• 한국정밀공학회지
• /
• 제20권3호
• /
• pp.89-96
• /
• 2003

An electro-hydraulic manipulator using hydraulic actuators has many nonlinear abetments, and its parameter fluctuations are greater than those of an electrically driven manipulator. So it is relatively difficult to realize not only stable but also accurate trajectory control for the autonomous assembly tasks using hydraulic manipulators. In this report, we propose a two-degree-of-freedom control including parallel feedforward compensator (PFC) where PFC plays a very important role in the stability of a proposed control system. In the experimental results of the 6-link electro hydraulic manipulator, it is verified that the stability and the model matching performance are improved by using the proposed control method.

• 한국정밀공학회지
• /
• 제16권11호
• /
• pp.158-165
• /
• 1999

It has been established that a crack has an important effect on the dynamic behavior of a structure. This effect depends mainly on the location and depth of the crack. To identify the location and depth of a crack in a structure, a method is presented in this paper which uses hybrid neuro-genetic technique. Feed-forward multilayer neural networks trained by back-propagation are used to learn the input)the location and dept of a crack)-output(the structural eigenfrequencies) relation of the structural system. With this neural network and genetic algorithm, it is possible to formulate the inverse problem. Neural network training algorithm is the back propagation algorithm with the momentum method to attain stable convergence in the training process and with the adaptive learning rate method to speed up convergence. Finally, genetic algorithm is used to fine the minimum square error.

• Membrane and Water Treatment
• /
• 제9권2호
• /
• pp.129-136
• /
• 2018

In this contribution, the control of multivariable reverse osmosis (RO) desalination plant using proportional-integral-derivative (PID) controllers is presented. First, feed-forward compensators are designed using simplified decoupling method and then the PID controllers are tuned for flux (flow-rate) and conductivity (salinity). The tuning of PID controllers is accomplished by minimization of the integral of squared error (ISE). The ISEs are minimized using a recently proposed algorithm named as teacher-learner-based-optimization (TLBO). TLBO algorithm is used due to being simple and being free from algorithm-specific parameters. A comparative analysis is carried out to prove the supremacy of TLBO algorithm over other state-of-art algorithms like particle swarm optimization (PSO), artificial bee colony (ABC) and differential evolution (DE). The simulation results and comparisons show that the purposed method performs better in terms of performance and can successfully be applied for tuning of PID controllers for RO desalination plants.

• Geomechanics and Engineering
• /
• 제1권4호
• /
• pp.307-321
• /
• 2009

The paper employs a feed forward neural network with back-propagation algorithm for modeling time dependent swell in clays containing carbonate in the presence of sulfuric acid. The oedometer swell percent is estimated at a nominal surcharge pressure of 6.25 kPa to develop 612 data sets for modeling. The input parameters used in the network include time, sulfuric acid concentration, carbonate percentage, and liquid limit. Among the total data sets, 280 (46%) were assigned to training, 175 (29%) for testing and the remaining 157 data sets (25%) were relegated to cross validation. The network was programmed to process this information and predict the percent swell at any time, knowing the variable involved. The study demonstrates that it is possible to develop a general BPNN model that can predict time dependent swell with relatively high accuracy with observed data ($R^2$=0.9986). The obtained results are also compared with generated non-linear regression model.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2009년도 춘계학술대회 논문집 특별세미나,특별/일반세션
• /
• pp.259-264
• /
• 2009

This paper proposes a real-time estimation of the boost inductance in a single-phase AC/DC parallel PWM converter for high-speed EMU. The estimation procedure of the boost inductance is only based on the variation of input current and the input AC voltage measurement. The estimated boost inductance is optimized by the least square method. This estimation technique can improve the performance of current controller and reduce the harmonics of the input current in the feed-forward controller. The validity of proposed technique is verified through the MATLAB SIMULINK simulation results.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2019년도 전력전자학술대회
• /
• pp.136-138
• /
• 2019

