• 전자공학회논문지B
• /
• 제31B권7호
• /
• pp.179-189
• /
• 1994

A two-phase neural network finds exact feasible solutions for a constrained optimization programming problem. The time-varying programming neural network is a modified steepest-gradient algorithm which solves time-varying optimization problems. In this paper, we propose a time-varying two-phase optimization neural network which incorporates the merits of the two-phase neural network and the time-varying neural network. The proposed algorithm is applied to system identification and function approximation using a multi-layer perceptron. Particularly training of a multi-layer perceptrion is regarded as a time-varying optimization problem. Our algorithm can also be applied to the case where the weights are constrained. Simulation results prove the proposed algorithm is efficient for solving various optimization problems.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술회의 논문집 정보 및 제어부문 A
• /
• pp.255-258
• /
• 2003

It is hard to centrol the wheeled mobile robot because of uncertainty of modeling, non-holonomic constraint and so on. To solve the problems, we design the controller of wheeled mobile robot based on fuzzy-neural network algorithm. In this paper, we should research the problem of classical controller for path-tracking algorithm and design of Fuzzy-Neural Network algorithm controller. Classical controller acquired different control value according to change of initial position and direction. In this control value having very difficult and having acquired a lot of trial and error Fuzzy is implemented to adaptive adjust control value by error and change of error and neural network is implemented to adaptive adjust the control gain during the optimization. The computer simulation shows that the proposed fuzzy-neural network controller is effective.

• Journal of Communications and Networks
• /
• 제5권1호
• /
• pp.7-18
• /
• 2003

In this paper, a decision feedback recurrent neural network equalizer and a modified real time recurrent learning algorithm are proposed, and an adaptive adjusting of the learning step is also brought forward. Then, a complex case is considered. A decision feedback complex recurrent neural network equalizer and a modified complex real time recurrent learning algorithm are proposed. Moreover, weights of decision feedback recurrent neural network equalizer under burst-interference conditions are analyzed, and two anti-burst-interference algorithms to prevent equalizer from out of working are presented, which are applied to both real and complex cases. The performance of the recurrent neural network equalizer is analyzed based on numerical results.

• 한국컴퓨터정보학회논문지
• /
• 제22권12호
• /
• pp.137-143
• /
• 2017

In this paper, we propose optimal route searching algorithm using ANN(Artificial Neural Network) and implement route searching system. Our proposed scheme shows that the route using artificial neural network is almost same as the route using Dijkstra's algorithm but the time in our propose algorithm is shorter than that of existing Dijkstra's algorithm. Proposed route searching method using artificial neural network has better performance than exiting route searching method because it use several weight value in making different routes. Through simulation, we show that our proposed routing system improves the performance and reduces time to make route irrespective of the number of hidden layers.

• 전기학회논문지
• /
• 제58권1호
• /
• pp.126-131
• /
• 2009

This study was carried out for the reliability of PD(Partial Discharge) pattern recognition. For the pattern recognition, the database for PD was established by use of self-designed insulation defects which occur and were mostly critical in GIS(Gas Insulated Switchgear). The acquired database was analyzed to distinguish patterns by means of PRPD(Phase Resolved Partial Discharge) method and stored to the form with to unite the average amplitude of PD pulse and the number of PD pulse as the input data of neural network. In order to prove the performance of genetic algorithm combined with neural network, the neural networks with trial-and-error method and the neural network with genetic algorithm were trained by same training data and compared to the results of their pattern recognition rate. As a result, the recognition success rate of defects was 93.2% and the neural network train process by use of trial-and-error method was very time consuming. The recognition success rate of defects, on the other hand, was 100% by applying the genetic algorithm at neural network and it took a relatively short time to find the best solution of parameters for optimization. Especially, it could be possible that the scrupulous parameters were obtained by genetic algorithm.

