• The Transactions of the Korean Institute of Power Electronics
• /
• v.6 no.3
• /
• pp.273-281
• /
• 2001

In this paper, we propose a CMAC(Cerebellar Model Articulation Controller) neural network for controlling a non-linear system. CMAC is a neural network that models the human cerebellum. CMAC uses a table look-up method to resolve the complex non-linear system instead of numerical calculation method. It is very fast learn compared with other neural networks. It does not need a calculation time to generate control signals. The simulation results show that the proposed CMAC controllers for a simple non-linear function and a DC Motor speed control reduce tracking errors and improve the stability of its learning controllers. The validity of the proposed CMAC controller is also proved by the real-time tension control.

• Journal of Power Electronics
• /
• v.10 no.5
• /
• pp.505-517
• /
• 2010

In this paper, an intelligent sliding-mode speed controller for achieving favorable decoupling control and high precision speed tracking performance of permanent-magnet synchronous motor (PMSM) drives is proposed. The intelligent controller consists of a sliding-mode controller (SMC) in the speed feed-back loop in addition to an on-line trained wavelet-neural-network controller (WNNC) connected in parallel with the SMC to construct a robust wavelet-neural-network controller (RWNNC). The RWNNC combines the merits of a SMC with the robust characteristics and a WNNC, which combines artificial neural networks for their online learning ability and wavelet decomposition for its identification ability. Theoretical analyses of both SMC and WNNC speed controllers are developed. The WNN is utilized to predict the uncertain system dynamics to relax the requirement of uncertainty bound in the design of a SMC. A computer simulation is developed to demonstrate the effectiveness of the proposed intelligent sliding mode speed controller. An experimental system is established to verify the effectiveness of the proposed control system. All of the control algorithms are implemented on a TMS320C31 DSP-based control computer. The simulated and experimental results confirm that the proposed RWNNC grants robust performance and precise response regardless of load disturbances and PMSM parameter uncertainties.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.8 no.6
• /
• pp.142-155
• /
• 2000

A MIMO model reference control scheme incorporating the variable structure theory for a vehicle four wheel steering system(4WS) is proposed and evaluated for a class of continuous-time nonlinear dynamics with known or unknown uncertainties. The scheme employs an neural network to identify the plant systems, where the neural network estimates the nonlinear dynamics of the plant. By the Lyapunov direct method, the algorithm is proven to be globally stable, with tracking errors converging to the neighborhood of zero. The merits of this scheme is that the global system stability is guaranteed and it is not necessary to know the exact structure of the system. With the resulting identification model which contains the neural networks, it does not need higher degrees of freedom vehicle model than 3 degree of freedom model. Th proposed scheme is applied to the active four wheel system and shows the validity is used to investigate vehicle handing performances. In simulation of the J-turn maneuver, the reduction of yaw rate overshoot of a typical mid-size car improved by 30% compared to a two wheel steering system(2WS) case, resulting that the proposed scheme gives faster yaw rate response and smaller side angle than the 2WS case.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.5
• /
• pp.705-711
• /
• 2013

In this paper, we introduce an design of multi-output fuzzy neural networks based on Interval Type-2 fuzzy set. The proposed Interval Type-2 fuzzy set-based fuzzy neural networks with multi-output (IT2FS-based FNNm) comprise the network structure generated by dividing the input space individually. The premise part of the fuzzy rules of the network reflects the individuality of the division space for the entire input space and the consequent part of the fuzzy rules expresses three types of polynomial functions with interval sets such as constant, linear, and modified quadratic inference for pattern recognition. The learning of fuzzy neural networks is realized by adjusting connections of the neurons in the consequent part of the fuzzy rules, and it follows a back-propagation algorithm. In addition, in order to optimize the network, the parameters of the network such as apexes of membership functions, uncertainty factor, learning rate and momentum coefficient were automatically optimized by using real-coded genetic algorithm. The proposed model is evaluated with the use of numerical experimentation.

