• 품질경영학회지
• /
• 제50권4호
• /
• pp.701-716
• /
• 2022

Purpose: This study aims to predict the dry cargo transportation market economy. The subject of this study is the BDI (Baltic Dry Index) time-series, an index representing the dry cargo transport market. Methods: In order to increase the accuracy of the BDI time-series, we have pre-processed the original time-series via time-series decomposition and data augmentation techniques and have used them for ANN learning. The ANN algorithms used are Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) to compare and analyze the case of learning and predicting by applying time-series decomposition and data augmentation techniques. The forecast period aims to make short-term predictions at the time of t+1. The period to be studied is from '22. 01. 07 to '22. 08. 26. Results: Only for the case of the MAPE (Mean Absolute Percentage Error) indicator, all ANN models used in the research has resulted in higher accuracy (1.422% on average) in multivariate prediction. Although it is not a remarkable improvement in prediction accuracy compared to uni-variate prediction results, it can be said that the improvement in ANN prediction performance has been achieved by utilizing time-series decomposition and data augmentation techniques that were significant and targeted throughout this study. Conclusion: Nevertheless, due to the nature of ANN, additional performance improvements can be expected according to the adjustment of the hyper-parameter. Therefore, it is necessary to try various applications of multiple learning algorithms and ANN optimization techniques. Such an approach would help solve problems with a small number of available data, such as the rapidly changing business environment or the current shipping market.

• Nuclear Engineering and Technology
• /
• 제54권5호
• /
• pp.1825-1834
• /
• 2022

Performing high-fidelity computational fluid dynamics (HF-CFD) to predict the flow and heat transfer state of the coolant in the reactor core is expensive, especially in scenarios that require extensive parameter search, such as uncertainty analysis and design optimization. This work investigated the performance of utilizing a multi-fidelity reduced-order model (MF-ROM) in PWR rod bundles simulation. Firstly, basis vectors and basis vector coefficients of high-fidelity and low-fidelity CFD results are extracted separately by the proper orthogonal decomposition (POD) approach. Secondly, a surrogate model is trained to map the relationship between the extracted coefficients from different fidelity results. In the prediction stage, the coefficients of the low-fidelity data under the new operating conditions are extracted by using the obtained POD basis vectors. Then, the trained surrogate model uses the low-fidelity coefficients to regress the high-fidelity coefficients. The predicted high-fidelity data is reconstructed from the product of extracted basis vectors and the regression coefficients. The effectiveness of the MF-ROM is evaluated on a flow and heat transfer problem in PWR fuel rod bundles. Two data-driven algorithms, the Kriging and artificial neural network (ANN), are trained as surrogate models for the MF-ROM to reconstruct the complex flow and heat transfer field downstream of the mixing vanes. The results show good agreements between the data reconstructed with the trained MF-ROM and the high-fidelity CFD simulation result, while the former only requires to taken the computational burden of low-fidelity simulation. The results also show that the performance of the ANN model is slightly better than the Kriging model when using a high number of POD basis vectors for regression. Moreover, the result presented in this paper demonstrates the suitability of the proposed MF-ROM for high-fidelity fixed value initialization to accelerate complex simulation.

• 실천공학교육논문지
• /
• 제14권2호
• /
• pp.305-312
• /
• 2022

본 논문에서는 기초적인 데이터 예측 모델을 만들고 최적화하는 교육에 초점을 맞추었다. 그리고 데이터 예측 모델을 최적화하는 데 널리 사용되는 머신러닝의 경사하강법 교육 방법을 제안하였다. 미분법을 적용하여 데이터 예측 모델에 필요한 파라미터 값들을 최적화하는 과정에 사용되는 경사하강법의 전체 동작과정을 시각적으로 보여주며, 수학의 미분법이 머신러닝에 효과적으로 사용되는 것을 교육한다. 경사하강법의 전체 동작과정을 시각적으로 설명하기위해, 스프레드시트로 경사하강법 SW를 구현한다. 본 논문에서는 첫번째로, 2변수 경사하강법 교육 방법을 제시하고, 오차 최소제곱법과 비교하여 2변수 데이터 예측모델의 정확도를 검증한다. 두번째로, 3변수 경사하강법 교육 방법을 제시하고, 3변수 데이터 예측모델의 정확도를 검증한다. 이후, 경사하강법 최적화 실습 방향을 제시하고, 비전공자 교육 만족도 결과를 통해, 제안한 경사하강법 교육방법이 갖는 교육 효과를 분석하였다.

