• 응용통계연구
• /
• 제34권1호
• /
• pp.99-114
• /
• 2021

반도체 제조 산업에서는 Big Data에 기초한 Smart Factory 도입과 적용이 가시화되면서 생산 공정의 각 단계에서 수집 가능한 다양한 센서(sensor) 데이터를 활용하여 공정 이상 탐지 및 최종 수율 예측 등에 다양한 분석 방법을 시도하고 있다. 현재 반도체 공정은 원료인 잉곳(ingot)에서 패키징(packaging) 작업 이전의 웨이퍼(wafer) 생산까지 500 600개 이상의 세부 공정과 이와 연계된 수천 개의 계측 공정으로 구성된다. 개별 계측 공정 내의 실제 계측 비율은 대상 제품 대비 0.1%에서 최대 5%를 넘지 못하고 계측 시점별로 일정하게 유지할 수 없다. 이러한 이유로 공정 각 단계의 정상 상태를 간접적으로 판단할 수 있는 장비 센서(sensor) 데이터를 활용하여 관리 여부를 판단하고자 하는 노력이 계속되고 있다. 본 연구에서는 장비 센서 데이터 기반의 공정 이상 탐지 프로세스를 정의하고 현재 적용 되고 있는 기술 통계량 기반 진단 방법의 단점을 보완하기 위해 FDA(Functional Data Analysis)방법을 활용하였다. 실제 현장 사례 데이터에 머신러닝을 이용하여 이상 탐지 정확도 비교를 통해 효과성을 검증하였다.

• 한국음향학회지
• /
• 제40권1호
• /
• pp.92-98
• /
• 2021

발전소의 실내는 규모가 크고, 위치마다 소음레벨 편차가 매우 크기 때문에 소음관리가 어렵다. 따라서 실내소음을 효과적으로 관리하기 위해서 소음분포를 분석할 수 있는 소음 가시화 시스템이 필요하다. 터빈실 내를 모델링하고, 선정된 지점의 소음레벨을 측정하여 소음지도를 작성할 수 있는 소음 매핑 시스템을 개발하였다. 그리고 모델의 신뢰성을 높이기 위하여 소음지도와 실제 소음측정 결과와 비교하는 방법을 통하여 모델을 수정하였다. 소음지도에 대한 정기적인 분석을 통하여 설비 이상을 판단할 수 있고, 특정 지점의 현재와 이전 소음에 대한 주파수 및 레벨을 비교 분석함으로써 실내소음을 효과적으로 관리하는 방법을 제시하였다. 매핑 시스템을 활용하면 근무환경을 개선할 수 있는 소음대책의 수립이 가능하고, 기계의 이상 유무를 확인하고, 예방정비를 통해 설비의 신뢰성을 높일 수 있다.

• Composites Research
• /
• 제34권6호
• /
• pp.394-399
• /
• 2021

Piecewise Integrated Composite(PIC) 보는 구간 조합 복합재 보로 구간 마다 적층 각도 및 순서를 다르게 적용하여 보의 강성과 강도를 향상시킬 수 있는 복합재료 보의 새로운 개념이다. 본 연구에서는 보의 거동을 고려하기 어려운 2차원 학습 데이터를 대신하여 3차원 학습 데이터가 적용된 머신 러닝 모델을 이용한 PIC 보가 제안되었다. 학습 데이터 및 훈련 데이터 셋(Training Data Set)은 지정된 참조 요소에서 3축 특성 값(Stress Triaxiality Factor)을 추출하여 세 가지 하중 유형(인장, 압축 그리고 전단)으로 분류되어 구성되었고, 이에 따른 하이퍼파라미터(Hyperparameter)가 제안되었다. 이를 통하여 예측된 PIC 보로 유한 요소 해석이 진행되었고 3차원 학습 데이터로 예측된 모델이 처짐 변형량이 감소된 것이 확인되었다. 이를 통해 3차원 학습 데이터를 이용하는 것이 경쟁력있는 것으로 판단되었고 처짐 변형량의 감소로 타당성이 검증되었다.

• 전기전자학회논문지
• /
• 제26권2호
• /
• pp.265-270
• /
• 2022

본 논문에서는 정지 좌표계 dq-축 전류를 기반으로 하는 비대칭 6상 PMSM의 스위치 개방 고장 검출 알고리즘을 제안한다. 본 논문에서의 해당 모터는 2개의 3상 권선이 30°의 전기적 위상차를 갖고 중성점이 분리된 비대칭 구조를 갖는다. 따라서 듀얼 3상 PWM 인버터와 스위치 개방 고장으로 인한 검출기법이 반드시 필요하다. 본 논문에서는 비대칭 6상 PMSM을 구동하기 위해 듀얼 dq축 전류 제어 방식을 사용하며 전역 통과 필터와 저역 통과 필터를 사용해 전류 변동을 감지하여 개방 고장이 발생한 스위치를 검출하는 방식을 제안한다. 제안한 방법의 효과와 유용성은 여러 실험을 통해 검증하였다.