• KIISE Transactions on Computing Practices
• /
• v.23 no.3
• /
• pp.194-198
• /
• 2017

In this paper, we propose a revised Deep Convolutional Neural Network (DCNN) model to extract Protein-Protein Interaction (PPIs) from the scientific literature. The proposed method has the merit of improving performance by applying various global features in addition to the simple lexical features used in conventional relation extraction approaches. In the experiments using AIMed, which is the most famous collection used for PPI extraction, the proposed model shows state-of-the art scores (78.0 F-score) revealing the best performance so far in this domain. Also, the paper shows that, without conducting feature engineering using complicated language processing, convolutional neural networks with embedding can achieve superior PPIE performance.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2001.10a
• /
• pp.156-161
• /
• 2001

Currently, agricultural facilities are evaluated using either basic inspections or detailed analysis. However, conventional analyses as well as methods based on fuzzy logic and rule of thumb have not been very successful in providing a clear relationship between rating and real state of agricultural facilities, because they can't provide exactly acceptable reliability of degraded structures with manager or supervisor. Therefore, in this stage, we must define probabilistic variables for representing degradation of structures being given damages during a survival time. This paper describes the application of neural network system in developing the relation between subjective ratings and parameters of agricultural reservoir as well as that between subjective and analytical ratings. It is shown that neural networks can be trained and used successfully in estimating a rating based on several parameters. The specific application problem for agricultural reservoir in the rural area of Korea is presented and database is constructed to maintain training data set, the information of inspection and facilities. This study showed that a successful training of a neural network could be useful, especially if the input data set for target problem contains parameters with a diverse combination of inter-correlation coefficients. And the networks had a prediction rating of about $^{\ast}^{\ast}^{\ast}%$. The neural network system is expected to show high performance fairly in estimate than statistical method to use equation that is consisted of very lowly interrelated variables.

• Korean Management Science Review
• /
• v.29 no.3
• /
• pp.81-89
• /
• 2012

Since introduced by Vining and Myers in 1990, the concept of dual response approach based on response surface methodology has widely been investigated and adopted for the purpose of robust design. Separately estimating mean and variance responses, dual response approach may take advantages of optimization modeling for finding optimum settings of input factors. Explicitly assuming functional relationship between responses and input factors, however, it may not work well enough especially when the behavior of responses are poorly represented. A sufficient number of experimentations are required to improve the precision of estimations. This study proposes an alternative to dual response approach in which additional experiments are not required. An artificial neural network has been applied to model relationships between responses and input factors. Mean and variance responses correspond to output nodes while input factors are used for input nodes. Training, validating, and testing a neural network with empirical process data, an artificial data based on the neural network may be generated and used to estimate response functions without performing real experimentations. A drug formulation example from pharmaceutical industry has been investigated to demonstrate the procedures and applicability of the proposed approach.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1220-1225
• /
• 2010

This paper proposes a novel active noise control (ANC) approach that uses an IIR filter and neural network techniques to effectively reduce interior noise. We construct a multiple-channel IIR filter module which is a linearly augmented framework with a generic IIR model to generate a primary control signal. A three-layer perceptron neural network is employed for establishing a secondary-path model to represent air channels among noise fields. Since the IIR module and neural network are connected in series, the output of an IIR filter is transferred forward to the neural model to generate a final ANC signal. A gradient descent optimization based learning algorithm is analytically derived for the optimal selection of the ANC parameter vectors. Moreover, re-estimation of partial parameter vectors in the ANC system is proposed for online learning. Lastly, we present the results of a numerical study to test our ANC methodology with realistic interior noise measurement obtained from Korean railway trains.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.1
• /
• pp.13-21
• /
• 1995

In this paper, we improve an image classifier algorithm based on neural network learning. It consists of two steps. The first is input pattern generation and the second, the global neural network implementation using an improved back-propagation algorithm. The feature vector for pattern recognition consists of the codebook data obtained from self-organization feature map learning. It decreases the input neuron number as well as the computational cost. The global neural network algorithm which is used in classifier inserts a control part and an address memory part to the back-propagation algorithm to control weights and unit-offsets. The simulation results show that it does not fall into the local minima and can implement easily the large-scale neural network. And it decreases largely the learning time.

• Journal of Hydrogen and New Energy
• /
• v.26 no.3
• /
• pp.294-299
• /
• 2015

Free piston linear engine (FPLE) is a promising concept being explored in the mid-20th century. On the other hand, Arficial neural networks (ANNs) are non-linear computer algorithms and can model the behavior of complicated non-linear processes. Some researchers already studied this method to predict internal combustion engine characteristics. However, no investigation to predict the performance of a FPLE using ANN approach appears to have been published in the literature to date. In this study, the ability of an artificial neural network model, using a back propagation learning algorithm has been used to predict the in-cylinder pressure, frequency, maximum stroke length of a free piston linear engine. It is advised that, well-trained neural network models can provide fast and consistent results, making it an easy-to-use tool in preliminary studies for such thermal engineering problems.