• 한국구조물진단유지관리공학회 논문집
• /
• 제27권1호
• /
• pp.30-36
• /
• 2023

이 연구에서는 콘크리트 표면 이미지를 활용하여 표면공극률을 평가할 수 있는 영상 분할모델을 도출하였다. 물-시멘트비가 다른 3종류의 콘크리트 실험체 (w/c = 54, 35, 및 30%) 가 제작되었으며, 광학현미경을 활용하여 2,729장의 표면 이미지를 취득하였다. 공극이 마스킹 된 표면 이미지 를 활용하여 벤치마킹 테스트, 매개변수 최적화, 최종모델 도출이 실시되었으며, 97%의 검증정확도를 나타내는 영상 분할 모델을 도출할 수 있었다. 영상 분할모델 및 X-Ray Microscope (XRM)을 통해 얻은 공극률을 비교하여 모델을 검증하였으며, 물시멘트비가 높은 시편에 대해선 모델과 XRM이 평가한 공극률이 유사하였고, 물시멘트비가 낮은 시편에 대해서는 모델이 XRM보다 공극률을 낮게 평가하는 경향을 나타내었다.

• Composites Research
• /
• 제36권1호
• /
• pp.59-67
• /
• 2023

항공우주산업에서 경량화를 위해 사용되는 CFRP 복합재료로 구성된 차체의 충격에 따른 파손은 탑승자의 안전과 직결된다. 따라서 충돌 상황에서 육안으로 확인하기 힘든 재료의 손상거동을 파악하는 것이 중요하며, 이를 구현할 수 있는 유한요소모델을 통한 연구가 필요하다. 본 연구에서는 일방향 적층 복합재료의 충돌 해석에 대해 파손 거동 예측에 적합한 유한요소모델을 구축하였다. 인공신경망 모델을 통해 LS-DYNA에서 제공하는 MAT_54 Enhanced Composite Damage 재료 모델의 교정 파라미터를 역추정하여 획득하였다. 획득한 파라미터에 대한 인공신경망 모델의 결과를 실험결과와 비교하여 신뢰성을 검증하였다. 그 결과, 교정 파라미터의 최적화를 통해 실험에 대한 정확도를 향상시킨 유한요소모델을 구축할 수 있음을 확인하였다.

• 한국분말재료학회지
• /
• 제29권6호
• /
• pp.459-467
• /
• 2022

Soft magnetic powder materials are used throughout industries such as motors and power converters. When manufacturing Fe-based soft magnetic composites, the size and shape of the soft magnetic powder and the microstructure in the powder are closely related to the magnetic properties. In this study, Fe-Si-Al-P alloy powders were manufactured using various manufacturing process parameter sets, and the process parameters of the vacuum induction melt gas atomization process were set as melt temperature, atomization gas pressure, and gas flow rate. Process variable data that records are converted into 6 types of data for each powder recovery section. Process variable data that recorded minute changes were converted into 6 types of data and used as input variables. As output variables, a total of 6 types were designated by measuring the particle size, flowability, apparent density, and sphericity of the manufactured powders according to the process variable conditions. The sensitivity of the input and output variables was analyzed through the Pearson correlation coefficient, and a total of 6 powder characteristics were analyzed by artificial neural network model. The prediction results were compared with the results through linear regression analysis and response surface methodology, respectively.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권6호
• /
• pp.251-258
• /
• 2023

안정적으로 전력을 공급하고 전력계통을 운영하기 위해서는 최대전력을 정확히 예측해야 한다. 특히, 최대전력이 높게 발생하는 겨울과 여름에는 그 중요성이 매우 커진다. 최대전력을 실제 수요보다 높게 예측하면 발전소 기동 비용이 증가하여 경제적 손실이 발생하고, 최대전력을 실제 수요보다 낮게 예측하면 기동이 가능한 발전소가 부족하여 정전이 발생할 수 있다. 최대전력의 예측 오차를 최소화함으로써 경제적 손실과 정전을 예방할 수 있다. 본 논문에서는 최대전력 예측의 오차를 최소화하기 위하여 최신 딥러닝 모델인 TCN을 이용한다. 딥러닝 모델은 하이퍼 파라미터를 어떻게 설정하느냐에 따라 성능 차이가 발생하므로, TCN의 하이퍼 파라미터를 최적화하는 방법을 제안한다. 2006년부터 2021년까지의 데이터를 입력하여 모델을 훈련하고, 2022년의 데이터를 이용하여 예측 오차를 실험하였다. 실험을 수행한 결과 본 논문에서 제안한 최적화 방법을 이용한 TCN 모델의 성능이 다른 딥러닝 모델보다 성능이 우수한 것을 확인하였다.

