• Construction Engineering and Management
• /
• v.22 no.2
• /
• pp.17-20
• /
• 2021

• KIEAE Journal
• /
• v.13 no.4
• /
• pp.49-54
• /
• 2013

released by IEA, 2010, indicated that Korea's GDP, of 8 countries surveyed-Korea, Frans, Germany, Italy, Japan, the UK, the USA, and Australia-was the lowest, but the electric consumption per head was third, following America and Australia. Thus, our government has been striving to reduce energy usage and especially to lessen the energy used in buildings, proposing a variety of road maps such as 'building energy efficiency rating' and 'energy saving design standards of buildings'. Accordingly, this study investigated the effect of the items of machine part among EPI items on the energy saving rate. I measured energy usage by ECO2 program, for simulation program, that is used for the building energy efficiency rating. Result showed that items concerning control of pumps and fans had much more saving rate than the ones concerning efficiency of heater and cooler that had bigger scores assigned among EPI items. Result showed that items concerning control of pumps and fans had much more saving rate than the ones concerning efficiency of heater and cooler that had bigger scores assigned among EPI items. Therefore, I think that grades assigned to items in energy performance index need to be corrected.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.129-136
• /
• 2022

The most important part of the smart livestock building system is to maintain a breeding environment so that livestock can grow to high quality despite changes in the internal and external atmospheric environment. Especially, it is very important to maintain the temperature and humidity in the livestock building because various diseases occur during the summer and winter. To manage the environment suitable for livestock, a smartfarm system for livestock building is applied, but it is very expensive. In this study, we propose a hardware design and control method for low cost system based on HMI and fuzzy control. To evaluate the performance of the proposed system, we did a simulation experiment in the atmospheric conditions of summer and winter. As a result, it showed the performance of minimizing the temperature and humidity stress of livestock. And when applied to the livestock building, the proposed system showed stable control performance even in the change of the external atmospheric environment. Therefore, as with these results, if proposed system in this study is applied to the smart farm system, it will be effective in managing the environment of livestock building.

• Smart Structures and Systems
• /
• v.24 no.6
• /
• pp.733-744
• /
• 2019

Wind speed forecasting is critical for a variety of engineering tasks, such as wind energy harvesting, scheduling of a wind power system, and dynamic control of structures (e.g., wind turbine, bridge, and building). Wind speed, which has characteristics of random, nonlinear and uncertainty, is difficult to forecast. Nowadays, machine learning approaches (generalized regression neural network (GRNN), back propagation neural network (BPNN), and extreme learning machine (ELM)) are widely used for wind speed forecasting. In this study, two schemes are proposed to improve the forecasting performance of machine learning approaches. One is that optimization algorithms, i.e., cross validation (CV), genetic algorithm (GA), and particle swarm optimization (PSO), are used to automatically find the optimal model parameters. The other is that the combination of different machine learning methods is proposed by finite mixture (FM) method. Specifically, CV-GRNN, GA-BPNN, PSO-ELM belong to optimization algorithm-assisted machine learning approaches, and FM is a hybrid machine learning approach consisting of GRNN, BPNN, and ELM. The effectiveness of these machine learning methods in wind speed forecasting are fully investigated by one-year field monitoring data, and their performance is comprehensively compared.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.29-34
• /
• 2023

The flow from developing a machine learning model to deploying it in a production environment suffers challenges. Efficient and reliable deployment is critical for realizing the true value of machine learning models. Bridging this gap between development and publication has become a pivotal concern in the machine learning community. FastAPI, a modern and fast web framework for building APIs with Python, has gained substantial popularity for its speed, ease of use, and asynchronous capabilities. This paper focused on leveraging FastAPI for deploying machine learning models, addressing the potentials associated with integration, scalability, and performance in a production setting. In this work, we explored the seamless integration of machine learning models into FastAPI applications, enabling real-time predictions and showing a possibility of scaling up for a more diverse range of use cases. We discussed the intricacies of integrating popular machine learning frameworks with FastAPI, ensuring smooth interactions between data processing, model inference, and API responses. This study focused on elucidating the integration of machine learning models into production environments using FastAPI, exploring its capabilities, features, and best practices. We delved into the potential of FastAPI in providing a robust and efficient solution for deploying machine learning systems, handling real-time predictions, managing input/output data, and ensuring optimal performance and reliability.

