• Steel and Composite Structures
• /
• 제15권5호
• /
• pp.519-538
• /
• 2013

The design optimization of a cold-formed steel portal frame building is considered in this paper. The proposed genetic algorithm (GA) optimizer considers both topology (i.e., frame spacing and pitch) and cross-sectional sizes of the main structural members as the decision variables. Previous GAs in the literature were characterized by poor convergence, including slow progress, that usually results in excessive computation times and/or frequent failure to achieve an optimal or near-optimal solution. This is the main issue addressed in this paper. In an effort to improve the performance of the conventional GA, a niching strategy is presented that is shown to be an effective means of enhancing the dissimilarity of the solutions in each generation of the GA. Thus, population diversity is maintained and premature convergence is reduced significantly. Through benchmark examples, it is shown that the efficient GA proposed generates optimal solutions more consistently. A parametric study was carried out, and the results included. They show significant variation in the optimal topology in terms of pitch and frame spacing for a range of typical column heights. They also show that the optimized design achieved large savings based on the cost of the main structural elements; the inclusion of knee braces at the eaves yield further savings in cost, that are significant.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.361-367
• /
• 1998

The main two applications of the Genetic Algorithms(GA) are the optimization and the machine learning. Machine Learning has two objectives that make the complex system learn its environment and produce the proper output of a system. The machine learning using the Genetic Algorithms is called GA machine learning or genetic-based machine learning (GBML). The machine learning is different from the optimization problems in finding the rule set. In optimization problems, the population of GA should converge into the best individual because optimization problems, the population of GA should converge into the best individual because their objective is the production of the individual near the optimal solution. On the contrary, the machine learning systems need to find the set of cooperative rules. There are two methods in GBML, Michigan method and Pittsburgh method. The former is that each rule is expressed with a string, the latter is that the set of rules is coded into a string. Th classifier system of Holland is the representative model of the Michigan method. The classifier systems arrange the strength of classifiers of classifier list using the message list. In this method, the real time process and on-line learning is possible because a set of rule is adjusted on-line. A classifier system has three major components: Performance system, apportionment of credit system, rule discovery system. In this paper, we solve the food search problem with the learning and evolution of an artificial ant using the learning classifier system.

• 산업공학
• /
• 제13권3호
• /
• pp.479-485
• /
• 2000

We consider a Location-Allocation Problem with the Cost of Land(LAPCL). LAPCL has extremely huge size of problem and complex characteristic of location and allocation problem. Heuristics and decomposition approaches on simple Location-Allocation Problem were well developed in last three decades. Recently, genetic algorithm(GA) is used widely at combinatorics and NLP fields. A lot of research shows that GA has efficiency for finding good solution. Our main motive of this research is developing of a package for LAPCL. We found that LAPCL could be reduced to trivial problem, if locations were given. In this case, we can calculate fitness function by simple technique. We built a database constructed by zipcode, latitude, longitude, administrative address and posted land price. This database enables any real field problem to be coded into a mathematical location problem. We developed a package for a class of multi-location problem at PC. The package allows for an interactive interface between user and computer so that user can generate various solutions easily.

• Smart Structures and Systems
• /
• 제19권4호
• /
• pp.403-413
• /
• 2017

The present article encompasses a nonlinear finite element (FE) and genetic algorithm (GA) based optimal vibration energy harvesting from nonprismatic piezo-laminated cantilever beams. Three cases of cross section profiles (such as linear, parabolic and cubic) are modelled to analyse the geometric nonlinear effects on the output responses such as displacement, voltage, and power. The simultaneous effects of taper ratios (such as breadth and height taper) on the output power are also studied. The FE based nonlinear dynamic equation of motion has been solved by an implicit integration method (i.e., Newmark method in conjunction with the Newton-Raphson method). Besides this, a real coded GA based constrained optimization scheme has also been proposed to determine the best set of design variables for optimal harvesting of power within the safe limits of beam stress and PZT breakdown voltage.

• 수산해양기술연구
• /
• 제59권2호
• /
• pp.145-154
• /
• 2023

In this study, to control the heading angle of a ship, which is constantly subjected to various internal and external disturbances during the voyage, an LADRC (linear active disturbance rejection control) design that focuses more on improving the disturbance removal performance was proposed. The speed rate of change of the ship's heading angle due to the turn of the rudder angle was selected as a significant factor, and the nonlinear model of the ship's maneuvering equation, including the steering gear, was treated as a total disturbance. It is the similar process with an LADRC design for the first-order transfer function model. At this time, the gains of the controller included in LADRC and the gains of the extended state observer were tuned to RCGAs (real-coded genetic algorithms) to minimize the integral time-weighted absolute error as an evaluation function. The simulation was performed by applying the proposed GA-LADRC controller to the heading angle control of the Mariner class vessel. In particular, it was confirmed that the proposed controller satisfactorily maintains and follows the set course even when the disturbances such as nonlinearity, modelling error, uncertainty and noise of the measurement sensor are considered.

