• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3482-3497
• /
• 2021

Artificial intelligence has emerged as the core of the 4th industrial revolution, and large amounts of data processing, such as big data technology and rapid data analysis, are inevitable. The most fundamental and universal data interpretation technique is an analysis of information through regression, which is also the basis of machine learning. Ridge regression is a technique of regression that decreases sensitivity to unique or outlier information. The time-consuming calculation portion of the matrix computation, however, basically includes the introduction of an inverse matrix. As the size of the matrix expands, the matrix solution method becomes a major challenge. In this paper, a new algorithm is introduced to enhance the speed of ridge regression estimator calculation through series expansion and computation recycle without adopting an inverse matrix in the calculation process or other factorization methods. In addition, the performances of the proposed algorithm and the existing algorithm were compared according to the matrix size. Overall, excellent speed-up of the proposed algorithm with good accuracy was demonstrated.

• 한국기계가공학회지
• /
• 제20권7호
• /
• pp.15-24
• /
• 2021

In this paper, to analyze the types of surface morphology error according to factors that cause machining error, the experiments were conducted in the ultra-precision diamond machine using a diamond tool. The factors causing machining error were classified into the pressure variation of compressed air, external shock, tool errors, machining conditions (rotational speed and feed rate), tool wear, and vibration. The pressure variation of compressed air causes a form accuracy error with waviness. An external shock causes a ring-shaped surface defect. The installed diamond tool for machining often has height error, feed-direction position error, and radius size error. The types of form accuracy error according to the tool's errors were analyzed by CAD simulation. The surface roughness is dependent on the tool radius, rotational speed, and feed rate. It was confirmed that the surface roughness was significantly affected by tool wear and vibration, and the surface roughness of Rz 0.0105 ㎛ was achieved.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2002년도 춘계학술대회 논문집
• /
• pp.422-428
• /
• 2002

In this study, actuator, sensor, guide, power transmission element and control method are considered for ultra-precision positioning apparatus. Through previous process, single plane X-Y stage with ultra-precision positioning is manufactured. Global stage for the purpose of materialization with robust system, is combined by using AC servo motor and ball screw and rolling guide. And ultra-precision positioning system is developed by micro stage with elastic hinge type and piezo element. global servo and micro servo for the purpose of materialization positioning accuracy with nm(nanometer) are controlled simultaneously by using incremental encoder and laser interferometer as displacement measurement sensor. Through previous process, ultra-precision positioning system (100mm stroke and ${\pm}$ 10nm positioning accuracy) with single plane X-Y stage are materialized.

• 한국공작기계학회논문집
• /
• 제16권3호
• /
• pp.23-30
• /
• 2007

Nano-stages are used in many ultra-precision systems, such as scanning probe microscope(SPM), optical fiber aligners, ultra-precision cutting, measuring systems, and optical systems. It is difficult to find the solutions because the performances and characteristics of nano-scale motion stage are determined by various factors. To understand effects of nano-scale motion stage, three types of hinge structures were designed and manufactured. Each hinge structures were designed following with the results of simulation. And from the result of experiments, hysteresis, displacement, and accuracy were compared with each hinge structures.

• Journal of Electrical Engineering and Technology
• /
• 제12권4호
• /
• pp.1548-1555
• /
• 2017

This paper attempts to employ and investigate neural based approaches as interpolation tools for modeling of Switched Reluctance Motor (SRM) drive. Precise modeling of SRM is essential to analyse the performance of control strategies for variable speed drive application. In this work the suitability of Generalized Regression Neural Network (GRNN) and Extreme Learning Machine (ELM) in addition to conventional neural network are explored for improving the modeling accuracy of SRM. The neural structures are trained with the data obtained by modeling of SRM using Finite Element Analysis (FEA) and the trained neural network is incorporated in the model of SRM drive. The results signify the modeling accuracy with GRNN model. The closed loop drive simulation is performed in MATLAB/Simulink environment and the closeness of the results in comparison with the experimental prototype validates the modeling approach.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.1040-1043
• /
• 1996

