• 제목/요약/키워드: Error Handling

검색결과 222건 처리시간 0.026초

Data-driven prediction of compressive strength of FRP-confined concrete members: An application of machine learning models

  • Berradia, Mohammed;Azab, Marc;Ahmad, Zeeshan;Accouche, Oussama;Raza, Ali;Alashker, Yasser
    • Structural Engineering and Mechanics
    • /
    • 제83권4호
    • /
    • pp.515-535
    • /
    • 2022
  • The strength models for fiber-reinforced polymer (FRP)-confined normal strength concrete (NC) cylinders available in the literature have been suggested based on small databases using limited variables of such structural members portraying less accuracy. The artificial neural network (ANN) is an advanced technique for precisely predicting the response of composite structures by considering a large number of parameters. The main objective of the present investigation is to develop an ANN model for the axial strength of FRP-confined NC cylinders using various parameters to give the highest accuracy of the predictions. To secure this aim, a large experimental database of 313 FRP-confined NC cylinders has been constructed from previous research investigations. An evaluation of 33 different empirical strength models has been performed using various statistical parameters (root mean squared error RMSE, mean absolute error MAE, and coefficient of determination R2) over the developed database. Then, a new ANN model using the Group Method of Data Handling (GMDH) has been proposed based on the experimental database that portrayed the highest performance as compared with the previous models with R2=0.92, RMSE=0.27, and MAE=0.33. Therefore, the suggested ANN model can accurately capture the axial strength of FRP-confined NC cylinders that can be used for the further analysis and design of such members in the construction industry.

300 mm 웨이퍼의 전영역 TTV 측정 정밀도 향상을 위한 모듈 설계 (Design for Enhanced Precision in 300 mm Wafer Full-Field TTV Measurement)

  • 정안목;이학준
    • 마이크로전자및패키징학회지
    • /
    • 제30권3호
    • /
    • pp.88-93
    • /
    • 2023
  • 고대역폭 메모리(HBM)에 대한 수요가 증가하고 직경이 더 큰 웨이퍼의 핸들링 기술이 발전함에 따라 본딩 웨이퍼의 두께 균일성에 대해 신뢰성을 확보할 수 있는 측정 방법이 요구되고 있다. 본 연구에서는 300mm 웨이퍼를 대상으로 웨이퍼의 전 영역에 대해 TTV를 측정할 수 있는 모듈을 설계 제직하고, 측정 모듈의 설계를 바탕으로 발생할 수 있는 측정 오차를 분석하였으며, 웨이퍼의 처짐과 척의 기구적 오차를 고려한 모델 해석을 통해 예측된 기울기 값에 따른 측정 오차를 추정하였다. TTV 측정 모듈은 웨이퍼 지지를 위한 센터 척과 리프트 핀을 활용하여 웨이퍼의 전체 영역에 대해 측정이 가능하도록 하였다. 모달 해석을 통해 모듈의 구조적 안정성을 예측하였으며, 구동부와 측정부 모두 100Hz 이상의 강성을 갖는 것을 확인하였다. 설계된 모듈의 측정 오차를 예측한 결과 두께 1,500um의 본딩 웨이퍼를 측정할 경우 예측된 측정 오차는 1.34nm로 나타났다.

Application of neural network for airship take-off and landing system by buoyancy change

  • Chang, Yong-Jin;Woo, Gui-Aee;Kim, Jong-Kwon;Cho, Kyeum-Rae
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 2003년도 ICCAS
    • /
    • pp.333-336
    • /
    • 2003
  • For long time, the takeoff and landing control of airship was worked by human handling. With the development of the autonomous control system, the exact controls during the takeoff and landing were required and lots of methods and algorithms were suggested. This paper presents the result of airship take-off and landing by buoyancy control using air ballonet volume change and performance control of pitch angle for stable flight within the desired altitude. For the complexity of airship's dynamics, firstly, simple PID controller was applied. Due to the various atmospheric conditions, this controller didn’t give satisfactory results. Therefore, new control method was designed to reduce rapidly the error between designed trajectory and actual trajectory by learning algorithm using an artificial neural network. Generally, ANN has various weaknesses such as large training time, selection of neuron and hidden layer numbers required to deal with complex problem. To overcome these drawbacks, in this paper, the RBFN (radial basis function network) controller developed.