• 한국구조물진단유지관리공학회 논문집
• /
• 제6권4호
• /
• pp.169-179
• /
• 2002

This paper presents an efficient algorithm for the estimation of damage location and severity in structure using Probabilistic Neural Network (PNN). Artificial neural network has been being used for damage assessment by many researchers, but there are still some barriers that must be overcome to improve its accuracy and efficiency. The major problems with the conventional neural network are the necessity of many training data for neural network learning and ambiguity in the relation of neural network architecture with convergence of solution. In this paper, PNN is used as a pattern classifier to overcome those problems in the conventional neural network. The basic idea of damage assessment algorithm proposed in this paper is that modal characteristics from a damaged structure are compared with the training patterns which represent the damage in specific element to determine how close it is to training patterns in terms of the probability from PNN. The training pattern that gives a maximum probability implies that the element used in producing the training pattern is considered as a damaged one. The proposed damage assessment algorithm using PNN is applied to a 2-span continuous beam model structure to verify the algorithm.

• 한국항해항만학회지
• /
• 제28권3호
• /
• pp.221-225
• /
• 2004

본 논문은 신경 회로망과 유전 알고리즘을 이용한 비선형 시스템 모델링을 다룬다. 비선형 함수의 근사성 때문에 시스템을 식별하고 제어하기 위해서 신경 회로망을 응용한 연구가 실제로 많이 이루어지고 있다. 빠른 응답시간과 최소의 오차를 위해서는 최적구조 신경 회로망을 설계하는 것이 중요하다. 유선 알고리즘은 최근에 단순성과 견고성 때문에 점점 많이 이용되는 추세이다. 따라서 본 논문에서는 유선알고리즘을 이용하여 신경회로망을 최적화한다. 오차와 응답시간을 최소화하는 신경 회로망 구조를 위해서 유전알고리즘의 유전자로 이진 코딩하여 최적 신경회로망을 탐색하고자 한다. 시뮬레이션을 통해서, 최적 신경회로망 구조가 비선형 시스템 식별에 효과적인 것을 입증하고자 한다.

• International Journal of Control, Automation, and Systems
• /
• 제6권3호
• /
• pp.453-459
• /
• 2008

The neural network is currently being used throughout numerous control system fields. However, it is not easy to obtain an input-output pattern when the neural network is used for the system of a single feedback controller and it is difficult to obtain satisfactory performance with when the load changes rapidly or disturbance is applied. To resolve these problems, this paper proposes a new mode to implement a neural network controller by installing a real object for control and an algorithm for this, which can replace the existing method of implementing a neural network controller by utilizing activation function at the output node. The real plant object for controlling of this mode implements a simple neural network controller replacing the activation function and provides the error back propagation path to calculate the error at the output node. As the controller is designed using a simple structure neural network, the input-output pattern problem is solved naturally and real-time learning becomes possible through the general error back propagation algorithm. The new algorithm applied neural network controller gives excellent performance for initial and tracking response and shows a robust performance for rapid load change and disturbance, in which the permissible error surpasses the range border. The effect of the proposed control algorithm was verified in a test that controlled the speed of a motor equipped with a high speed computing capable DSP on which the proposed algorithm was loaded.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 하계학술대회 논문집 D
• /
• pp.2573-2575
• /
• 2003

In this paper, we discuss a fuzzy neural network classifier with immune algorithm. The fuzzy neural network classifier is constructed with the fuzzy classifier and the neural network classifier based on fuzzy rules. To maximize performance of classifier, the immune algorithm and the back propagation algorithm are used. For the generalized classification ability, the simulation results from the iris data demonstrate superiority of the proposed classifier in comparison with other classifier.

• 디지털콘텐츠학회 논문지
• /
• 제18권5호
• /
• pp.969-976
• /
• 2017

본 논문에서는 최적화 알고리즘으로 개발된 WFSO(Water Flowing and Shaking Optimization) 알고리즘을 사용한 인공신경망 과합성공 신경망의 학습 방법을 제안한다. 최적화 알고리즘은 다수의 후보 해를 기반으로 탐색해 나가기 때문에 일반적으로 속도가 느린 단점이 있으나 지역 최소값에 거의 빠지지 않고 병렬화가 용이하며 미분 불가능한 활성화함수를 갖는 인공신경망 학습도 가능하고 구조와 가중치를 동시에 최적화 할 수 있는 장점이 있다. 본 논문에서는 WFSO 알고리즘을 인공신경망 학습에 적용하는 방법을 설명하고 다층 인공신경망과 합성곱 신경망에서 오류역전파 알고리즘과 성능을 비교한다.