• 청정기술
• /
• 제29권1호
• /
• pp.53-58
• /
• 2023

This study shows the summary of the economic performance of excess electricity conversion to hydrogen as well as methane and returned conversion to electricity using a fuel cell. The methane production process has been examined in a previous study. Here, this study focuses on the conversion of methane to electricity. As a part of this study, capital expenditure (CAPEX) is estimated under various sized plants (0.3, 3, 9, and 30 MW). The study shows a method for economic optimization of electricity generation using a fuel cell. The CAPEX and operating expenditure (OPEX) as well as the feed cost are used to calculate the discounted cash flow. Then the levelized cost of returned electricity (LCORE) is estimated from the discounted cash flow. This study found the LCORE value was ¢10.2/kWh electricity when a 9 MW electricity generating fuel cell was used. A methane production plant size of 1,500 Nm³/hr, a methane production cost of $11.47/mcf, a storage cost of $1/mcf, and a fuel cell efficiency of 54% were used as a baseline. A sensitivity analysis was performed by varying the storage cost, fuel cell efficiency, and excess electricity cost by ±20%, and fuel cell efficiency was found as the most dominating parameter in terms of the LCORE sensitivity. Therefore, for the best cost-performance, fuel cell manufacturing and efficiency need to be carefully evaluated. This study provides a general guideline for cost performance comparison with LCORE.

• 사물인터넷융복합논문지
• /
• 제9권3호
• /
• pp.61-67
• /
• 2023

구리의 전기주조 공정을 최적화하기 위하여 이중 비밀 다층구조의 역전파 뉴럴 네트워크가 구성된다. 샘플 학습을 통하여, 구리 전기주조 공정 조건과 목표 특성 간의 함수관계가 정확히 성취되고, 구리 전기주조 공정 내에서 다층구조의 미세강도와 장력에 대한 예측이 이루어진다. 예측된 결과는 펄스 전원공급기를 장착한 구리 피로인산염 솔루션 시스템 내에서 구리의 전해석출 시험에 의하여 증명된다. 그 결과는 다음과 같이 나타난다. "3-4-3-2" 구조의 이중비밀 다층구조 뉴럴 네트워크에 의하여 예측된 구리 다층구조의 미세강도와 장력은 실험값에 매우 근접하며 그 상대적 오차는 2.32%보다 작다. 주어진 파라미터의 범위 내에서, 구리의 미세강도는 100.3~205.6MPa이며, 장력은 112~485MPa 정도로 측정된다. 미세강도와 장력이 최적인 조건에서 그에 대응하는 공정 조건은 다음과 같다: 전류밀도는 2A·dm-2, 펄스 주파수는 2KHz, 펄스의 듀티싸이클은 10%이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권7호
• /
• pp.1773-1793
• /
• 2023

Automated machine learning, often referred to as "AutoML," is the process of automating the time-consuming and iterative procedures that are associated with the building of machine learning models. There have been significant contributions in this area across a number of different stages of accomplishing a data-mining task, including model selection, hyper-parameter optimization, and preprocessing method selection. Among them, preprocessing method selection is a relatively new and fast growing research area. The current work is focused on the recommendation of preprocessing methods, i.e., feature subset selection (FSS) algorithms. One limitation in the existing studies regarding FSS algorithm recommendation is the use of a single learner for meta-modeling, which restricts its capabilities in the metamodeling. Moreover, the meta-modeling in the existing studies is typically based on a single group of data characterization measures (DCMs). Nonetheless, there are a number of complementary DCM groups, and their combination will allow them to leverage their diversity, resulting in improved meta-modeling. This study aims to address these limitations by proposing an architecture for preprocess method selection that uses ensemble learning for meta-modeling, namely AutoFE-Sel. To evaluate the proposed method, we performed an extensive experimental evaluation involving 8 FSS algorithms, 3 groups of DCMs, and 125 datasets. Results show that the proposed method achieves better performance compared to three baseline methods. The proposed architecture can also be easily extended to other preprocessing method selections, e.g., noise-filter selection and imbalance handling method selection.