• 상하수도학회지
• /
• 제12권1호
• /
• pp.70-80
• /
• 1998

Many algorithms to find a minimum cost design of water distribution network (WDN) have been developed during the last decades. Most of them have tried to optimize cost only while satisfying other constraining conditions. For this, a certain degree of simplification is required in their calculation process which inevitably limits the real application of the algorithms, especially, to large networks. In this paper, an optimum design method using the Genetic Algorithms (GA) is developed which is designed to increase the applicability, especially for the real world large WDN. The increased to applicability is due to the inherent characteristics of GA consisting of selection, reproduction, crossover and mutation. Just for illustration, the GA method is applied to find an optimal solution of the New York City water supply tunnel. For the calculation, the parameter of population size and generation number is fixed to 100 and the probability of crossover is 0.7, the probability of mutation is 0.01. The yielded optimal design is found to be superior to the least cost design obtained from the Linear Program method by $4.276 million.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.752-757
• /
• 2003

Recently, 3D structure recovery through self-calibration of camera has been actively researched. Traditional calibration algorithm requires known 3D coordinates of the control points while self-calibration only requires the corresponding points of images, thus it has more flexibility in real application. In general, self-calibration algorithm results in the nonlinear optimization problem using constraints from the intrinsic parameters of the camera. Thus, it requires initial value for the nonlinear minimization. Traditional approaches get the initial values assuming they have the same intrinsic parameters while they are dealing with the situation where the intrinsic parameters of the camera may change. In this paper, we propose new initialization method using the minimum 2 images. Proposed method is based on the assumption that the least violation of the camera’s intrinsic parameter gives more stable initial value. Synthetic and real experiment shows this result.

• 한국농공학회:학술대회논문집
• /
• 한국농공학회 2001년도 학술발표회 발표논문집
• /
• pp.295-299
• /
• 2001

To protect the flooding damages in Medium and Small watershed, it needs to set up flood warning system and develope Flood forecasting Model in real-time basis for medium and small watershed. In this study, it was able to minimize the error range between forecasted flood inflow and actual flood inflow, and forecast accurately the flood discharge some hours in advance by using simplex method recursively for the determination of the best parameters of RETFLO model. The result of RETFLO performance applied to several storm of Yugu river during 3 past years was very good with relative errors of 10% for comparison of total runoff volume and with one hour delayed peak time.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 1999년도 춘계종합학술대회
• /
• pp.355-360
• /
• 1999

본 논문에서는 퍼지 논리 제어기에서 전문가의 지식없이 시행 착오법에 의해 최적화 되지 않은 제어 규칙을 이용하는 경우에도, 소속 함수 관계와 스케일링 팩터를 유전자 알고리즘으로 최적화하여 우수한 제어 성능을 갖는 지능 제어 방식을 제안한다. 제안하는 제어 방식은 실제 플랜트는 퍼지 논리를 이용해서 제어를 하되 먼저 오프 라인상에서 퍼지 제어기의 소속 함수 초기 변수값과 스케일링 팩터의 초기값을 유전 알고리즘으로 최적화시킨후 제어를 하는 직접 적응 제어 방식이다. 제안된 제어 방식의 유용성을 확인하기 위하여 비선형 시스템을 제어 대상으로 기존의 퍼지 제어 방식과 시뮬레이션을 통하여 비교 및 검토를 한다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 춘계학술대회 학술발표 논문집 제14권 제1호
• /
• pp.523-527
• /
• 2004

This paper presents a new design methods of the short-term load forecasting system (STLFS) using the data mining. The proposed predictor takes form of the convex combination of the linear time series predictors for each inputs. The problem of estimating the consequent parameters is formulated by the convex optimization problem, which is to minimize the norm distance between the real load and the output of the linear time series estimator, The problem of estimating the premise parameters is to find the parameter value minimizing the error between the real load and the overall output. Finally, to show the feasibility of the proposed method, this paper provides the short-term load forecasting example.

• Nuclear Engineering and Technology
• /
• 제56권8호
• /
• pp.3347-3358
• /
• 2024

Addressing the challenge of identifying an appropriate set of material and irradiation parameters for accurate simulation models using crystal plasticity finite element method (CPFEM), this study proposes a novel two-stage method for nano-indentation modeling of ion-irradiated face-centered cubic (FCC) materials. It includes implementing the strain-gradient crystal plasticity (SGCP) theory with irradiation effects and the calibration of simulation parameters using the particle swarm optimization (PSO) algorithm with experimental data. The proposed method consists of two stages: establishing CPFEM without irradiation effects in stage 1 and modeling irradiation effects based on CPFEM in stage 2. Modeling the nano-indentation test of ion-irradiated stainless steel 304 (SS304) using real experimental data is conducted to evaluate the efficiency of the proposed method. The accuracy of the calibration method using PSO is verified through comparisons between simulation and experimental results for force-indentation depth and hardness-indentation depth relationships under both unirradiated and irradiated conditions. Moreover, effect of ion-irradiation on the mechanical behavior during the nano-indentation of single crystal SS304 is also examined to demonstrate that the proposed method is a powerful approach for nano-indentation modeling of ion-irradiated FCC single crystals using SGCP theory and the PSO algorithm.