• Earthquakes and Structures
• /
• v.16 no.6
• /
• pp.679-690
• /
• 2019

This paper presents machine learning methods using Support Vector Machine (SVM) and Multilayer Perceptron (MLP) to analyze optimal damper distribution for structural vibration control. Regarding different building structures, a genetic algorithm based optimization method is used to determine optimal damper distributions that are further used as training samples. The structural features, the objective function, the number of dampers, etc. are used as input features, and the distribution of dampers is taken as an output result. In the case of a few number of damper distributions, multi-class prediction can be performed using SVM and MLP respectively. Moreover, MLP can be used for regression prediction in the case where the distribution scheme is uncountable. After suitable post-processing, good results can be obtained. Numerical results show that the proposed method can obtain the optimized damper distributions for different structures under different objective functions, which achieves better control effect than the traditional uniform distribution and greatly improves the optimization efficiency.

• Journal of the Korean Society for Precision Engineering
• /
• v.34 no.1
• /
• pp.35-39
• /
• 2017

We used a construction method using a CNC milling machine, where free-formed molds were made by cutting EPS (Expanded PolyStyrene) foam with the CNC machine, to build free-formed buildings. CNC milling is off-the-shelf technology that can easily cut EPS foam; however its production cost is too high and the time to manufacture an EPS mold is too long. This paper proposes a novel cutting machine with a fast and cost effective mechanism to manufacture EPS concrete molds. Our machine comprises a cutter and Cartesian coordinate type moving mechanism, where the cutter cuts EPS foam using a hotwire in the shape of '$\sqcap$' and is capable of adjusting its cutting angle in real-time while keeping its cutting width. We proved through cutting experiments on the CNC machine that cutting time was greatly shortened compared to the conventional method and that the resulting concrete mold satisfied manufacturing precision.

• KIEAE Journal
• /
• v.15 no.1
• /
• pp.13-20
• /
• 2015

The main purpose of the green buildings by reducing energy consumption and carbon footprint of the building society, global as to ensure the sustainability of the building and the environment. These regulations and schemes are used to activate the green buildings were made on the basis of the relevant laws and regulations. Mainly in the research for the improvement of the domestic institutional assessment items, the analysis of the legislation was fundamentally focused on Scoring the incomplete state. The analysis based on the laws and regulations of the institution is the way to know the purpose and direction of the respective certification. This study was performed in the following order to target the new commercial buildings. First, the analysis of the geungeobeop G-SEED and BREEAM. Second, we analyze the content and method of building energy performance in the certification system. As a result, Green Building Act is broad in relation to the composition of the contents are building for the activation energy green building and EPI is dealt with in an abstract and presented the applicability of such documentary content of insulation and airtightness, efficient machine. In contrast, the UK has been directly limit the carbon footprint of buildings in the Building Regulations Part L and evaluate them in BREEAM. This analysis of the ways to reduce substantially the energy for domestic green building regulations should be addressed through the feed.

• Journal of the Korea Institute of Building Construction
• /
• v.11 no.3
• /
• pp.238-246
• /
• 2011

Choosing the best-performance materials is a crucial task for the successful completion of a project in the construction field. In general, the process of material selection is performed through the use of information by a highly experienced expert and the purchasing agent, without the assistance of logical decision-making techniques. For this reason, the construction field has considered various artificial intelligence (AI) techniques to support decision systems as their own selection method. This study proposes the application of a systematic and efficient support vector machine (SVM) model to select optimal exterior materials. The dataset of the study is 120 completed construction projects in South Korea. A total of 8 input determinants were identified and verified from the literature review and interviews with experts. Using data classification and normalization, these 120 sets were divided into 3 groups, and then 5 binary classification models were constructed in a one-against-all (OAA) multi classification method. The SVM model, based on the kernel radical basis function, yielded a prediction accuracy rate of 87.5%. This study indicates that the SVM model appears to be feasible as a decision support system for selecting an optimal construction method.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2008.05a
• /
• pp.209-213
• /
• 2008

Recently, it increases in use of CFT(Concrete filled steel tube, below CFT) because material and method are required to be diversification and High-Performance according to increase the super-high structure. But, CFT column lose bearing capacity under fire because steel tube is exposed to outside. As a result, structure is collapsed and then it cause much damage. In case of the Europe, Japan and America, they have studied the fire-resistance performance of CFT under fire for a long time. However, it would have hardly studied it in domestic because it is much difficulty about experiment machine and cost. So it is needed base on fire-resist performance of CFT under fire. Therefore, this study dynamic specificity of stub column which made tester of stub column based on facts of strength and mixing fiber evaluated used heating and load testing machine. As a result, it is willing to propose fundamental data for quick and accurate diagnosis of deteriorated concrete structure by fire damage with experiment according to the design high strength concrete.