• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.8
• /
• pp.898-906
• /
• 1999

A control structure is introduced for the purpose of rejecting periodic (or repetitive) disturbances on a tracking system. The objective of the proposed structure is to drive the output of the system to the reference input that will result in perfect following without any changing the inner configuration of the system. The structure includes an adaptation block which learns the dynamics of the periodic disturbance and forces the interferences, caused by disturbances, on the output of the system to be reduced. Since the control structure acquires the dynamics of the disturbance by on-line adaptation, it is possible to generate control signals that reject any slowly varying time-periodic disturbance provided that its amplitude is bounded. The artificial neural network is adopted as the adaptation block. The adaptation is done at an on-line process. For this , the real-time recurrent learning (RTRL) algoritnm is applied to the training of the artificial neural network.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.4
• /
• pp.635-641
• /
• 2016

In many industrial applications that use the electric motors robust controllers are needed. The method using a neural network in order to design a robust controller when a disturbance occurs is studied. Backpropagation algorithm, which is used in a conventional neural network controller is used in many areas, but when the number of neurons in the input layer, hidden layer and output layer of the neural network increases the processing speed of the learning process is slow. In this paper an adaptive PI(Proportional and Integral) controller based on CTRNN(Continuous Time Recurrent Neural Network) for permanent magnet synchronous motors is presented. By varying the load and the speed the validity of the proposed method is verified through simulation and experiments.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.168-171
• /
• 2002

A neural network model for predicting the quality or soundness of the injected plastic aspherical lens based on process parameters has been developed. The approach uses a Real Time Recurrent Neural Network 4-5-2 (RTRN) trained based on input/output data that were taken from FE analysis worts carried out through a CAE software. The system has been developed to search an optimum set of process parameters and reduce the time required for planning the conditions of plastic injection molding at the design stage.

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.3
• /
• pp.238-244
• /
• 2008

Dynamic neural networks have been applied to diverse fields requiring temporal signal processing. This paper presents gamma neural network(GAM) to improve the dynamics of multilayer network. The GAM network uses the gamma memory kernel in the hidden layer of feedforword multilayer network. The GAM network is evaluated in linear and nonlinear system identification, and compared with feedforword(FNN) and recurrent neural networks(RNN) for the relative comparison of its performance. Experimental results show that the GAM network performs better with respect to the convergence and accuracy, indicating that it can be a more effective network than conventional multilayer networks in system identification.

• Advances in Computational Design
• /
• v.5 no.4
• /
• pp.445-465
• /
• 2020

This paper presents a study conducted with the aim of developing a model of tendering based on a technique of artificial intelligence by managing and controlling the factors of success or failure of construction projects through the evaluation of the process of invitation to tender. Aiming to solve this problem, analysis of the current environment based on SWOT (Strengths, Weaknesses, Opportunities, and Threats) is first carried out. Analysis was evaluated through a case study of the construction projects in Algeria, to bring about the internal and external factors which affect the process of invitation to tender related to the construction projects. This paper aims to develop a mean to identify threats-opportunities and strength-weaknesses related to the environment of various national construction projects, leading to the decision on whether to continue the project or not. Following a SWOT analysis, novel artificial intelligence models in forecasting the project status are proposed. The basic principal consists in interconnecting the different factors to model this phenomenon. An artificial neural network model is first proposed, followed by a model based on fuzzy logic. A third model resulting from the combination of the two previous ones is developed as a hybrid model. A simulation study is carried out to assess performance of the three models showing that the hybrid model is better suited in forecasting the construction project status than RNN (recurrent neural network) and FL (fuzzy logic) models.