• Smart Structures and Systems
• /
• 제30권3호
• /
• pp.333-338
• /
• 2022

Planning activity is complex process assuming the term "complexity" as a group of elements interconnected each other. The common knowledge about city planning underlines its main aim as: figuring the present, imaging the future, governing every day the territory and the way people use and live it at different scales. When considering the strength of technological opportunities and the spreading of ICT and IoT devices within everyday life, that mean within the life of cities, the complex nature of the urban system increases with the intensification of information and their connections. Recent orientations about urban and regional planning try to carry the discipline to a more flexible approach in respect to the hyperdeterminant role of direct technical applications. This passage is a fundamental aspect considering the faster and faster modifications of social and economic assets at the global and local scale. At the same time, the "environment question" became more and more relevant at the worldwide scale within the 2015 UN 2030 Agenda for Sustainable Development. Another relevant aspect about the recent urban planning orientations regards the role of the different subjects that are part of the planning process. Approaching the government of smart cities means to define how every subject, with different roles (public or private), could enrich the knowledge of the functioning of the "urban machine" and the awareness of participation of people and city users in the quality of urban life. In the paper author starts defining recent approaches in urban planning, then the nature of the city as a complex system is analyzed from the point of view of planners and of the different subjects that act in the city. Then the smart city is introduced as a further level of complexity and finally author propose the basic element of a Planning Support System.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.25-30
• /
• 2022

The article is devoted to the actual problem of the use of digital technologies in modern cinema in developed countries. The purpose of the study is to identify the essence of the term "cyberdramaturgy" and the problems of its use in modern film production. The research methodology is based on a systematic approach and includes the methods of the general scientific group (analysis, synthesis, deduction, induction), as well as a number of special methods: the method of content analysis of scientific literature on the research topic; sociological survey method; as well as the method of statistical analysis. The results of the survey were analyzed using the Neural Designer program (a tool for advanced statistical analytics) and translated into a graphical diagram format for clarity of perception. Answers in 75 questionnaires were evaluated by the average score for six analysis criteria, which made it possible to bring all the calculations to a 10-point scale. As a result of the study, the author of the article concluded the following: directors believe that the use of cyber analogues of actors and backgrounds leads to the blurring of genres, the hybridization of cinema and animation; directors are also concerned about the problem of replacing the director himself with a special program. The writers are completely concerned with the problem of machine scripting with almost infinite variability beyond the human imagination. Directors-producers believe that the cyberdramaturgy development will lead to completely new standards of cinematic quality, sharply different from the traditional assessment of acting and scene setting, to the appreciation of 3D animation as the highest category in the art. Such innovations actually devalue all international cinematography awards, as cyberdrama reduces the value of cyberactors to zero. It is impossible to bail out an "Oscar" or a "Golden Globe" award for a digital double or a separate cyber model that is used in the film instead of the actors.

• Structural Engineering and Mechanics
• /
• 제80권5호
• /
• pp.503-522
• /
• 2021

This paper investigates experimentally and numerically the influence of drilling process on the mechanical and thermomechanical behaviors of woven glass fiber reinforced polymer (GFRP) composite plate. Through the experimental analysis, a CNC machine with cemented carbide drill (point angles 𝜙=118° and 6 mm diameter) was used to drill a woven GFRP laminated squared plate with a length of 36.6 mm and different thicknesses. A produced temperature during drilling "heat affected zone (HAZ)" was measured by two different procedures using thermal IR camera and thermocouples. A thrust force and cutting torque were measured by a Kistler 9272 dynamometer. The delamination factors were evaluated by the image processing technique. Finite element model (FEM) has been developed by using LS-Dyna to simulate the drilling processing and validate the thrust force and torque with those obtained by experimental technique. It is found that, the present finite element model has the capability to predict the force and torque efficiently at various drilling conditions. Numerical parametric analysis is presented to illustrate the influences of the speeding up, coefficient of friction, element type, and mass scaling effects on the calculated thrust force, torque and calculation's cost. It is found that, the cutting time can be adjusted by drilling parameters (feed, speed, and specimen thickness) to control the induced temperature and thus, the force, torque and delamination factor in drilling GFRP composites. The delamination of woven GFRP is accompanied with edge chipping, spalling, and uncut fibers.

