• 한국산업융합학회 논문집
• /
• 제22권2호
• /
• pp.87-93
• /
• 2019

This research deals with posture optimization for humanoid robot against external forces using genetic algorithm and neural network. When the robot takes a motion to push an object, the torque of each joint is generated by reaction force at the palm. This study aims to optimize the posture of the humanoid robot that will change this torque. This study finds an optimized posture using a genetic algorithm such that torques are evenly distributed over the all joints. Then, a number of different optimized postures are generated from various the reaction forces at the palm. The data is to be used as training data of MLP(Multi-Layer Perceptron) neural network with BP(Back Propagation) learning algorithm. Humanoid robot can find the optimal posture at different reaction forces in real time using the trained neural network include non-training data.

• 한국기계가공학회지
• /
• 제14권3호
• /
• pp.85-91
• /
• 2015

The press-fit shaft is an important part used in automobiles, vessels, and trains. This study proposes an optimized design method to reduce damage that may occur in the press-fitted shaft by modifying the shape of the boss step of the press-fitted shaft. To reduce the time and cost of running the optimized design method, an approximate design optimization is applied and an optimized algorithm is generated using a genetic algorithm that is widely used in engineering fields and an approximate model using a response surface method. The planned experiments for the data that are needed to generate the approximate model use a central composite design (CCD) and Latin hypercube sampling (LHS), and the results of the approximate optimization using the above two design of experiments are to be compared.

• Journal of Welding and Joining
• /
• 제17권4호
• /
• pp.39-45
• /
• 1999

The procedure of robotic Gas metal Arc (GMA) welding in order to achieve the optimized bead geometry needs the selection of suitable process parameters such as arc current, welding voltage, welding speed. It is required the relationships between process parameters and bead geometry. The objective of this paper is to develop the algorithm that enables the determination of process parameters from the optimized bead geometry for robotic GMA welding. It depends on the inversion of empirical equations derived from multiple regression analysis of the relationships between the process parameters and the bead dimensions using the least square method. The method not only directly determines those parameters which will give the desired set of bead geometry, but also avoids the need to iterate with a succession of guesses employed Finite Element Method(FEM). These results suggest that process parameter from experimental equation for robotic GMA welding may be employed to monitor and control the bead geometry in real time.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2005년도 춘계학술대회 학술발표 논문집 제15권 제1호
• /
• pp.297-300
• /
• 2005

In this study, we proposed genetically optimized self-organizing fuzzy polynomial neural network based on information granulation and evolutionary algorithm (gdSOFPNN), develop a comprehensive design methodology involving mechanisms of genetic optimization. The proposed gdSOFPNN gives rise to a structural Iy and parametrically optimized network through an optimal parameters design available within FPN (viz. the number of input variables, the order of the polynomial, input variables, the number of membership functions, and the apexes of membership function). Here, with the aid of the information granulation, we determine the initial location (apexes) of membership functions and initial values of polynomial function being used in the premised and consequence part of the fuzzy rules respectively. The performance of the proposed gdSOFPNN is quantified through experimentation that exploits standard data already used in fuzzy modeling.

• 한국복합재료학회:학술대회논문집
• /
• 한국복합재료학회 2000년도 추계학술발표대회 논문집
• /
• pp.191-194
• /
• 2000

In this study, experimental verification of performance of flat speaker has been conducted. The piezofilm (PVDF) actuator has been designed to prevent the distortion of sound and make the frequency response of radiated sound flat. The electrode pattern of piezofilm actuator is optimized to satisfy the design objective. The formulation of design method is based on the coupled finite element and boundary element method and electrode pattern is optimized by genetic algorithm. The flat speaker with optimized piezofilm actuator has been manufactured. The sound pressure level at the distance of 50cm is measured using microphone and compared with the result of numerical simulation.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2005년도 추계학술대회 논문집
• /
• pp.275-281
• /
• 2005

In this paper, a new algorithm is proposed for high speed roaming in an Intelligent Train Control System(ITCS) and study on optimized positioning of radio communication equipment. A DCS(Data Communication System) which is a main part of CBTC(Communication Based Train Control) system, is consisted of radio based wireless communication system and wired optical system. In the radio based wireless communication, the position of AP enclosures and antennas shall be optimized for the guaranteed communication channel between wayside and trains both in open aired and tunnelled area. Also a communication channel established between wayside and train shall be maintained while train moves at its maximum speed. This study shows the way of determining the optimal position for the railway side communication equipment in Bundang Line and how to achieve continuous communicating channel for tracking and controlling train.

