• 한국기계가공학회지
• /
• 제11권6호
• /
• pp.69-74
• /
• 2012

Surface roughness is widely used as an index for processing degree of accuracy. Recently, regression analysis to predict the machining results are actively used to characterize a cutting operations. In the past, diamond machining had been used for ultra precision cutting operation, but now industrial diamond tools like PCD(Polycrystalline Diamond) have been widely used in ultraprecision machining of nonferrous metals. In this study, the authors focus on the effect of PCD tool property on the surface roughness of Al5083 aluminum alloy after cutting process by CNC operated lathe. Based on the regression analysis approach on a surface roughness data obtained by experiment, predictive analysis of surface roughness is effective to achieve better surface quality.

• 한국컴퓨터정보학회논문지
• /
• 제23권4호
• /
• pp.17-24
• /
• 2018

This paper proposes data mining models relevant to the serial publication periods and mobile gamification likelihood of webtoon contents which were either serialized or completed in platform. The size of the cartoon industry including webtoon takes merely 1% of the total entertainment contents industry in Korea. However, the significance of webtoon business is rapidly growing because its intellectual property can be easily used as an effective OSMU (One Source Multi-Use) vehicle for multiple types of contents such as movie, drama, game, and character-related merchandising. We suggested a set of data mining classifiers that are deemed suitable to provide prediction models for serial publication periods and mobile gamification likelihood for the sake of webtoon contents. As a result, the balanced accuracies are respectively recorded as 85.0% and 59.0%, from the two models.

• Structural Engineering and Mechanics
• /
• 제46권4호
• /
• pp.447-458
• /
• 2013

Splitting tensile strength (STS) is a respectable mechanical property reflecting ability of the concrete. The STS of concrete is mainly related to compressive strength (CS), water/binder (W/B) ratio and concrete age. In this study, the assessment of STS is made by a novel uncertainty-oriented method which uses least square optimization and then predicts STS of concrete by uncertain (fuzzy) numbers. The approximation method addresses a novel integration of fuzzy set theory and multivariate statistics. The numerical examples showed that the method is applicable with relatively limited data. In addition, the prediction of uncertainty at various levels of possibility can be described. In conclusion, the uncertainty-oriented interval analysis can be suggested an effective tool for appraising the uncertainties in concrete technology.

• International journal of advanced smart convergence
• /
• 제11권1호
• /
• pp.19-27
• /
• 2022

Across the world, 'housing' comprises a significant portion of wealth and assets. For this reason, fluctuations in real estate prices are highly sensitive issues to individual households. In Korea, housing prices have steadily increased over the years, and thus many Koreans view the real estate market as an effective channel for their investments. However, if one purchases a real estate property for the purpose of investing, then there are several risks involved when prices begin to fluctuate. The purpose of this study is to design a real estate price 'return rate' prediction model to help mitigate the risks involved with real estate investments and promote reasonable real estate purchases. Various approaches are explored to develop a model capable of predicting real estate prices based on an understanding of the immovability of the real estate market. This study employs the LSTM method, which is based on artificial intelligence and deep learning, to predict real estate prices and validate the model. LSTM networks are based on recurrent neural networks (RNN) but add cell states (which act as a type of conveyer belt) to the hidden states. LSTM networks are able to obtain cell states and hidden states in a recursive manner. Data on the actual trading prices of apartments in autonomous districts between January 2006 and December 2019 are collected from the Actual Trading Price Disclosure System of the Ministry of Land, Infrastructure and Transport (MOLIT). Additionally, basic data on apartments and commercial buildings are collected from the Public Data Portal and Seoul Metropolitan Government's data portal. The collected actual trading price data are scaled to monthly average trading amounts, and each data entry is pre-processed according to address to produce 168 data entries. An LSTM model for return rate prediction is prepared based on a time series dataset where the training period is set as April 2015~August 2017 (29 months), the validation period is set as September 2017~September 2018 (13 months), and the test period is set as December 2018~December 2019 (13 months). The results of the return rate prediction study are as follows. First, the model achieved a prediction similarity level of almost 76%. After collecting time series data and preparing the final prediction model, it was confirmed that 76% of models could be achieved. All in all, the results demonstrate the reliability of the LSTM-based model for return rate prediction.

