• Steel and Composite Structures
• /
• 제28권1호
• /
• pp.1-11
• /
• 2018

In this paper, local ratcheting behavior of 1045 steel plates with circular cutout was investigated. Experimental tests were carried out by a Zwick/Roell HB 100 servo hydraulic machine. In order to measure the local strain at notch root, a data acquisition system with strain gauge was used. Various notch diameters and distances of strain gauges mounted from the notch root were found influential in the magnitude of local ratcheting strain. It was found that the local maximum principal stress plays a crucial role in increasing the local plastic deformation. Numerical simulation was done by ABAQUS software using nonlinear isotropic/kinematic hardening model. Material parameters of hardening model were attained from several stabilized cycles of flat specimens subjected to symmetric strain cycles. The nonlinear kinematic hardening model along with the Neuber's rule was employed to assess local ratcheting at the notch root of steel plates. The results of the numerical simulations agreed closely with those measured values in this study. Both ratcheting progress and mean stress relaxation occurred simultaneously at the notch root.

• 한국공작기계학회논문집
• /
• 제10권5호
• /
• pp.118-123
• /
• 2001

Most structures of automobile are composed of many substructures connected to one another by various types of mechanical joints. In automotive engineering, it is important to study these connected structures under various dynamic farces for the evaluations of fatigue life and stress concentration exactly. It is rarely obtained the accurate load history of specified positions because of the errors such as modeling, measurement, and etc. In the beginning of design, exact load data are actually necessary for the fatigue strength and life analysis to minimize the cost and time of designing. In this paper, the procedure of practical dynamic load determination is developed by the combination of the principal stresses of F.E. analysis and experiment. Inverse problem and least square pseudo inverse matrix are adopted to obtain an inverse matrix of analyzed stresses matrix. Pseudo-Practical dynamic load was calculated for Lab. Test of sub-structure. GUI program(PLODAS) was developed for whole of above procedure. This proposed method could be extended to any geometric shape of structure.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2002년도 추계학술대회 논문집
• /
• pp.192-197
• /
• 2002

In this study, examined the cutting characteristics of alumuminum alloy AC8A-T6 that is used to present car piston materials. And in been holding materials machining empirically escape as result that experiment comparison changing the cutting speed and feed on various condition to choose efficient machining condition. The following results can be summarized from this research. 1. As the cutting speed decreased, principal cutting force and thrust cutting force is increased, and reason that cutting force interacts greatly in the low cutting speed is thought by result by BUE's stabilization. 2. The feed speed and cutting speed increase, friction factor is decrescent and the cause appeared the thrust cutting force is fallen than cutting force relatively because chip flow according to increase of the feed rate is constraint. 3. Though specific cutting resistance grows cutting area and the feed rate are few, the cause was expose that shear angle decreases by rake face of tool gets into negative angle remarkably as wear of a cutting tool or defect part of workpiece is cut. 4. Cutting speed do greatly depth of cut is slow, surface roughness examined closely through an experiment that becomes bad, and know that it can get good surface that process cutting speed because do feed rate by 0.1mm/rev low more than 250m/min to get good surface roughness can.

• Journal of Electrical Engineering and Technology
• /
• 제13권4호
• /
• pp.1614-1622
• /
• 2018

The research related to fault diagnosis in permanent magnet synchronous motors (PMSMs) has attracted considerable attention in recent years because various faults such as permanent magnet demagnetization and short-circuited turns can occur and result in unexpected failure of motor related system. Several conventional current and back electromotive force (BEMF) analysis techniques were proposed to detect certain faults in PMSMs; however, they generally deal with a single fault only. On the contrary, cases of multiple faults are common in PMSMs. We propose a fault diagnosis method for PMSMs with single and multiple combined faults. Our method uses three phase BEMF voltages based on the fast Fourier transform (FFT), support vector machine(SVM), and visualization tools for identifying fault types and severities in PMSMs. Principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) are used to visualize the high-dimensional data into two-dimensional space. Experimental results show good visualization performance and high classification accuracy to identify fault types and severities for single and multiple faults in PMSMs.

• Journal of Information Processing Systems
• /
• 제14권4호
• /
• pp.892-903
• /
• 2018

The paper proposes a novel gait recognition algorithm based on feature fusion of gait energy image (GEI) dynamic region and Gabor, which consists of four steps. First, the gait contour images are extracted through the object detection, binarization and morphological process. Secondly, features of GEI at different angles and Gabor features with multiple orientations are extracted from the dynamic part of GEI, respectively. Then averaging method is adopted to fuse features of GEI dynamic region with features of Gabor wavelets on feature layer and the feature space dimension is reduced by an improved Kernel Principal Component Analysis (KPCA). Finally, the vectors of feature fusion are input into the support vector machine (SVM) based on multi classification to realize the classification and recognition of gait. The primary contributions of the paper are: a novel gait recognition algorithm based on based on feature fusion of GEI and Gabor is proposed; an improved KPCA method is used to reduce the feature matrix dimension; a SVM is employed to identify the gait sequences. The experimental results suggest that the proposed algorithm yields over 90% of correct classification rate, which testify that the method can identify better different human gait and get better recognized effect than other existing algorithms.

