This study proposes a weighted ensemble deep learning framework for accurately predicting the State of Health (SOH) of lithium-ion batteries. Three distinct model architectures—CNN-LSTM, Transformer-LSTM, and CEEMDAN-BiGRU—are combined using a normalized inverse RMSE-based weighting scheme to enhance predictive performance. Unlike conventional approaches using fixed hyperparameter settings, this study employs Bayesian Optimization via Optuna to automatically tune key hyperparameters such as time steps (range: 10-35) and hidden units (range: 32-128). To ensure robustness and reproducibility, ten independent runs were conducted with different random seeds. Experimental evaluations were performed using the NASA Ames B0047 cell discharge dataset. The ensemble model achieved an average RMSE of 0.01381 with a standard deviation of ±0.00190, outperforming the best single model (CEEMDAN-BiGRU, average RMSE: 0.01487) in both accuracy and stability. Additionally, the ensemble's average inference time of 3.83 seconds demonstrates its practical feasibility for real-time Battery Management System (BMS) integration. The proposed framework effectively leverages complementary model characteristics and automated optimization strategies to provide accurate and stable SOH predictions for lithium-ion batteries.

This study focuses on the effectiveness of regional business support programs funded by South Korea's Balanced National Development Special Account, one of the policies designed to address regional imbalances and promote local autonomy. Using the analytical approach including DEA (Data Envelopment Analysis) methodology, This study analyzed the efficiency of 76 star companies in the Jeonbuk region based on their performance from 2018 to 2023. This study was designed to improve previous studies limitations, which only analyzed simple input-output efficiency in the short term, by using six years of mid-term data to comprehensively evaluate input variables in both R&D and Non-R&D sectors. The main purpose of this study is to analyze the effectiveness of the expiring Star Company Development Program by evaluating efficiency of supported company groups using DEA and to propose support models and policy suggestions for upcoming regional specialized industries support program by identifying the features of both optimal and inefficiency models. For this, employments along with financial indicators such as sales revenue, operating profit, and total assets were set as output variables, with R&D and non-R&D support amounts were set as input variables for analysis. According to the results, the optimal efficiency model group has strong intellectual property acquisition capabilities, and continuous R&D investment. It shows that continuous innovation activities are a key factor for improving the effectiveness of support. This study found that, from a mid․long term perspective, policy support programs should be customized by unique characteristics of each industry field, Based on this, it was suggested that upcoming regional specialized industry support programs in the Jeonbuk region should include policy planning and support program design to complement the weaknesses of each industry field.

The design variables and material properties as well as the external loads concerned with structural engineering are used to be deterministic in optimization process. These values, however, have variability from expected performance. Therefore, deterministic optimum designs that are obtained without taking these uncertainty into account could lead to unreliable designs, which necessitates the Reliability-Based Design Optimization(RBDO). RBDO involves an evaluation of probabilistic constraints which constitutes another optimization procedure. So, an expensive computational cost is required. Therefore, how to decrease the computational cost has been an important challenge in the RBDO research field. Approximation models, response surface model and Kriging model, are employed to improve an efficiency of the RBDO.

This study introduces and experimentally validates a novel approach that combines Instruction fine-tuning and Low-Rank Adaptation (LoRA) fine-tuning to optimize the performance of Large Language Models (LLMs). These models have become revolutionary tools in natural language processing, showing remarkable performance across diverse application areas. However, optimizing their performance for specific domains necessitates fine-tuning of the base models (FMs), which is often limited by challenges such as data complexity and resource costs. The proposed approach aims to overcome these limitations by enhancing the performance of LLMs, particularly in the analysis precision and efficiency of national Research and Development (R&D) data. The study provides theoretical foundations and technical implementations of Instruction fine-tuning and LoRA fine-tuning. Through rigorous experimental validation, it is demonstrated that the proposed method significantly improves the precision and efficiency of data analysis, outperforming traditional fine-tuning methods. This enhancement is not only beneficial for national R&D data but also suggests potential applicability in various other data-centric domains, such as medical data analysis, financial forecasting, and educational assessments. The findings highlight the method's broad utility and significant contribution to advancing data analysis techniques in specialized knowledge domains, offering new possibilities for leveraging LLMs in complex and resource- intensive tasks. This research underscores the transformative potential of combining Instruction fine-tuning with LoRA fine-tuning to achieve superior performance in diverse applications, paving the way for more efficient and effective utilization of LLMs in both academic and industrial settings.

