• Steel and Composite Structures
• /
• v.47 no.4
• /
• pp.513-521
• /
• 2023

The goal of this work is to create a new and improved GWO (Grey Wolf Optimizer), the so-called Robot GWO (RGWO), for dynamic and static target tracking involving multiple robots in unknown environmental conditions. From applying ourselves with the Gray Wolf Optimization Algorithm (GWO) and how it works, as the name suggests, it is a nature-inspired metaheuristic based on the behavior of wolf packs. Like other nature-inspired metaheuristics such as genetic algorithms and firefly algorithms, we explore the search space to find the optimal solution. The results also show that the improved optimal control method can provide superior power characteristics even when operating conditions and design parameters are changed.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.299-299
• /
• 2021

본 연구에서는 강우-유출 모형의 매개변수를 최적화하기 위해 머신러닝 기법을 활용하였다. 강우-유출 모형의 종류가 검토되었으며 이를 통해 선정된 강우-유출 모형의 매개변수 특성과 유출량 선정과의 관계성이 검토되었다. 이를 위해 다년간의 유출 측정 자료가 있는 연구지역이 선정되었다. 또한 매개변수 최적화를 위한 머신러닝 기법이 검토되었으며, 매개변수 최적화와 유출량 산정 정확성을 비교, 분석함으로써 관계성을 검토하였다. 본 연구의 결과를 요악하면 다음과 같다. (1) 여름 장마의 지속성은 매개변수 최적화 정확성에 영향을 주며 이 둘은 비선형적인 관계를 나타낸다. (2) 매개변수 최적화가 강우 심도에 따라 다른 결과를 나타내며 최적의 강우 심도는 연구 지역마다 차이가 있기 때문에 유역 특성을 반영한 머신러닝 기법 활용이 가능하다. 이를 통해 강우-유출 모형의 매개변수 최적화를 위한 머신러닝 기법의 활용 가능성을 확대하고, 모형의 정확도 개선을 기대 할 수 있다.

• Analytical Science and Technology
• /
• v.36 no.5
• /
• pp.250-257
• /
• 2023

The development of a spectrofluorimetric method for the determination of trimethoprim according to the reaction between O-phthalaldehyde (OPA) in highly alkaline media, and 2-mercaptoethanol (2ME) and this reaction gives fluorescent product measured at (458) nm when excited at (342) nm. The optimization of the analytical parameters that influence intensity was investigated. The intensity of fluorescence of the formed product was linearly related to the concentration of trimethoprim in the (100-1200) ng mL^-1 range. The limit of detection and limit of quantification were estimated to be (22.54) ng mL^-1 and (75.15) ng mL^-1 respectively. The utility of the proposed methods was successfully verified by analysis of trimethoprim in pure and real pharmaceutical preparations with high accuracy, the recovery percentages Re%, were found to be (100.5) % and (99.76) % for pure drug and pharmaceutical preparations respectively.

• Journal of Information Processing Systems
• /
• v.19 no.4
• /
• pp.513-526
• /
• 2023

Supply chain coordination plays a critical role in improving the enterprise performance and the competitive advantage of fresh e-commerce. This study explores the coordination problem of a two-echelon fresh produce e-commerce supply chain comprising a fresh e-commerce enterprise and a fresh supplier in a novel framework. In this framework, the fresh e-commerce sells fresh produce and provides promotion effort; meanwhile, the fresh supplier deliveries fresh produce and provides freshness-keeping effort. Specifically, the optimal decisions under centralized and decentralized decision-making are compared, and it is found that centralized decision-making is more profitable. Based on this work, we created a cost-sharing and revenue-sharing combination contract. This study demonstrates that this contract effectively coordinates the supply chain and makes both parties achieve Pareto optimization when the parameters meet certain conditions. Finally, the feasibility and validity of the contract are presented through a numerical example.

• Nuclear Engineering and Technology
• /
• v.55 no.10
• /
• pp.3515-3524
• /
• 2023

A reinforcement learning framework is proposed for the control problem of outlet steam pressure of the once-through steam generator(OTSG) in this paper. The double-layer controller using Proximal Policy Optimization(PPO) algorithm is applied in the control structure of the OTSG. The PPO algorithm can train the neural networks continuously according to the process of interaction with the environment and then the trained controller can realize better control for the OTSG. Meanwhile, reinforcement learning has the characteristic of difficult application in real-world objects, this paper proposes an innovative pretraining method to solve this problem. The difficulty in the application of reinforcement learning lies in training. The optimal strategy of each step is summed up through trial and error, and the training cost is very high. In this paper, the LSTM model is adopted as the training environment for pretraining, which saves training time and improves efficiency. The experimental results show that this method can realize the self-adjustment of control parameters under various working conditions, and the control effect has the advantages of small overshoot, fast stabilization speed, and strong adaptive ability.

• Computers and Concrete
• /
• v.33 no.6
• /
• pp.739-754
• /
• 2024

This study presents an innovative AI-driven approach to assess the ultimate axial load in Double-Skinned Profiled Steel sheet Composite Walls (DPSCWs). Utilizing a dataset of 80 entries, seven input parameters were employed, and various AI techniques, including Linear Regression, Polynomial Regression, Support Vector Regression, Decision Tree Regression, Decision Tree with AdaBoost Regression, Random Forest Regression, Gradient Boost Regression Tree, Elastic Net Regression, Ridge Regression, and LASSO Regression, were evaluated. Decision Tree Regression and Random Forest Regression emerged as the most accurate models. The top three performing models were integrated into a hybrid approach, excelling in accurately estimating DPSCWs' ultimate axial load. This adaptable hybrid model outperforms traditional methods, reducing errors in complex scenarios. The validated Artificial Neural Network (ANN) model showcases less than 1% error, enhancing reliability. Correlation analysis highlights robust predictions, emphasizing the importance of steel sheet thickness. The study contributes insights for predicting DPSCW strength in civil engineering, suggesting optimization and database expansion. The research advances precise load capacity estimation, empowering engineers to enhance construction safety and explore further machine learning applications in structural engineering.

