• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.9 no.3
• /
• pp.150-159
• /
• 2000

In-process diagnosis of the cutting state is essential for the automation of manufacturing systems. Especially when the cutting process becomes unstable it induces self-exited vibrations a frequent case of poor tool life rough surface finish damage to the workpiece and the machine tool itself and excessive down time. To ensure that the cutting process main-tains stable it is highly desirable to have the capability of real-time. To ensure that the cutting process main-tains stable it is highly desirable to have the capability of real-time monitoring and controlling chatter. This paper describes the detection method of chatter vibration using cutting force in turning process. In order to detect a chatter vibra-tion the dynamic fluctuation of radial force is analyzed since this components is sensitive to the chatter. The envelope sig-nal of radial force has been calculated by the use of FIR Hilbert transformer and it was useful to classify the chatter signal from the dynamically unstable circumstances. It was found that the mode and the mode width were closely correlated with the chatter amplitude was well. Finally back propagation(BP) neural network have been applied to the pattern recognition for the classification of chatter signal in various cutting conditions. The validity of this systed was confirmed by the experiments under the various cutting conditions.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.11
• /
• pp.1195-1202
• /
• 2004

The international competition in refrigerator markets has continuously required the research for sound quality of a refrigerator to improve the quality of a life. In this paper, A new method for evaluation of the sound quality of a refrigerator is developed based on human sensibility engineering by using ANN(artificial neural network). In this paper, the loudness and the sharpness of the refrigerator's signals was used for the input value in ANN's training process because the loudness and the sharpness has a good correlation between the output of the ANN and the target of the individual evaluation In the training process. Two input factor was used repeatedly in the training process to get more optimum weighting value. And then finally we developed the sound quality index of a refrigerator. The developed sound quality index was confirmed by the 96.5 % of correlation between the output of the ANN and the real evaluation. It will be applied to evaluate the sound quality of a refrigerator in the industry.

• Wind and Structures
• /
• v.18 no.3
• /
• pp.253-265
• /
• 2014

The platform and floating structure of spar type offshore wind turbine systems should be designed in order for the 6-DOF motions to be minimized, considering diverse loading environments such as the ocean wave, wind, and current conditions. The objective of this study is to optimally design the platform and substructure of a 3MW spar type wind turbine system with the maximum postural stability in 6-DOF motions as well as the minimum material cost. Therefore, design variables of the platform and substructure were first determined and then optimized by a hydrodynamic analysis. For the hydrodynamic analysis, the body weight of the system was considered, and the ocean wave conditions were quantified to the wave forces using the Morison's equation. Moreover, the minimal number of computation analysis models was generated by the Design of Experiments (DOE), and the design variables of the platform and substructure were finally optimized by using a genetic algorithm with a neural network approximation.

• International Journal of Korean Welding Society
• /
• v.1 no.1
• /
• pp.23-30
• /
• 2001

Among the various welding conditions, the welding current that is inversely proportional to the tip-to-work-piece distance is an essential parameter as to monitor the GMAW process and to implement the welding automation. Considering the weld pool surface geometry including weld defects, it should modify the signal processing method for automatic seam tracking in horizontal fillet welding. To meet the above necessities, a mathematical model related with the weld pool geometry was proposed as in a conjunction with the two-dimensional heat flow analysis of the horizontal fillet welding. The signal processing method based on the artificial neural network (Adaptive Resonance Theory) was proposed for discriminating the sound weld pool surface from that with the weld defects. The reliability of the numerical model and the signal processing method proposed were evaluated through the experiments of which showed that they are effective for predicting the weld bead shape with or without the weld defects in a horizontal fillet welding.

• 한국IT서비스학회:학술대회논문집
• /
• 2005.05a
• /
• pp.372-380
• /
• 2005

소프트웨어 개발노력 추정에 대한 연구는 소프트웨어가 복잡해지고 범위가 크게 증가함에 따라서 그 중은 지속적으로 부각되고 있다. 관련 프로젝트를 발주하는 업체나, 이를 수주하고 개발을 진행하는 업체에게 원가를 고려하는 측면에서 매우 중요한 부분을 차지하고 있다. 이러한 개발노력 추정을 위하여 다양한 접근 방식들이 고려되어지고 있는데, 그중에서 많이 활용되어지고 있는 방식은 소프트웨어 규모에 기반을 둔 LOC(Line Of Code) 기반 COCOMO (Constructive Cost Model) 모델이나 기능점수(Function Point)를 기반으로 한 회귀분석 모델, 인공지능(Artificial Intelligence)을 활용한 신경망(Neural Network) 모델, 사례분석기법 (CBR, Case Based Reasoning) 등이 있다. 이중에서 최근에 기능점수를 활용한 개발노력 추정에 관한 연구들이 활발히 진행되고 있으나 개발노력 추정에는 소프트웨어 규모의 척도인 기능점수 뿐만 아니라, 개발환경을 구성하는 여러 가지 측면에 대한 고려가 추가되어져야 한다. 이에 본 논문은 최신의 소프트웨어 개발 사례들에 대하여 기능점수 및 추가적인 개발환경 요소들을 면밀히 분석하고, 분석한 내용에 대해서 전문가들의 설문을 통한 빈도분석 및 로지스틱 회귀분석, 데이터마이닝 기법인 신경망 분석 등을 활용하여 개발노력 추정 모델을 구축함으로써, 소프트웨어 개발의 다양한 측면의 중요성을 강조하고, 정확한 추정의 방안을 제시 하고자 노력 하였다.