This research presented the procedural framework of developing and optimizing an artificial intelligence model for predicting the change of bread texture by different baking enhancers. Emphasis was placed on the impact of various baking enhancers on the Mixolab thermo-mechanical properties of wheat flour and consequent alterations in bread texture. The application of baking enhancers positively contributed to dough formation and stability, producing bread with a soft texture. However, a relatively low Pearson correlation coefficient was observed between a single Mixolab parameter and bread texture (r<0.59). To more accurately predict the texture of bread from the thermo-mechanical features of wheat flour with baking enhancers, five AI models (multiple linear regression, decision tree, stochastic gradient descent, random forest, and multilayer perceptron neural network) were applied, and their prediction performance was compared. The multilayer perceptron neural network model was further utilized to enhance the prediction of bread texture by mitigating overfitting risks. Finally, the hyperparameter tuning (activation function [Leaky ReLU], regularization [0.0001], and dropout [0.1]) led to enhanced model performance (R2 = 0.8109 and RMSE = 0.1096).

본 논문에서는 다이나믹크리깅 대리모델 기반 자동차 브레이크 패드 마모량 측정센서 브라켓의 설계최적화를 소개한다. 브레이크 작동시 마찰재 바닥의 온도가 600°C 이상으로 상승하고, 이 열이 전달되어 센서의 기능을 상실시킨다. 따라서 열전달을 최소화하는 브라켓 형상의 설계최적화는 필수적이다. 최적화에 소요되는 계산비용을 절감하기 위해 다이나믹크리깅 대리모델로 열전달 시뮬레 이션을 대체하였다. 다이나믹크리깅은 최적의 상관함수와 기저함수를 선정하였으며, 정확한 대리모델을 도출하였다. 최적화 결과 센 서위치의 온도가 초기모델에 비해 7.57% 감소하였으며, 이를 열전달 시뮬레이션으로 다시 한번 확인하여 대리모델 기반 최적설계가 유의미함을 검증하였다.

본 논문에서는 무도상 철도판형교에 열차하중이 재하되었을 때 변위를 최소화시키는 하부 수평브레이싱의 보강 형상 및 설치 위치를 검토하였다. 우선 거더와 수평 브레이싱으로 연결된 2거더 구조계의 전체 횡좌굴모멘트에 영향을 주는 요소를 검토하였다. 다음 으로는 무도상 철도판형교의 하부를 설치 위치를 달리하여 수평브레이싱으로 보강하였다. 보강된 무도상 철도판형교에 열차하중 및 거 더의 중심과 열차하중의 재하위치간의 편심거리(e)에 따라 발생하는 축방향의 비틀림모멘트를 고려하여 구조해석을 수행하였다. 보강모 델별로 지간 중앙에서의 단면의 중심에서 발생하는 변위를 검토하여 변위를 최소화시키는 모델을 선정하였다. 본 연구를 통하여 무도상 철도판형교에 열차하중 재하시 변위를 최소화시키는 하부 수평브레이싱의 보강 형상 및 설치 위치를 제안하였다.

본 논문에서는 위상최적설계를 위한 입자-구조 충돌 모델을 제시한다. 위상최적설계를 위해서는 민감도 분석이 선행되어야 하며, 민감도 분석이 가능한 새로운 모델이 필요하다. 본 논문에서는 위상최적설계를 위한 민감도 분석을 수행하기 위한 입자-구조 충돌 모 델을 제시한다. 이후 이 모델을 이용하여 위상최적설계를 위한 민감도 분석을 수행한다. 제안한 모델의 정확도를 평가하기 위해 먼저 단순화된 1차원 충돌 문제에 적용한다. 이후, 이 모델을 이용하여 위상 최적화를 통해 입자의 최종 위치를 최적화하여 위상 최적화에 대한 이 모델의 적용 가능성을 확인한다. 이러한 결과는 위상 최적화에서 입자-구조 충돌을 고려하는 것이 가능하다는 것을 보여준다.