• Journal of Power Electronics
• /
• v.19 no.3
• /
• pp.771-783
• /
• 2019

Due to nonlinear-synthetic uncertainty including the total unknown nonlinear load torque, the total parameter variation and the fixed load torque, a synchronous reluctance motor (SynRM) driving a continuously variable transmission (CVT) system causes a lot of nonlinear effects. Linear control methods make it hard to achieve good control performance. To increase the control performance and reduce the influence of nonlinear time-synthetic uncertainty, an admixed recurrent Gegenbauer orthogonal polynomials neural network (ARGOPNN) with a modified particle swarm optimization (MPSO) control system is proposed to achieve better control performance. The ARGOPNN with a MPSO control system is composed of an observer controller, a recurrent Gegenbauer orthogonal polynomial neural network (RGOPNN) controller and a remunerated controller. To insure the stability of the control system, the RGOPNN controller with an adaptive law and the remunerated controller with a reckoned law are derived according to the Lyapunov stability theorem. In addition, the two learning rates of the weights in the RGOPNN are regulating by using the MPSO algorithm to enhance convergence. Finally, three types of experimental results with comparative studies are presented to confirm the usefulness of the proposed ARGOPNN with a MPSO control system.

• ETRI Journal
• /
• v.43 no.6
• /
• pp.1081-1092
• /
• 2021

Electroencephalography (EEG) recordings taken during the perception of music tempo contain information that estimates the tempo of a music piece. If information about this tempo stimulus in EEG recordings can be extracted and classified, it can be effectively used to construct a music-based brain-computer interface. This study proposes a novel convolutional recurrent attention model (CRAM) to extract and classify features corresponding to tempo stimuli from EEG recordings of listeners who listened with concentration to the tempo of musics. The proposed CRAM is composed of six modules, namely, network inputs, two-dimensional convolutional bidirectional gated recurrent unit-based sample encoder, sample-level intuitive attention, segment encoder, segment-level intuitive attention, and softmax layer, to effectively model spatiotemporal features and improve the classification accuracy of tempo stimuli. To evaluate the proposed method's performance, we conducted experiments on two benchmark datasets. The proposed method achieves promising results, outperforming recent methods.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.4
• /
• pp.22-27
• /
• 2000

In this paper, new neural network called dynamic multidimensional wavelet neural network (DMWNN) is proposed. The resulting network from wavelet theory provides a unique and efficient representation of the given function. Also the proposed DMWNN have ability to store information for later use. Therefore it can represent dynamic mapping and decreases the dimension of the inputs needed for network. This feature of DMWNN can compensate for the weakness of diagonal recurrent neural network(DRNN) and feedforward wavelet neural network(FWNN). The efficacy of this type of network is demonstrated through experimental results.

• Journal of Industrial Convergence
• /
• v.20 no.4
• /
• pp.23-30
• /
• 2022

Recently, with the development of artificial intelligence (AI) and deep learning, the importance of conversational artificial intelligence chatbots is being highlighted. In addition, chatbot research is being conducted in various fields. To build a chatbot, it is developed using an open source platform or a commercial platform for ease of development. These chatbot platforms mainly use RNN and application algorithms. The RNN algorithm has the advantages of fast learning speed, ease of monitoring and verification, and good inference performance. In this paper, a method for improving the inference performance of RNNs and applied algorithms was studied. The proposed method used the word group expansion learning technique of key words for each sentence when RNN and applied algorithm were applied. As a result of this study, the RNN, GRU, and LSTM three algorithms with a cyclic structure achieved a minimum of 0.37% and a maximum of 1.25% inference performance improvement. The research results obtained through this study can accelerate the adoption of artificial intelligence chatbots in related industries. In addition, it can contribute to utilizing various RNN application algorithms. In future research, it will be necessary to study the effect of various activation functions on the performance improvement of artificial neural network algorithms.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.26-30
• /
• 2022

Spiking neural network is a neural network that applies the working principle of real brain neurons. Due to the biological mechanism of neurons, it consumes less power for training and reasoning than conventional neural networks. Recently, as deep learning models become huge and operating costs increase exponentially, the spiking neural network is attracting attention as a third-generation neural network that connects convolution neural networks and recurrent neural networks, and related research is being actively conducted. However, in order to apply the spiking neural network model to the industry, a lot of research still needs to be done, and the problem of model retraining to apply a new model must also be solved. In this paper, we propose a method to minimize the cost of model retraining by extracting the weights of the existing trained deep learning model and converting them into the weights of the spiking neural network model. In addition, it was found that weight conversion worked correctly by comparing the results of inference using the converted weights with the results of the existing model.