  • PDF

저온 농축법에 의한 수소와 헬륨 중의 미량가스 분석 (Analysis of Trace Impurities in The Bulk $H_2$ and He Gases by a Cold Concentration Method)

  • 이택홍;박두선;손무용
    • 대한화학회지
    • /
    • 제42권5호
    • /
    • pp.526-530
    • /
    • 1998
  • 가스분석에서 극미량 성분분석은 반도체 관련 산업의 발달과 더불어 매우 중요하다. 특히 반도체 생산설비 중 가스공급시스템의 공기성분에 의한 오염은 제조자에게 어려움을 제공해 왔다. 그래서 공기성분의 분석은 반도체의 품질조절에 매우 중요하다. 본 연구에서는 가스분석에서 범용으로 사용되는 열전도도 검출기를 장착한 가스크로마토그래프와 액체질소트랩을 이용하여 헬륨과 수소 중의 질소와 아르곤성분을 분석하였다. 농축법으로 결정된 미지 시료의 농도를 다른 종류의 검출기와 비교 분석하였다. 이 방법에 의해서 결정된 농도는 결정된 확장불확도 범위 내에서 만족할 만한 결과를 보여 주었다.

  • PDF

비선형 관측기를 이용한 차량의 타이어 횡력 감지시스템 개발 (Development of Tire Lateral Force Monitoring Systems Using Nonlinear Observers)

  • 김준영;허건수
    • 한국자동차공학회논문집
    • /
    • 제8권4호
    • /
    • pp.169-176
    • /
    • 2000
  • Longitudinal and lateral forces acting on tires are known to be closely related to the tract-ability braking characteristics handling stability and maneuverability of ground vehicles. In thie paper in order to develop tire force monitoring systems a monitoring model is proposed utilizing not only the vehicle dynamics but also the roll motion. Based on the monitoring model three monitoring systems are developed to estimate the tire force acting on each tire. Two monitoring systems are designed utilizing the conventional estimation techniques such as SMO(Sliding Mode Observer) and EKF(Extended Kalman Filter). An additional monitoring system is designed based on a new SKFMEC(Scaled Kalman Filter with Model Error Compensator) technique which is developed to improve the performance of EKF method. Tire force estimation performance of the three monitoring systems is compared in the Matlab simulations where true tire force data is generated from a 14 DOF vehicle model with the combined-slip Magic Formula tire model. The built in our Lab. simulation results show that the SKFMEC method gives the best performance when the driving and road conditions are perturbed.

  • PDF

Real-time line control system for automated robotic assembly line for multi-PCB models

  • Park, Jong-Oh;Hyun, Kwang-Ik;Um, Doo-Gan;Kim, Byoung-Doo;Cho, Sung-Jong;Park, In-Gyu;Kim, Young-Sik
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국제학술편); KOEX, Seoul; 22-24 Oct. 1991
    • /
    • pp.1915-1919
    • /
    • 1991
  • The efficiency of automated assembly line is increased by realizing the automation of each assembly cell, monitoring the line information and developing the real-time line control system it. which production flow is controllable. In this paper, the several modules which are important factors when constructing automated real-time control system, such as, line control S/W module, real-time model change module, error handling module and line production management S/W module, are developed. For developing these important programming modules, real-time control and multi-tasking techniques are integrated. In this paper, operating method of real-time line control in PCB automated assembly line is proposed and for effective control of production line by using multi-tasking technique, proper operating method for relating real-time line control with multi-tasking is proposed by defining the levels of signals and tasks. CIM-Oriented modular programming method considering expandability and flexibility will be added for further research in the future.

  • PDF

일반화된 미등록어 처리와 오류 수정규칙을 이용한 혼합형 품사태깅 (Hybrid POS Tagging with generalized unknown word handling and post error-correction rules)

  • 차정원;이원일;이근배;이종혁
    • 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
    • /
    • 한국정보과학회언어공학연구회 1997년도 제9회 한글 및 한국어 정보처리 학술대회
    • /
    • pp.88-93
    • /
    • 1997
  • 본 논문에서는 품사 태깅을 위해 여러 통계 모델을 실험을 통하여 비교하였으며 이를 토대로 통계적 모델을 구성하였다. 형태소 패턴 사전을 이용하여 미등록어의 위치와 개수에 관계없는 일반적인 방법의 미등록어 처리 방법을 개발하고 통계모델이 가지는 단점을 보완할 수 있는 오류 수정 규칙을 함께 이용하여 혼합형 품사 태깅 시스템인 $POSTAG^{i}$를 개발하였다. 미등록어를 추정하는 형태소 패턴 사전은 한국어 음절 정보와 용언의 불규칙 정보를 이용하여 구성하고 다어절어 사전을 이용하여 여러 어절에 걸쳐 나타나는 연어를 효과적으로 처리하면서 전체적인 태깅 정확도를 개선할 수 있다. 또 오류 수정 규칙은 Brill이 제안한 학습을 통하여 자동으로 얻어진다. 오류 수정 규칙의 자동 추출시에 몇 가지의 휴리스틱을 사용하여 보다 우수하고 일반적인 규clr을 추출할 수 있게 하였다. 10만의 형태소 품사 말뭉치로 학습하고 학습에 참여하지 않은 2만 5천여 형태소로 실험하여 97.28%의 정확도를 보였다.