Effects-Based Operations (EBO) refers to a process for achieving strategic goals by focusing on effects rather than attrition-based destruction. For a successful implementation of EBO, identifying key nodes in an adversary network is crucial in the process of EBO. In this study, we suggest a network-based approach that combines network centrality and optimization to select the most influential nodes. First, we analyze the adversary’s network structure to identify the node influence using degree and betweenness centrality. Degree centrality refers to the extent of direct links of a node to other nodes, and betweenness centrality refers to the extent to which a node lies between the paths connecting other nodes of a network together. Based on the centrality results, we then suggest an optimization model in which we minimize the sum of the main effects of the adversary by identifying the most influential nodes under the dynamic nature of the adversary network structure. Our results show that key node identification based on our optimization model outperforms simple centrality-based node identification in terms of decreasing the entire network value. We expect that these results can provide insight not only to military field for selecting key targets, but also to other multidisciplinary areas in identifying key nodes when they are interacting to each other in a network.

In the automobile manufacturing industry, lightweight design is one of the essential challenges to be solved fundamentally. The vehicle wheels are classified as safety related components as the main substructure of the vehicle. In this study, we illustrate a technique for selecting the appropriate number of spokes. Based on the basic model of the selected number of spokes, we propose a method to maintain stiffness and design lightweight using topology optimization software. Based on the basic model of the selected number of spokes, it was redesigned to be lightweight while maintaining stiffness by utilizing topology optimization software. By comparing and reviewing the structural analysis results of the basic model and the redesigned model, a design technique that can maintain structural safety and reduce wheel mass was proposed.

전 세계적으로 해상을 마주하고 있는 여러 국가들은 기존의 전력 생산방식의 단점을 극복하고 해상풍력 개발을 통한 친환경에 너지자원을 활용하고 있다. 해상은 넓은 해역에 대규모 풍력단지를 개발할 수 있는 장점이 있으나 해양구조물의 설치로 인해 선박의 안 전운항이 위협받고 있다. 이에 따라, 선박 통항로와 해상풍력단지 간 상호 미치는 영향에 대해 분석하여 선박이 안전하게 운항할 수 있도 록 PIANC에서는 표준 Guideline을 제시하였다. 그럼에도 불구하고, 표준 Guideline은 모든상황에서 동일한 이격거리를 산정하였다. 따라서 본 연구에서는 선회성능, 조우상태, 환경외력, 해상밀집도, 해상풍력발전기, 항로형태 등을 요소로 반영한 선박 통항로와 해상풍력단지 간 최적의 이격거리 산정 모델을 개발하였다. 개발된 모델 검증을 위한 시뮬레이션 결과, 운항 준비상태에 따른 입지 특성별 선회성능 크기 는 산정 모델에서 제시한 크기와 유사하였다.

Due to environmental pollution, regulations on fossil fuels are required. There is a movement for the regulations by using LNG fueled propulsion ships. LNG is an eco-friendly fuel that does not emit NOx or SOx during combustion, but its boiling point is -163°C. Under that condition, the use of metal is restricted, and IMO defined applicable materials through IGC code. Among the metals, 9% nickel steel is one of excellent mechanical properties such as yield strength and tensile strength in cryogenic condition. Thus 9% nickel steel is widely used in cryogenic storage containers for ships. In addition, laser welding, which minimizes thermoelastic distortion by applying a concentrated heat source to a narrow area for a short period of time, is in the spotlight. So, this study is a basic research to predict and respond to thermal distortion during laser welding. Secondary version of the representative heat source model was derived through the author's previous research with STS304L, and the heat source model was derived by applying the heat source model to 9% nickel steel in this study. 9% nickel steel is a material that is in high demand and is widely used in the manufacture of cryogenic containers, so this study is expected to be able to respond immediately to the field.

In system design, it is not always possible that all decision makers can cooperate fully and thus avoid conflict. They each control a specified subset of design variables and seek to minimize their own cost functions subject to their individual constraints. However, a system management team makes every effort to coordinate multiple disciplines and overcome such noncooperative environment. Although full cooperation is difficult to achieve, noncooperation also should be avoided as possible. Our approach is to predict the results of their cooperation and generate approximate Pareto set for their multiple objectives. The Pareto set can be obtained according to the degree of one's conceding coupling variables in the other's favor. We employ approximation concept for modelling this coordination and the mutiobjective genetic algorithm for exploring the coupling variable space for obtaining an approximate Pareto set. The approximation management concept is also used for improving the accuracy of the Pareto set. The exploration for the coupling variable space is more efficient because of its smaller dimension than the design variable space. Also, our approach doesn't force the disciplines to change their own way of running analysis and synthesis tools. Since the decision making process is not sequential, the required time can be reduced comparing to the existing multidisciplinary design optimization. This approach is applied to some mathematical examples and structural optimization problems.