• 한국지리정보학회지
• /
• 제20권3호
• /
• pp.52-66
• /
• 2017

본 연구는 풍수해 피해예측지도 활용 고도화에 필요한 표준 메타데이터를 시범 설계하고, 이를 기반으로 표준메타정보관리 프로토타입 시스템 구축을 목적으로 하였다. 이를 위해, 국내 외 메타데이터 표준 현황 조사를 통해 가장 활용도가 높은 것으로 분석된 ISO/TC211 19115 국제표준을 기반으로 표준 메타데이터 설계 방향을 설정하였으며, 식별정보, 기준계정보, 배포정보 등 9개의 클래스로 구분하여 메타데이터를 시범 설계하였다. 또한, 본 연구에서 설계한 표준 메타데이터를 바탕으로 메타속성정보를 확인 및 다운로드할 수 있는 표준메타정보관리 프로토타입 시스템을 HTML 기반 JAVASCRIPT 언어로 구축하였다. 본 연구결과를 활용한다면, 표준화된 통합 풍수해 피해예측지도 데이터베이스 구축을 통해 향후 구축되는 피해예측지도의 품질유지가 가능해지며, 풍수해 피해예측 시스템 운영에 필요한 데이터 관리 및 제공 등을 통해 효율적인 재난대응에 활용가능할 것으로 사료된다.

• 한국정보통신학회논문지
• /
• 제10권1호
• /
• pp.171-175
• /
• 2006

본 논문에서는 2 GHz LS 대역에서 동작하는 역지향성 능동배열 안테나가 설계 제작되었다. 역지향성 안테나는 임의의 방향에서 입사하는 전파를 그 방향으로 되돌려 복사시키는 안테나 배열 시스템으로서, 반사파가 입사 반대 방향으로 파면(wave front)을 갖도록 하기 위한 공액 위상변위기가 포함된 능동 안테나 배열로 구성된다. 본 연구에서는 RF/IF 신호포트와 LO 포트로 이루어진 2-포트 게이트 HEMT 혼합기와 1/4파장 모노폴 안테나 배열($1{\times}4$)을 사용하여 역지향성 능동배열 안테나를 구현하였다. 제작된 배열 안테나의 역지향 특성을 실험 측정하고, 이론적 예측치와 비교하여 잘 일치함을 확인하였다. 모노폴 안테나 배열은 구조가 간단하여 제작이 용이한 장점을 가지며, 본 연구결과는 무선 이동통신, 무선 실내 LAN 및 RFID등의 기지국 및 트랜스폰더 장치에 직접 적용 가능하다.

• 한국추진공학회:학술대회논문집
• /
• 한국추진공학회 2006년도 제26회 춘계학술대회논문집
• /
• pp.118-122
• /
• 2006

액체 로켓 엔진용 가스발생기 개발을 위해서는 추진제 혼합비에 따른 연소 가스의 열역학적 물성치 예측이 필수적이다. 본 연구에서는 Lox/Jet A-1 조합의 연료 과농 가스발생기의 실 추진제 연소 시험을 통해 전체 혼합비에 따른 연소 가스의 생성 온도를 계측하였다. 연소실 내 동압 섭동 측정 및 정압 측정 결과를 이용하여 비열비, 가스 상수, 정압 비열과 같은 물성치를 간접적으로 산출해내었다. 본 실험값은 보간 계수를 이용한 예측 결과와 비교해보았을 때 동일한 대표 값을 가지는 것으로 나타나, 보간 계수 예측 방법이 설계 도구로 충분히 적용 가능하다는 것을 확인하였다.