• Computers and Concrete
• /
• 제23권5호
• /
• pp.311-320
• /
• 2019

The substructuring technique is one of the efficient methods for reducing computational effort and memory usage in the finite element method, especially in large-scale structures. Proper mesh partitioning plays a key role in the efficiency of the technique. In this study, new algorithms are proposed for mesh partitioning based on an element search technique. The computational cost function is optimized by aligning each element of the structure to a proper substructure. The genetic algorithm is employed to minimize the boundary nodes of the substructures. Since the boundary nodes have a vital performance on the mesh partitioning, different strategies are proposed for the few number of substructures and higher number ones. The mesh partitioning is optimized considering both computational and memory requirements. The efficiency and robustness of the proposed algorithms is demonstrated in numerous examples for different size of substructures.

• 한국CDE학회논문집
• /
• 제14권2호
• /
• pp.129-136
• /
• 2009

Generally, curved surfaces of ship hull are deformed by flame bending (line heating), multi-press forming, and die-less forming method. The forming methods generate the required in-plane/bending strain or displacement on the flat plate to make the curved surface. Multi-press forming imposes the forced displacements on the flat plate by controlling the position of each pressing points based upon the shape difference between the unfolded flat plate and the curved object shape. The flat plate has been obtained from the unfolding system that is independent of the ship CAD. Apparently, the curved surface and the unfolded-flat surface are expressed by different coordinate systems. Therefore, one of the issues is to find a registration of the unfolded surface and the curved shape for the purpose of minimum amount of forming works by comparing the two surfaces. This paper presents an efficient algorithm to get an optimized registration of two different surfaces in the multi-press forming of ship hull plate forming. The algorithm is based upon the ICP (Iterative Closest Point) algorithm. The algorithm consists of two iterative procedures including a transformation matrix and the closest points to minimize the distance between the unfolded surface and curved surfaces. Thereby the algorithm allows the minimized forming works in ship-hull forming.

• 문화기술의 융합
• /
• 제6권4호
• /
• pp.721-726
• /
• 2020

다윈의 적자생존 이론을 토대로 자연에서 일어나는 적응현상을 연구하기 위해 처음 소개된 유전자 알고리즘은 일반적으로 변수가 많아 기존의 수치 해석적인 방법으로 해를 찾기 힘든 수학적인 최적화된 해를 찾는데 사용되어왔다. 본 논문에서는 물리적인 최적화된 실험값을 얻기 위해 유전자 알고리즘이 적용 될 수 있음을 보였다. 먼저 몇 개의 가우시안 함수를 이용하여 주어진 함수 값을 찾는 유전자 알고리즘을 구현 하였고 동일한 알고리즘을 레이저 시스템에 연결하여 최대 40fs 펄스 폭과 1mJ의 최대 출력을 갖는 레이저 펄스를 얻을 수 있었다. 본 연구는 유전자 알고리즘을 레이저 시스템에 적용하여 우리가 원하는 레이저 펄스를 얻는데 사용 될 수 있음을 보였다.

• 한국정보통신학회논문지
• /
• 제13권12호
• /
• pp.2541-2546
• /
• 2009

EPCglobal Class-1 Gen-2 충돌방지 기법에서는 Q-알고리즘을 통하여 질의 라운드의 프레임 크기를 결정한다. Q-알고리즘은 리더의 식별영역 내에 있는 태그의 수를 추정하지 않고 슬롯의 상태만을 이용하여 질의 라운드의 프레임 크기를 계산하므로 다른 DFSA 알고리즘에 비하여 리더의 알고리즘이 단순한 장점이 있다. 반면, Q-알고리즘에서는 프레임 크기를 조절하기 위한 매개변수의 최적화 된 값은 정의하지 않고 있다. 따라서 본 논문에서는 시뮬레이션을 통하여 최소의 식별시간을 얻을 수 있는 최적의 매개변수 값을 제안하였다.