무선급전 시스템에서 대기 모드 시에도 전력을 소모하는 비중이 큰 수신부 통신 모듈을 OFF 시켜서 대기전력을 낮출 수 있다. 이때 대기모드 시 PFC 동작을 OFF 시키게 되면 추가로 대기전력을 더 낮출 수 있지만 PFC가 OFF된 상태에서는 AC 입력전압 크기에 따라 인버터 입력 전압 범위가 크게 변동하게 된다. 하지만 수신 통신 모듈 OFF시에는 무선통신을 통한 출력전압제어를 할 수 없기 때문에 안정적인 전력전달이 힘들다. 따라서 본 논문에서는 대기모드 시 출력전압을 일정 수준으로 제어하기 위해, 입력전압 크기에 따른 Feed-forward 구조를 통하여 동작 주파수를 가변 하는 무선전력전송 시스템을 구현하고자 한다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2018년도 학술발표회
• /
• pp.157-157
• /
• 2018

A reliable and accurate downscaling model which can provide climate change information, obtained from global climate models (GCMs), at finer resolution has been always of great interest to researchers. In order to achieve this model, linear methods widely have been studied in the past decades. However, nonlinear methods also can be potentially beneficial to solve downscaling problem. Therefore, this study explored the applicability of some nonlinear machine learning techniques such as neural network (NN), extreme learning machine (ELM), and ELM autoencoder (ELM-AE) as well as a linear method, least absolute shrinkage and selection operator (LASSO), to build a reliable temperature downscaling model. ELM is an efficient learning algorithm for generalized single layer feed-forward neural networks (SLFNs). Its excellent training speed and good generalization capability make ELM an efficient solution for SLFNs compared to traditional time-consuming learning methods like back propagation (BP). However, due to its shallow architecture, ELM may not capture all of nonlinear relationships between input features. To address this issue, ELM-AE was tested in the current study for temperature downscaling.

• 한국산업융합학회 논문집
• /
• 제23권6_1호
• /
• pp.889-896
• /
• 2020

We describe a new approach to the analyze the control performance of robotic manipulator based on the monitoring system. The structure of monitoring simulator is consist of seven modes such as control state mode, coordinate mode, input/output mode, program mode, parameters mode, and track mode. The applied control algorithme consists of an time varying feed-forward and feedback controller. The proposed scheme is simple in structure, fast in computation, and suitable for real-time implimemtation. Moreover, this scheme does not require any accurate dynamic modeling and values of parameters. Performance of the proposed monitoring system is illustrated by simulation and experiment for robot manipulator with six degrees of freedom.

• The Plant Pathology Journal
• /
• 제38권4호
• /
• pp.395-402
• /
• 2022

To predict rice blast, many machine learning methods have been proposed. As the quality and quantity of input data are essential for machine learning techniques, this study develops three artificial neural network (ANN)-based rice blast prediction models by combining two ANN models, the feed-forward neural network (FFNN) and long short-term memory, with diverse input datasets, and compares their performance. The Blast_Weathe long short-term memory r_FFNN model had the highest recall score (66.3%) for rice blast prediction. This model requires two types of input data: blast occurrence data for the last 3 years and weather data (daily maximum temperature, relative humidity, and precipitation) between January and July of the prediction year. This study showed that the performance of an ANN-based disease prediction model was improved by applying suitable machine learning techniques together with the optimization of hyperparameter tuning involving input data. Moreover, we highlight the importance of the systematic collection of long-term disease data.

• Journal of Applied and Pure Mathematics
• /
• 제4권3_4호
• /
• pp.185-209
• /
• 2022

Here we exhibit multivariate quantitative approximations of Banach space valued continuous multivariate functions on a box or ℝ^N, N ∈ ℕ, by the multivariate normalized, quasi-interpolation, Kantorovich type and quadrature type neural network operators. We treat also the case of approximation by iterated operators of the last four types. These approximations are achieved by establishing multidimensional Jackson type inequalities involving the multivariate modulus of continuity of the engaged function or its high order Fréchet derivatives. Our multivariate operators are defined by using a multidimensional density function induced by the generalized symmetrical sigmoid function. The approximations are point-wise and uniform. The related feed-forward neural network is with one hidden layer.