• Smart Structures and Systems
• /
• 제30권6호
• /
• pp.601-612
• /
• 2022

The prediction of structural mechanical behaviors is vital important to early perceive the abnormal conditions and avoid the occurrence of disasters. Especially for underground engineering, complex geological conditions make the structure more prone to disasters. Aiming at solving the problems existing in previous studies, such as incomplete consideration factors and can only predict the continuous performance, the deep attention fused temporal convolution network (DATCN) is proposed in this paper to predict the spatial mechanical behaviors of structure, which integrates both the temporal effect and spatial effect and realize the cross-time prediction. The temporal convolution network (TCN) and self-attention mechanism are employed to learn the temporal correlation of each monitoring point and the spatial correlation among different points, respectively. Then, the predicted result obtained from DATCN is compared with that obtained from some classical baselines, including SVR, LR, MLP, and RNNs. Also, the parameters involved in DATCN are discussed to optimize the prediction ability. The prediction result demonstrates that the proposed DATCN model outperforms the state-of-the-art baselines. The prediction accuracy of DATCN model after 24 hours reaches 90 percent. Also, the performance in last 14 hours plays a domain role to predict the short-term behaviors of the structure. As a study case, the proposed model is applied in an underwater shield tunnel to predict the stress variation of concrete segments in space.

• 인터넷정보학회논문지
• /
• 제23권6호
• /
• pp.15-26
• /
• 2022

사이버 공격을 수행하는 주체와 그 목적이 점차 다양화되고 고도화되고 있다. 과거 사이버 공격은 개인 혹은 집단의 자신감 표출을 위해 수행되었지만, 최근에는 국가 단위의 후원을 받은 정치적, 경제적 목적의 공격도 활발히 이루어지고 있다. 이에 대응하고자 시그니처 기반의 악성코드 패밀리 분류, 공격 주체 분류 등이 이루어졌지만 공격 주체가 의도적으로 방어자를 속일 수 있다는 단점이 있다. 또한 공격의 주체, 방법, 목적과 목표가 다양해짐에 따라, 공격의 모든 과정을 분석하는 것은 비효율적이다. 따라서 방어자 관점에서 사이버 공격의 최종 목표를 식별해 유연하게 대응할 필요가 있다. 사이버 공격의 근본적인 목표는 대상의 정보보안을 훼손하는 것이다. 정보보안은 정보자산의 기밀성, 무결성, 가용성을 보존함으로써 달성된다. 이에 본 논문에서는 MITRE ATT&CK® 매트릭스에 기반하여 공격자의 목표를 정보보안의 3요소 관점에서 재정의하고, 이를 머신러닝 모델과 딥러닝 모델을 통해 예측하였다. 실험 결과 최대 80%의 정확도로 예측하는 것을 확인할 수 있었다.

• 대한인간공학회:학술대회논문집
• /
• 대한인간공학회 1997년도 춘계학술대회논문집
• /
• pp.56-60
• /
• 1997

The study of human erroneous actions has traditionally taken place along two different lines of approach. One has been concerned with finding and explaining the causes of erroneous actions, such as studies in the psychology of "error". The other has been concerned with the qualitative and quantitative prediction of possible erroneous actions, exemplified by the field of human reliability analysis (HRA). Another distinction is also that the former approach has been dominated by an academic point of view, hence emphasising theories, models, and experiments, while the latter has been of a more pragmatic nature, hence putting greater emphasis on data and methods. We have been developing a method to make predictions about error modes. The input to the method is a detailed task description of a set of scenarios for an experiment. This description is then analysed to characterise thd nature of the individual task steps, as well as the conditions under which they must be carried out. The task steps are expressed in terms of a predefined set of cognitive activity types. Following that each task step is examined in terms of a systematic classification of possible error modes and the likely error modes are identified. This effectively constitutes a qualitative analysis of the possibilities for erroneous action in a given task. In order to evaluate the accuracy of the predictions, the data from a large scale experiment were analysed. The experiment used the full-scale nuclear power plant simulator in the Halden Man-Machine Systems Laboratory (HAMMLAB) and used six crews of systematic performance observations by experts using a pre-defined task description, as well as audio and video recordings. The purpose of the analysis was to determine how well the predictions matiched the actually observed performance failures. The results indicated a very acceptable rate of accuracy. The emphasis in this experiment has been to develop a practical method for qualitative performance prediction, i.e., a method that did not require too many resources or specialised human factors knowledge. If such methods are to become practical tools, it is important that they are valid, reliable, and robust.