• 대한산업공학회지
• /
• 제39권5호
• /
• pp.361-366
• /
• 2013

Prediction of process parameters is very important in parameter design. If predictions are fairly accurate, the quality improvement process will be useful to save time and reduce cost. The concept of dual response approach based on response surface methodology has widely been investigated. Dual response approach may take advantages of optimization modeling for finding optimum setting of input factor by separately modeling mean and variance responses. This study proposes an alternative dual response approach based on machine learning techniques instead of statistical analysis tools. A hybrid neural network-genetic algorithm has been proposed for the purpose of parameter design. A neural network is first constructed to model the relationship between responses and input factors. Mean and variance responses correspond to output nodes while input factors are used for input nodes. Using empirical process data, process parameters can be predicted without performing real experimentations. A genetic algorithm is then applied to find the optimum settings of input factors, where the neural network is used to evaluate the mean and variance response. A drug formulation example from pharmaceutical industry has been studied to demonstrate the procedures and applicability of the proposed approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권8호
• /
• pp.2587-2605
• /
• 2022

In order to efficiently detect community structure in complex networks, community detection algorithms can be designed from the perspective of node similarity. However, the appropriate parameters should be chosen to achieve community division, furthermore, these existing algorithms based on the similarity of common neighbors have low discrimination between node pairs. To solve the above problems, a noval community detection algorithm using closeness similarity based on common neighbor node clustering entropy is proposed, shorted as CSCDA. Firstly, to improve detection accuracy, common neighbors and clustering coefficient are combined in the form of entropy, then a new closeness similarity measure is proposed. Through the designed similarity measure, the closeness similar node set of each node can be further accurately identified. Secondly, to reduce the randomness of the community detection result, based on the closeness similar node set, the node leadership is used to determine the most closeness similar first-order neighbor node for merging to create the initial communities. Thirdly, for the difficult problem of parameter selection in existing algorithms, the merging of two levels is used to iteratively detect the final communities with the idea of modularity optimization. Finally, experiments show that the normalized mutual information values are increased by an average of 8.06% and 5.94% on two scales of synthetic networks and real-world networks with real communities, and modularity is increased by an average of 0.80% on the real-world networks without real communities.

• 설비공학논문집
• /
• 제29권9호
• /
• pp.472-481
• /
• 2017

Radiant floor heating systems have been used as common heating supply systems in most residential buildings in Korea. Since the system uses a floor as thermal storage, proper control strategy should be adopted to avoid over-or under-heating problems. So far, studies related to control of the floor heating system have been conducted based on computer simulations. The active layer in TRNSYS is known for its usability as a floor heating system model and is integrated with the TRNSYS building model (Type 56). However, floor heating system simulations with the active layer are operated only if pre-defined minimum mass flow rate is ensured. This study proposes a simple RC (Resistance-Capacitance) model for radiant floor heating systems. Model parameters such as Rs and Cs are defined by optimization. The active layer, in this study, is used as the target system to search for optimal values. A TRNOPT optimization tool was used to conduct optimization under given simulation conditions. The RC model with optimal parameters are tested in other mass flow rates that were not used during optimization. Results reveal the RC model describes the active layer with successfully optimized model parameters. The RC model has fewer model limitations, and is expected to be used for various target systems, e.g. experimental data of a real radiant heating system.

• 한국정밀공학회지
• /
• 제20권11호
• /
• pp.117-126
• /
• 2003

GA(genetic algorithm) has a powerful searching ability and is comparatively easy to use and to apply as well. By that reason, GA is in the spotlight these days as an optimization skill for mechanical systems.$^1$However, GA has a low efficiency caused by a huge amount of repetitive computation and an inefficiency that GA meanders near the optimum. It also can be shown a phenomenon such as genetic drifting which converges to a wrong solution.$^{8}$ These defects are the reasons why GA is not widdy applied to real world problems. However, the low efficiency problem and the meandering problem of GA can be overcomed by introducing parallel computation$^{7}$ and gray code$^4$, respectively. Standard GA(SGA)$^{9}$ works fine on small to medium scale problems. However, SGA done not work well for large-scale problems. Large-scale problems with more than 500-bit of sere's have never been tested and published in papers. In the result of using the SGA, the powerful searching ability of SGA doesn't have no effect on optimizing the problem that has 96 design valuables and 1536 bits of gene's length. So it converges to a solution which is not considered as a global optimum. Therefore, this study proposes ExpGA(experience GA) which is a new genetic algorithm made by applying a new probability parameter called by the experience value. Furthermore, this study finds the solution throughout the whole field searching, with applying ExpGA which is a optimization technique for the structure having genetic drifting by the standard GA and not making a optimization close to the best fitted value. In addition to them, this study also makes a research about the possibility of GA as a optimization technique of large-scale design variable problems.