• Structural Engineering and Mechanics
• /
• 제81권6호
• /
• pp.665-675
• /
• 2022

The safety problems of giant hydraulic structures such as dams caused by terrorist attacks, earthquakes, and wars often have an important impact on a country's economy and people's livelihood. For the national defense department, timely and effective assessment of damage to or impending damage to dams and other structures is an important issue related to the safety of people's lives and property. In the field of damage assessment and vulnerability analysis, it is usually necessary to give the damage assessment results within a few minutes to determine the physical damage (crack length, crater size, etc.) and functional damage (decreased power generation capacity, dam stability descent, etc.), so that other defense and security departments can take corresponding measures to control potential other hazards. Although traditional numerical calculation methods can accurately calculate the crack length and crater size under certain combat conditions, it usually takes a long time and is not suitable for rapid damage assessment. In order to solve similar problems, this article combines simulation calculation methods with machine learning technology interdisciplinary. First, the common concrete gravity dam shape was selected as the simulation calculation object, and XFEM (Extended Finite Element Method) was used to simulate and calculate 19 cracks with different initial positions. Then, an LSTM (Long-Short Term Memory) machine learning model was established. 15 crack paths were selected as the training set and others were set for test. At last, the LSTM model was trained by the training set, and the prediction results on the crack path were compared with the test set. The results show that this method can be used to predict the crack propagation path rapidly and accurately. In general, this article explores the application of machine learning related technologies in the field of mechanics. It has broad application prospects in the fields of damage assessment and vulnerability analysis.

• Steel and Composite Structures
• /
• 제14권3호
• /
• pp.295-312
• /
• 2013

In this paper, a simplified approach based on critical temperature for fire resistance design of steel-concrete composite beams is proposed. The method for determining the critical temperature and fire protection of the composite beams is developed on the basis of load-bearing limit state method employed in current Chinese Technical Code for Fire safety of Steel Structure in Buildings. Parameters affecting the critical temperature of the composite beams are analysed. The results show that at a definite load level, section shape of steel beams, material properties, effective width of concrete slab and concrete property model have little influence on the critical temperature of composite beams. However, the fire duration and depth of concrete slab have significant influence on the critical temperature. The critical temperatures for commonly used composite beams, at various depth of concrete and fire duration, are given to provide a reference for engineers. The validity of the practical approach for predicting the critical temperature of the composite beams is conducted by comparing the prediction of a composite beam with the results from some fire design codes and full scale fire resistance tests on the composite beam.

• 한국복합재료학회:학술대회논문집
• /
• 한국복합재료학회 2002년도 추계학술발표대회 논문집
• /
• pp.100-105
• /
• 2002

This paper predicts the material properties of spatially reinforced composites (SRC) and analyzes the thermo-elastic behavior of a kick motor nozzle manufactured from that material. To find the appropriate SRC structure for the nozzle throat that satisfies given design conditions, the equivalent material properties of the SRC are predicted using the superposition method for those of rod and matrix. Studied are the elastic behavior, temperature distribution, and thermo-elastic behavior of a kick motor nozzle composed of carbon/carbon SRC as a throat part. The elastic deformation of the nozzle composed of 3D carbon/carbon SRC shows asymmetry in a circumferential direction. However, 4D carbon/carbon SRC nozzle shows uniform deformation in the circumferential direction. Stress concentration in connecting parts of the kick motor nozzle is ultimately high due to the high temperature gradient in each connecting part. The thermo-elastic deformations of both the 3D and the 4D SRC nozzles are uniform in the circumferential direction due to the isotropy of CTE of each SRC. The deformation of the 3D SRC nozzle is a slightly smaller than that of the 4D SRC nozzle in the nozzle throat, which is favorably effective on rocket thrust. The circumferential stress is the most critical component of the kick motor nozzle. The 4D SRC nozzle having 1,1,1,1.7 diameters in each direction has the smallest circumferential stress among several SRC nozzles.