  • PDF

Application of Principal Components Analysis Method to Wireless Sensor Network Based Structural Monitoring Systems

  • Congyi, Zhang;Mission, Jose Leo;Kim, Sung-Ho;Youk, Yui-Su;Kim, Hyeong-Joo
    • International Journal of Fuzzy Logic and Intelligent Systems
    • /
    • 제8권1호
    • /
    • pp.11-17
    • /
    • 2008
  • Typical wireless sensor networks used in structural monitoring are continuous types wherein data transmission is progressive at all time that may include irrelevant and insignificant data and information. Continuous types of wireless monitoring systems often pose problems of handling large-sized data that may deteriorate the performance of the system. The proposed method is to suggest an event-triggered monitoring system that captures and transmits relevant data only. An error signal generated by the Principal Components Analysis (PCA) is utilized as an index for event detection and selective data transmission. With this new monitoring scheme, the remote server is relieved of unwanted data by receiving only relevant information from the wireless sensor networks. The performance of the proposed scheme was verified with simulation studies.

단일물체 조작을 위한 두 협조 로봇의 협조제어 (A Coordination Control Methodlolgy for Two Cooperating Arms Handling a Single Object)

  • 여희주
    • 제어로봇시스템학회논문지
    • /
    • 제6권2호
    • /
    • pp.190-196
    • /
    • 2000
  • A hybrid position/force control scheme to regulate the force and position by dual arms is proposed where two arms are treated as one rm in a kinematic viewpoint. The force error calculated from the information of two force/torque sensors attached to the end of each arm is transferred to minimum configuration space coordinates and then is distributed to total system joint coordinates, The position adjustment at the total con-figuration coordinates is computed based on the effective compliance matrix with respect to total joint coordinates which is obtained by coordinate transformation between the task coordinates and the total joint coordinates. The proposed scheme is applied to sawing task. When the trajectory of the saw is planned to follow a line in a horizontal plane 2 position parameters are to be controlled(i.e., two translational positions) Also a certain level of contact force has to be controlled along the vertical direction(i.e. minus z-direction) not to loose the contact with the object to be sawn. We experimentally show that the performance of the velocity and force response are satisfactory. The proposed hybrid control scheme can be applied to arbitrary two cooperating arm system regardless of their kinematic structure and the number of actuated joints.

  • PDF

저소득층 노인의 유헬스 서비스 이용경험 (Low-income Elders' Experiences in Using u-Health (Ubiquitous Healthcare) Services)

  • 최한나;김정은
    • 지역사회간호학회지
    • /
    • 제25권4호
    • /
    • pp.270-281
    • /
    • 2014
  • Purpose: The purpose of the study was to understand low-income elders' experiences of community-based u-Health services. Methods: Qualitative data were collected from 11 participants. All interviews were recorded and transcribed verbatim. The transcribed data were analyzed using qualitative content analysis. Results: Three themes and eight sub-themes emerged as a result of analysis. The three main themes were 'recovered confidence and health condition,' 'trial and error in change,' and 'hope.'The eight sub-themes were 'the burden and efforts to overcome it in using bio-signal device,' 'ambivalence due to changing lifestyle,' 'increase of care time, decrease of pressure', 'conflict under environmental constraints,' 'difficulty in prioritizing health management,' 'discouragement in handling new devices,' 'desire not to be a burden to their children-gradual fulfillment of learning needs,' and 'long for broadening coverage range of services.' Conclusion: The findings of this study demonstrate that low-income elders among the participants have different needs in using u-Health services. Therefore, health professionals need to give personalized education to deal with their conflicts and requirements, especially emotional and environmental support in order for them to successfully accept the u-Health services for self-care.