• Proceedings of the KIEE Conference
• /
• 2006.07b
• /
• pp.729-730
• /
• 2006

The paper is proposed maximum torque control of SynRM drive using adaptive fuzzy neural network(A-FNN) controller and artificial neural network(ANN). For each control mode, a condition that determines the optimal d-axis current $i_d$ for maximum torque operation is derived. The proposed control algorithm is applied to SynRM drive system controlled A-FNN and ANN controller, the operating characteristics controlled by maximum torque control are examined in detail. Also, this paper is proposed the analysis results to verify the effectiveness of the A-FNN and ANN controller.

• Proceedings of the KIEE Conference
• /
• 2006.07b
• /
• pp.731-732
• /
• 2006

The paper is proposed maximum torque control of IPMSM drive using adaptive learning mechanism-fuzzy neural network (ALM-FNN) and artificial neural network(ANN). For each control mode, a condition that determines the optimal d-axis current $i_d$ for maximum torque operation is derived. The proposed control algorithm is applied to IPMSM drive system controlled ALM-FNN and ANN, the operating characteristics controlled by maximum torque control are examined in detail. Also, this paper is proposed the analysis results to verify the effectiveness of the ALM-FNN and ANN.

• Journal of the Korean Geosynthetics Society
• /
• v.6 no.1
• /
• pp.39-43
• /
• 2007

Geocomposites of needle punched and spunbonded nonwovens having the reinforcement and drainage functions were manufactured by use of thermal bonding method. The physical properties (e.g. tensile, tear and bursting strength, permittivity) of these multi-layered nonwovens were dependent on the processing parameters of temperatures, pressures, bonding periods etc. - in manufacturing by use of thermal bonding method. Therefore, it is very meaningful to optimize the processing parameters and physical properties of the geocomposites by thermal bonding method. In this study, an algorithm has been developed to optimize the process of the geocomposites using an artificial neural network (ANN). Geocomposites were employed to examine the effects of manufacturing methods on the analysis results and the neural network simulations have been applied to predict the changes of the nonwovens performances by varying the processing parameters.

• Journal of the Korean Geotechnical Society
• /
• v.17 no.2
• /
• pp.73-83
• /
• 2001

본 연구에서는 전국 4개 지구의 화강암 풍화토를 연구대상으로 현장 및 실내시험을 수행하고 토량 변화율을 노상과 노체에 대하여 결정하였다. 그리고, 본 연구에서는 인공 신경망 중 오류 역전파 학습 알고리즘을 도입하여 토량 변화율 C 값을 추정하고 신경망의 적용성에 대한 검증을 수행하였다. 화강암 풍화토에 대한 실내 및 현장시험 결과에서 얻어진 토량 변화율 C 값은 노상과 노체 구분 없이 최소 0.7에서 최대 1.2정도의 넓은 범위로 나타났다. 토지공사에서 제안하는 C값의 산정식과 본 연구 결과를 비교한 결과, 토지공사의 산정식에 의한 결과가 과대 평가될 가능성이 큰 것으로 나타났다. 비중, 자연 함수비, 자연상태의 습윤단위중량, #200 통과율 그리고 균등계수의 입력변수를 갖는 $I_{5-1}$$H_{30-30}$$O_1$의 신경망에서 다른 신경망 구조들보다 잦은 지역 최소점에 수렴하는 결과를 보였다. 본 연구에서 사용한 모든 신경망 구조에서 시험결과와 신경망 결과의 상관계수는 0.9이상으로 나타나 높은 상관성을 나타내었다. 특히, 인공 신경망에 의한 예측결과는 다양한 영향인자들 중에서 비중, 자연 함수비, 자연상태의 습윤단위중량 그리고 #200 통과율의 4개 변수만으로도 C값을 예측할 수 있었으며, 상관계수는 0.96으로 나타났다.다.

• Proceedings of the KIEE Conference
• /
• 2005.04a
• /
• pp.188-190
• /
• 2005

This paper is proposed HAI controller for high performance of induction motor drive. The design of this algorithm based on FNN controller that is implemented using fuzzy control and neural network. This controller uses fuzzy rule as training patterns of a neural network. The control performance of the HAI controller is evaluated by analysis for various operating conditions. The results of analysis prove that the proposed control system has strong high performance and robustness to parameter variation, and steady-state accuracy and transient response.