• Journal of applied mathematics & informatics
• /
• 제19권1_2호
• /
• pp.397-414
• /
• 2005

In the existing literature, most of the purchasing models were developed only for retailers problem ignoring the constraint of storage capacity of retailers shop/showroom. In this paper, we have developed a deterministic model of wholesaler-retailers' problem of single product. The storage capacity of wholesaler's warehouse/showroom and retailers' showroom/shop are assumed to be finite. The items are transported from wholesaler's warehouse to retailers' Own Warehouse (OW) in a lot. The customer's demand is assumed to be displayed inventory level dependent. Demands are met from OW and that spaces of OW will immediately be filled by shifting the same amount from the Rented Warehouse (RW) till the RW is empty. The time duration between selling from OW and filling up its space by new ones from RW is negligible. According to relative size of the retailers' existing (own) warehouse capacity and the demand factors, different scenarios are identified. Our objectives are to optimize the cost functions of wholesaler and two retailers separately. To solve this problem, a real coded Genetic Algorithm (GA) with roulette wheel selection/reproduction, whole arithmetic crossover and non-uniform mutation is developed. Finally a numerical example is presented to illustrate the results for different scenarios. To compare the results of GA, Generalised Reduced Gradient Method has been used for the problem. Also, a sensitivity analysis has been performed to study the variations of the optimal average cost with respect to the different parameters.

• 한국항공우주학회지
• /
• 제44권11호
• /
• pp.989-996
• /
• 2016

본 연구는 비선형 응답모델과 실수기반의 혼합형 유전자 알고리즘을 적용하여 로터의 트?-발란스(RTB) 기법을 개발하는 데 목적이 있다. 트?-발란스 조절 파라미터의 변화에 따른 트림해석 결과를 이용하여 2차의 근사함수를 이용하는 비선형 응답모델을 개발하였다. 트?편차와 기체의 진동응답을 최소화하기 위해 균형추 무게, 트림 탭(Trim Tab) 및 피치링크 길이를 최적화하기 위한 비선형계획 문제를 정식화하였다. 정식화 결과는 수렴성 향상을 위해 군집최적화 기법을 실변수기반의 유전자 알고리즘에 통합한 혼합형 유전자 기법을 사용함으로써 효율적인 해석이 가능하였다. 비선형 모델을 이용한 본 연구의 방법을 선형모델의 결과와 비교하여 본 연구의 방법을 검증하였으며 비선형모델을 사용하는 경우 선형모델의 결과보다 향상된 응답특성을 계산할 수 있음을 밝혔다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2007년도 춘계학술대회 학술발표 논문집 제17권 제1호
• /
• pp.341-344
• /
• 2007

본 논문에서는 계층적 공정 경쟁 개념을 병렬 유전자 알고리즘에 적용하여 계층적 공정 경쟁 기반 병렬유전자 알고리즘 (Hierarchical Fair Competition Genetic Algorithm: HFCGA)을 구현하였을 뿐만 아니라 실수코딩 유전자 알고리즘(Real-Coded Genetic Algorithm: RCGA)에서 좋은 성능을 갖는 산술교배(Arithmetic crossover), 수정된 단순교배(modified simple crossover) 그리고 UNDX(unimodal normal distribution crossover)등의 다양한 교배연산자들을 적용, 분석함으로써 개선된 병렬 유전자 알고리즘을 제안하였다. UNDX연산자는 다수의 부모(multiple parents)를 이용하여 부모들의 기하학적 중심(geometric center)에 근접하게 정규분포를 이루며 생성된다. 본 논문은 UNDX를 이용한 HFCGA모델을 구현하고 함수파라미터 최적화 문제에 많이 쓰이는 함수들에 적용시킴으로써 그 성능의 우수성을 증명 한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.329-330
• /
• 2007

본 논문에서는 particle swarm optimization(PSO)를 통한 비선형시스템의 퍼지집합 퍼지모델의 최적화 방법을 제안한다. 퍼지 모델링에서 전반부 동정, 즉 구조 동정 및 파라미터 동정은 비선형 시스템을 표현하는데 있어서 매우 중요하다. 퍼지모델의 전반부 동정에 있어 최적화 과정이 필요하며 유전자 알고리즘(Genetic Algorithm; GA)을 이용하여 퍼지모델을 최적화한 연구가 많이 있다. 본 연구는 파라미터 동정 시 최근 여러 가지 어려운 최적화 문제를 수행함에 있어서 성능의 우수성이 증명된 PSO를 이용하여 퍼지집합 퍼지모델의 전반부 파라미터를 동정하였다. 구조동정은 단순 유전자 알고리즘(Simple Genetic Algorithm; SGA)을 이용하여 동정하였으며 파라미터 동정시 실수 코딩유전자 알고리즘(Real Coded Genetic Algorithm; RCGA)와 PSO를 각각 파라미터 동정에 이용하여 성능을 비교하였다.

• 한국정밀공학회지
• /
• 제23권4호
• /
• pp.75-82
• /
• 2006

In this paper, we propose an optimal trajectory for biped robots to move up-and-down stairs using a genetic algorithm and a computed-torque control for biped robots to be dynamically stable. First, a Real-Coded Genetic Algorithm (RCGA) which of operators are composed of reproduction, crossover and mutation is used to minimize the total energy. Constraints are divided into equalities and inequalities: Equality constraints consist of a position condition at the start and end of a step period and repeatability conditions related to each joint angle and angular velocity. Inequality constraints include collision avoidance conditions of a swing leg at the face and edge of a stair, knee joint conditions with respect to the avoidance of the kinematic singularity, and the zero moment point condition with respect to the stability into the going direction. In order to approximate a gait, each joint angle trajectory is defined as a 4-th order polynomial of which coefficients are chromosomes. The effectiveness of the proposed optimal trajectory is shown in computer simulations with a 6-dof biped robot that consists of seven links in the sagittal plane. The trajectory is more efficient than that generated by the modified GCIPM. And various trajectories generated by the proposed GA method are analyzed in a viewpoint of the consumption energy: walking on even ground, ascending stairs, and descending stairs.