Control, Automation and Systems Engineering
• /
• v.2 no.3
• /
• pp.196-200
• /
• 2000

A neural controller for process control is proposed that combines a conventional multi-loop PID controller with a neural network. The concept of target signal based on feedback error is used fur on-line learning of the neural network. This controller is applied to distillation column control to illustrate its effectiveness. The result shows that the proposed neural controller can cope well with disturbance, strong interactions, time delays without any prior knowledge of the process.

• Transactions on Control, Automation and Systems Engineering
• /
• v.2 no.2
• /
• pp.136-139
• /
• 2000

A neural controller for process control is proposed that combines a conventional multi-loop PID controller with a neural network. The concept of target signal based on feedback error is used for on-line learning of the neural network. This controller is applied to distillation column control to illustrate its effectiveness. The result shows that the proposed neural controller can cope well with disturbance, strong interactions, time delays without any prior knowledge of the process.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.4
• /
• pp.338-342
• /
• 2000

In order to approximate a nonlinear function, wacelet neural networks combining wacelet theory and neural networks have been proposed as an alternative to conventional multi-layered neural networks. wacelet neural networks provide better approximating performance than conventional neural networks. In this paper, an effective method to construct an optimal wavelet neural network is proposed using genetic alogorithm. Genetic Algorithm is used to determine dilationa and translations of wavelet basic functions of wavelet neural networks. Then, these determined dilations dilations and translations, wavelet neural networks are funther trained by back propagation learning algorithm. The effectiveness of the final network is verified thrifigh the approximation result of a nonlinear function and comparison with conventional neural networks.

• Journal of Internet Computing and Services
• /
• v.19 no.4
• /
• pp.45-52
• /
• 2018

A single-image super-resolution is a process of restoring a high-resolution image from a low-resolution image. Recently, the super-resolution using the deep neural network has shown good results. In this paper, we propose a neural network structure that improves speed and performance over conventional neural network based super-resolution methods. To do this, we analyze the conventional neural network based super-resolution methods and propose solutions. The proposed method reduce the 5 stages of the conventional method to 3 stages. Then we have studied the optimal width and depth by experimenting on the width and depth of the network. Experimental results have shown that the proposed method improves the disadvantages of the conventional methods. The proposed neural network structure showed superior performance and speed than the conventional method.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.1
• /
• pp.58-66
• /
• 1992

This paper proposes a neuro-controller for position control of one-link flexible robot arm. Basically the controller consists of a multi-layer neural network and a conventional PD controller. Two controller are parallelly connected. Neural network is traind by the conventional error back propagation learning rules. During learning period, the weights of neural network are adjusted to minimize the position error between the desired hub angle and the actual one. Finally the effectiveness of the proposed approach will be demonstrated by computer simulation.

• Journal of IKEEE
• /
• v.20 no.3
• /
• pp.303-306
• /
• 2016

In this paper, we propose a method to accelerate convolutional neural network by utilizing a GPGPU. Convolutional neural network is a sort of the neural network learning features of images. Convolutional neural network is suitable for the image processing required to learn a lot of data such as images. The convolutional layer of the conventional CNN required a large number of multiplications and it is difficult to operate in the real-time on the embedded environment. In this paper, we reduce the number of multiplications through Winograd convolution operation and perform parallel processing of the convolution by utilizing SIMT-based GPGPU. The experiment was conducted using ModelSim and TestDrive, and the experimental results showed that the processing time was improved by about 17%, compared to the conventional convolution.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.195-198
• /
• 2000

We propose a new wavelet neural network structure, for which we apply new recurrent nodes to the network, in this paper for the dynamic system identification and control. We will construct the wavelet neural network by using wavelet frame function. The function does not have the best approximation property, but it may be possible to apply some modification to the structure of the network because the constriction of orthogonality is loosened a little. This wavelet neural network we propose can obtain previous state information by its structure of the network without any addition of input, though the conventional wavelet network needs additional previous state input for the improvement of the dynamic performance. In numerical experience, the performance of the new wavelet neural network we propose in the nonlinear system with uncertainity of parameter Is equal to that of the wavelet network which used the additional previous information input, superior to that of the conventional wavelet network.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.4
• /
• pp.1724-1731
• /
• 2018

The conventional polynomial neural network (PNN) is a classical flexible neural structure and self-organizing network, however it is not free from the limitation of overfitting problem. In this study, we propose a space search-optimized polynomial neural network (ssPNN) structure to alleviate this problem. Ranking selection is realized by means of ranking selection-based performance index (RS_PI) which is combined with conventional performance index (PI) and coefficients based performance index (CPI) (viz. the sum of squared coefficient). Unlike the conventional PNN, L2-norm regularization method for estimating the polynomial coefficients is also used when designing the ssPNN. Furthermore, space search optimization (SSO) is exploited here to optimize the parameters of ssPNN (viz. the number of input variables, which variables will be selected as input variables, and the type of polynomial). Experimental results show that the proposed ranking selection-based polynomial neural network gives rise to better performance in comparison with the neuron fuzzy models reported in the literatures.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.11
• /
• pp.987-994
• /
• 2000

A Linear Pulse Motor (LPM) is a direct drive motor that has good performance in terms of accuracy, velocity and acceleration compared to the conventional rotating system with toothed belts and ball screws. However, since an LPM needs supporting devices which maintain constant air-gap and has strong nonlinearity caused by leakage magnetic flux, friction and cogging, etc., there are many difficulties in improvement on accuracy with conventional control theory. Moreover, when designing the position controller of LPM, the modeling error and load variations has not been considered. In order to compensate these components, the neural network with conventional feedback controller is introduced. This neural network of feedback error learning type changes the current commands to improve position accuracy. As a result of experiments, we observes that more accurate position control is possible compared to conventional controller.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2003.04a
• /
• pp.357-365
• /
• 2003

The major problems with the conventional neural network, especially Back Propagation Neural Network, arise from the necessity of many training data for neural network learning and ambiguity in the relation of neural network structure to the convergence of solution. In this paper, the PNN is used as a pattern classifier to detect the damage of structure to avoid those drawbacks of the conventional neural network. In the PNN-based pattern classification problems, the probability density function for patterns is usually assumed by Gaussian distribution. But, in this paper, several probability density functions are investigated in order to select the most approriate one for structural damage assessment.