• Journal of the Korean GEO-environmental Society
• /
• v.18 no.2
• /
• pp.47-51
• /
• 2017

In this study, the optimization algorithm by inverse analysis that is the core of the adaptive management technique was adopted to update the soil engineering properties based on the ground response during the construction. Adaptive management technique is the framework wherein construction and design procedures are adjusted based on observations and measurements made as construction proceeds. To evaluate the performance of the adaptive management technique, the numerical simulation for the triaxial tests and the synthetic deep excavation were conducted with the Hardening Soil model. To effectively conduct the analysis, the effective parameters among the parameters employed in the model were selected based on the composite scaled sensitivity analysis. The results from the undrained triaxial tests performed with soft Chicago clays were used for the parameter calibration. The simulation for the synthetic deep excavation were conducted assuming that the soil engineering parameters obtained from the triaxial simulation represent the actual field condition. These values were used as the reference values. The observation for the synthetic deep excavation simulations was the horizontal displacement of the support wall that has the highest composite scaled sensitivity among the other possible observations. It was found that the horizontal displacement of the support wall with the various initial soil properties were converged to the reference displacement by using the adaptive management technique.

• Asian-Australasian Journal of Animal Sciences
• /
• v.31 no.1
• /
• pp.26-31
• /
• 2018

Objective: This study estimated the genetic parameters for body weight gain and growth curve parameter traits in Korean native chicken (KNC). Methods: A total of 585 $F_1$ chickens were used along with 88 of their $F_0$ birds. Body weights were measured every 2 weeks from hatching to 20 weeks of age to measure weight gain at 2-week intervals. For each individual, a logistic growth curve model was fitted to the longitudinal growth dataset to obtain three growth curve parameters (${\alpha}$, asymptotic final body weight; ${\beta}$, inflection point; and ${\gamma}$, constant scale that was proportional to the overall growth rate). Genetic parameters were estimated based on the linear-mixed model using a restricted maximum likelihood method. Results: Heritability estimates of body weight gain traits were low to high (0.057 to 0.458). Heritability estimates for ${\alpha}$, ${\beta}$, and ${\gamma}$ were $0.211{\pm}0.08$, $0.249{\pm}0.09$, and $0.095{\pm}0.06$, respectively. Both genetic and phenotypic correlations between weight gain traits ranged from -0.527 to 0.993. Genetic and phenotypic correlation between the growth curve parameters and weight gain traits ranged from -0.968 to 0.987. Conclusion: Based on the results of this study population, we suggest that the KNC could be used for selective breeding between 6 and 8 weeks of age to enhance the overall genetic improvement of growth traits. After validation of these results in independent studies, these findings will be useful for further optimization of breeding programs for KNC.

• Journal of Korea Water Resources Association
• /
• v.46 no.11
• /
• pp.1053-1067
• /
• 2013

Distributed ecohydrological model which can simulate hydrological components, vegetation and landsurface temperature using practically available input and observed data with minimum parameters is introduced. This model is designed to properly simulate in area with lack of observed data. Parameter estimation and calibration of the model can be carried out with indirectly estimated data (monthly surface runoff by NRCS-CN method and annual actual vaporization by empirical equation) and remote sensing data (NDVI, LST) instead of observed data. We applied this model in the Naeseong creek basin to evaluate the model validity. Firstly, we found the sensitive parameters which largely influence the simulation results by sensitivity analysis, and then hydrological components, vegetation, land-surface temperature, routed streamflow and water temperature were simulated over 10 years (2001 to 2010) using calibrated parameters. Parameters are estimated by optimization method. It is shown that most of grids are well simulated. In the case of streamflow and water temperature, we checked two observed points in the outlet of watershed and it is shown that streamflow and water temperature are properly simulated as well. Hence, it can be shown that this model properly simulate the hydrological components, vegetation, land-surface temperature, routed streamflow and water temperature as well, even though in despite of using limited input data and minimum parameters.

• Journal of Environmental Science International
• /
• v.23 no.3
• /
• pp.359-368
• /
• 2014

The aim of our research was to apply experimental design methodology in the optimization of N, N-Dimethyl-4-nitrosoaniline (RNO, which is indictor of OH radical formation) degradation using gas mixing-circulation plasma process. The reaction was mathematically described as a function of four independent variables [voltage ($X_1$), gas flow rate ($X_2$), liquid flow rate ($X_3$) and time ($X_4$)] being modeled by the use of the central composite design (CCD). RNO removal efficiency was evaluated using a second-order polynomial multiple regression model. Analysis of variance (ANOVA) showed a high coefficient of determination ($R^2$) value of 0.9111, thus ensuring a satisfactory adjustment of the second-order polynomial multiple regression model with the experimental data. The application of response surface methodology (RSM) yielded the following regression equation, which is an empirical relationship between the RNO removal efficiency and independent variables in a coded unit: RNO removal efficiency (%) = $77.71+10.04X_1+10.72X_2+1.78X_3+17.66X_4+5.91X_1X_2+3.64X_2X_3-8.72X_2X_4-7.80X{_1}^2-6.49X{_2}^2-5.67X{_4}^2$. Maximum RNO removal efficiency was predicted and experimentally validated. The optimum voltage, air flow rate, liquid flow rate and time were obtained for the highest desirability at 117.99 V, 4.88 L/min, 6.27 L/min and 24.65 min, respectively. Under optimal value of process parameters, high removal(> 97 %) was obtained for RNO.