• Journal of Information Science Theory and Practice
• /
• 제9권4호
• /
• pp.1-14
• /
• 2021

Library communities face many problems and limitations in describing alternative format materials based on the traditional MAchine Readable Cataloging (MARC) structure. To address these problems, this research proposes an XML-based descriptive metadata framework that establishes general but fundamental bibliographic aspects of various alternative format materials by providing core elements that are essential in describing these materials. Different from existing bibliographic structures, the proposed metadata framework can represent a fundamental descriptive structure by establishing four upper-level categories, 17 core elements, and 10 sub-elements in a hierarchical structure optimized to alternative format materials. By using this principal descriptive structure, the proposed metadata framework can guide different institutions in the creation of bibliographic records for these materials in a consistent way. It is also expected to address the difficulties in describing alternative format materials in library communities and enhance the information accessibility of individuals with various types of disabilities. In addition, the proposed metadata framework is an alternative approach which functions as a mediator between heterogeneous characteristics of alternative format materials and the existing bibliographic structures in library communities.

• 반도체디스플레이기술학회지
• /
• 제18권1호
• /
• pp.112-116
• /
• 2019

This study was carried out by structural analysis using finite element method for designing high rigidity structure of multi - functional automatic lathe bed. As a result of comparison, it was confirmed that the weight was designed to be higher than the maximum deformation amount. The shape and dimensions of the main pillars and walls of the bed were changed to derive the most suitable design for the multifunction automatic lathe bed. A model of structural design was derived with the goal of minimizing the maximum deformation amount of $20{\mu}m$ or less and the weight of the bed. As a result of applying the derived design improvement proposal to the multifunctional automatic lathe bed, 57.4% weight reduction and maximum principal stress decreased by 45.0% than the initial design model. It is expected that the optimum design that meets these design conditions will reduce the weight of the structure as well as improve the safety of the structure and reduce the machining error in the operation of the machine tool.

• 한국전자통신학회논문지
• /
• 제17권4호
• /
• pp.703-708
• /
• 2022

k-평균 군집화는 대표적인 클러스터링 기법이다. 하지만 성능 평가 척도와 최소 개수의 군집을 정하는 방법에 대하여 통합하지 못한 한계가 있다. 본 논문에서는 수치적으로 최소 개수의 군집을 정하는 방법을 도입한다. 설명된 분산을 통합측도로 제시한다. 최소 개수의 군집과 설명된 분산 달성을 동시에 만족하려면 주성분 해석의 부공간에서 k-평균 군집화 방법을 수행해야한다는 것을 제시하고자 한다. 패턴인식과 기계학습에서 왜 주성분 분석과 k-평균 군집화를 순차적으로 수행하는가에 대한 설명을 원론적으로 제시한다.

• Structural Monitoring and Maintenance
• /
• 제9권2호
• /
• pp.179-200
• /
• 2022

This paper proposes a data-driven methodology for online early damage identification under changing environmental conditions. The proposed method relies on two data analysis methods: feature-based method and hybrid principal component analysis (PCA) and kernel PCA to separate damage from environmental influences. First, spectral sub-band features, namely, spectral sub-band centroids (SSCs) and log spectral sub-band energies (LSSEs), are proposed as damage-sensitive features to extract damage information from measured structural responses. Second, hybrid modeling by integrating PCA and kernel PCA is performed on the spectral sub-band feature matrix for data normalization to extract both linear and nonlinear features for nonlinear procedure monitoring. After feature normalization, suppressing environmental effects, the control charts (Hotelling T² and SPE statistics) is implemented to novelty detection and distinguish damage in structures. The hybrid PCA-KPCA technique is compared to KPCA by applying support vector machine (SVM) to evaluate the effectiveness of its performance in detecting damage. The proposed method is verified through numerical and full-scale studies (a Bridge Health Monitoring (BHM) Benchmark Problem and a cable-stayed bridge in China). The results demonstrate that the proposed method can detect the structural damage accurately and reduce false alarms by suppressing the effects and interference of environmental variations.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권2호
• /
• pp.59-76
• /
• 2023

코로나 시대 이후 아파트 가격 상승은 비상식적이었다. 이러한 불확실한 부동산 시장에서 가격 예측 연구는 매우 중요하다. 본 논문에서는 다양한 부동산 사이트에서 자료 수집 및 크롤링을 통해 2015년부터 2020년까지 87만개의 방대한 데이터셋을 구축하고 다양한 아파트 정보와 경제지표 등 가능한 많은 변수를 모은 뒤 미래 아파트 매매실거래가격을 예측하는 모델을 만든다. 해당 연구는 먼저 다중 공선성 문제를 변수 제거 및 결합으로 해결하였다. 이후 의미있는 독립변수들을 뽑아내는 전진선택법(Forward Selection), 후진소거법(Backward Elimination), 단계적선택법(Stepwise Selection), L1 Regularization, 주성분분석(PCA) 총 5개의 변수 선택 알고리즘을 사용했다. 또한 심층신경망(DNN), XGBoost, CatBoost, Linear Regression 총 4개의 머신러닝 및 딥러닝 알고리즘을 이용해 하이퍼파라미터 최적화 후 모델을 학습시키고 모형간 예측력을 비교하였다. 추가 실험에서는 DNN의 node와 layer 수를 바꿔가면서 실험을 진행하여 가장 적절한 node와 layer 수를 찾고자 하였다. 결론적으로 가장 성능이 우수한 모델로 2021년의 아파트 매매실거래가격을 예측한 후 실제 2021년 데이터와 비교한 결과 훌륭한 성과를 보였다. 이를 통해 머신러닝과 딥러닝은 다양한 경제 상황 속에서 투자자들이 주택을 구매할 때 올바른 판단을 할 수 있도록 도움을 줄 수 있을 것이라 확신한다.