• 한국컴퓨터정보학회논문지
• /
• 제21권5호
• /
• pp.73-77
• /
• 2016

This paper deals with the network reliability problem that decides the communication line between main two districts while the k districts were destroyed in military communication network that the n communication lines are connected in m districts. For this problem, there is only in used the mathematical approach as linear programming (LP) software package and has been unknown the polynomial time algorithm. In this paper we suggest the heuristic algorithm with O(n) linear time complexity to solve the optimal solution for this problem. This paper suggests the flow path algorithm (FPA) and level path algorithm (LPA). The FPA is to search the maximum number of distinct paths between two districts. The LPA is to construct the levels and delete the unnecessary nodes and edges. The proposed algorithm can be get the same optimal solution as LP for experimental data.

• 한국정밀공학회지
• /
• 제29권1호
• /
• pp.79-86
• /
• 2012

This paper proposes PID and RIC (Robust Internal-loop Compensator) based motion controller using dual learning algorithm for position control of linear synchronous motor respectively. Its gains are auto-tuned by using two learning algorithms, reinforcement learning and neural network. The feedback controller gains are tuned by reinforcement learning, and then the feedforward controller gains are tuned by neural network. Experiments prove the validity of dual learning algorithm. The RIC controller has better performance than does the PID-feedforward controller in reducing tracking error and disturbance rejection. Neural network shows its ability to decrease tracking error and to reject disturbance in the stop range of the target position and home.

• Journal of Electrical Engineering and Technology
• /
• 제11권2호
• /
• pp.265-273
• /
• 2016

A water wall system is one of the most important components of a boiler in a thermal power plant, and it is a nonlinear Multi-Input and Multi-Output (MIMO) system, with 6 inputs and 3 outputs. Three models are developed and comp for the controller design, including a linear model, a multilayer feed-forward neural network (MFNN) model and an Echo State Network (ESN) model. First, the linear model is developed by linearizing a given nonlinear model and is analyzed as a function of the operating point. Second, the MFNN and the ESN are developed by using training data from the nonlinear model. The three models are validated using Matlab with nonlinear input-output data that was not used during training.

• 제어로봇시스템학회논문지
• /
• 제6권11호
• /
• 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.

• 전자공학회논문지B
• /
• 제32B권3호
• /
• pp.130-138
• /
• 1995

In this paper, a Novel Approach is Proposed which Identifies linear system Parameters Using a multilayer feedforward neural network trained with backpropagation algorithm. The parameters of linear system can be represented by x9t)/x(t) and x(t)/u(t). Thud, its parameters can be represented in terms of the derivative of output with respect to input of parameters can be represented in terms of the derivative of output with respect to input of trained neural network which is a function of weights and output of neurons. Mathematical representation of the proposed approach is derived, and its validity is shown by simulation results on 2-layer and 3-layer neural network.

• Computers and Concrete
• /
• 제11권3호
• /
• pp.237-252
• /
• 2013

This paper presents the application of artificial neural network (ANN) to predict deep beam deflection using experimental data from eight high-strength-self-compacting-concrete (HSSCC) deep beams. The optimized network architecture was ten input parameters, two hidden layers, and one output. The feed forward back propagation neural network of ten and four neurons in first and second hidden layers using TRAINLM training function predicted highly accurate and more precise load-deflection diagrams compared to classical linear regression (LR). The ANN's MSE values are 40 times smaller than the LR's. The test data R value from ANN is 0.9931; thus indicating a high confidence level.

• Geomechanics and Engineering
• /
• 제16권1호
• /
• pp.21-34
• /
• 2018

Discontinuities considerably affect the mechanical and hydraulic properties of rock mass. These properties of the rock mass are influenced by the geometry of the discontinuities to a great extent. This paper aims to render an account of the geometrical parameters of several discontinuity sets related to the surrounding rock mass of Rudbar Lorestan Pumped Storage Power Plant powerhouse cavern making use of the linear and areal (circular and rectangular) sampling methods. Taking into consideration quite a large quantity of scanline and the window samplings used in this research, it was realized that the areal sampling methods are more time consuming and cost-effective than the linear methods. Having corrected the biases of the geometrical properties of the discontinuities, density (areal and volumetric) as well as the linear, areal and volumetric intensity accompanied by the other properties related to four sets of discontinuities were computed. There is an acceptable difference among the mean trace lengths measured using two linear and areal methods for the two joint sets. A 3D discrete fracture network generation code (3DFAM) has been developed to model the fracture network based on the mapped data. The code has been validated on the basis of numerous geometrical characteristics computed by use of the linear, areal sampling methods and volumetric method. Results of the linear sampling method have significant variations. So, the areal and volumetric methods are more efficient than the linear method and they are more appropriate for validation of 3D DFN (Discrete Fracture Network) codes.

• 정보관리학회지
• /
• 제29권2호
• /
• pp.193-204
• /
• 2012

이 연구에서는 인용 및 동시인용 문헌 네트워크에서의 중심성 지수를 사용한 추론 통계 적용의 첫 번째 단계로써 이들 간 관계의 선형성을 살펴보고자 하였다. 703개의 문헌 동시인용 네트워크를 활용하여 인용 빈도, 연결정도 중심성, 인접 중심성, 매개 중심성 간의 4가지 주요 관계의 패턴을 살펴본 결과, 모든 인용 및 중심성 간 관계가 선형모델보다는 비선형적 모델로 더 잘 설명될 수 있음을 통계적으로 확인되었다. 따라서 이들 간의 인과관계에 대한 다중회귀분석과 같은 추론 통계 분석의 기반이 되는 선형성을 확보하기 위해서는 논리적인 기준에 근거한 데이터 변환이나 실제값을 구간값으로 변환하는 과정이 필요하다고 할 수 있다.

• 전자공학회논문지B
• /
• 제30B권5호
• /
• pp.120-128
• /
• 1993

In this paper, an implementation of high-speed parallel processing system for neural network design on the multicomputer network is presented. Linear speedup expandability is increased by reducing the synchronization penalty and the communication overhead. Also, we presented the parallel processing models and their performance evaluation models for each of the parallization methods of the neural network. The results of the experiments for the character recognition of the neural network bases on the proposed system show that the proposed approach has the higher linear speedup expandability than the other systems. The proposed parallel processing models and the performance evaluation models could be used effectively for the design and the performance estimation of the neural network on the multicomputer network.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1353-1355
• /
• 1996

This paper presents classification of high impedance fault pattern using linear prediction coefficients. A feature of neutral phase current is extracted by the linear predictive coding. This feature is classified into faults by a multilayer perceptron neural network. Neural network successfully classifies test data into three faults and one normal state.