The accuracy of the servo control in CNC system has a great influence on the duality of machine product. Tracking performance of the servo control is deteriorated mainly by the time delay of the servo system and the inertia of the work table or bed. Contouring errors occur in every interpolation steps by the effect of the tracking performance. In this paper, $H_{\infty}$ two-degree-of-freedom(TDF) controller is designed for improvement to improve the tracking performance. The designed controller is applied 3-axis machining center model and the cutting accuracy is simulated in case of corner cutting, circular and involute interpolation. Simulation results show that $H_{\infty}$ TDF controller designed in this paper has a good effect to improve tracking performance in CNC system.

• 한국정밀공학회지
• /
• 제9권4호
• /
• pp.44-57
• /
• 1992

Ball screw systems have been used for positioning elements of machine tools and precision tables. In order to maintain the high rigidity and accuracy, a certain amount of preload is applied between the nut and the screw of ball screw systems. However, large amount of the preload oncreases the frictional heat. The temperature rises remarkably at the high speed motion, and the thermal expansion degrades the positioning accuracy. In this paper, a finite difference method is applied to analyse temperature distributions and thermal expansions of the ball screw system according to preload conditions and rotational speeds. Some simulation results show that the developed methodology is appropriate to study the thermal expansion characteristics of ball screw systems.

• 한국공작기계학회논문집
• /
• 제17권2호
• /
• pp.13-22
• /
• 2008

For the accuracy correction of the micro-positioning industrial robot, micro-manipulator has been devised. The compliant mechanisms using piezoelectric actuators is necessary geometrically and structurally to be developed by the optimization approaches. The overall geometric advantage as the mechanical efficiencies of the mechanism are considered as objective functions, which respectively art the ratio of output displacement to input force, and their constraints are the vertical notion of supporting leg and the structural strength of manipulation. In optimizing the compliant mechanical amplifier, the sequential linear programming and an optimality criteria method are used for the geometrical dimensions of compliant bridges and flexure hinges. This paper presents the integrated design process which not only can maximize the mechanism feasibilities but also can ensure the positioning accuracy and sufficient workspace. Experiment and simulation are presented for validating the design process through the comparisons of the kinematical and structural performances.

• 한국ITS학회 논문지
• /
• 제20권5호
• /
• pp.100-112
• /
• 2021

빅데이터의 등장과 더불어 교통 상태 예측은 과거 이력 데이터 분석 방식에 힘을 싣고 발전되어 왔으나, 이 방법은 관측된 적 없는 돌발 상황에 충분히 대응하지 못한다는 약점이 있다. 본 연구에서는 기계학습과 시뮬레이션 기법의 융합을 통해 돌발 상황 발생 시 교통 상태 예측 정확도 감소를 보완할 수 있는 예측 기법을 제시한다. 데이터 기반 방식의 맹점은 과거에 관측된 적 없는 데이터 패턴이 인지되었을 때 드러난다. 본 연구에서는 시뮬레이션을 이용하여 과거 이력 데이터를 보강하는 방법으로 문제를 해결하고자 하였다. 제시한 방법은 기계학습 기반의 교통 예측을 수행하고, 예측 결과와 실시간으로 수집되는 교통 데이터를 지속적으로 비교하여 돌발 상황 발생 여부를 판단한다. 돌발 상황이 인지되었을 시, 시뮬레이션을 통해 생성한 데이터베이스를 활용하여 예측을 수행한다. 본 연구에서 제시한 방법은 실제 도로 구간을 대상으로 검증되었으며, 검증 결과 돌발 상황에서의 교통 상태 예측 정확도 향상을 확인할 수 있었다. 본 연구에서 제시한 융합 교통 예측 방법은 향후 교통 예측 고도화에 이바지할 수 있을 것으로 전망된다.

• 응용통계연구
• /
• 제28권1호
• /
• pp.9-21
• /
• 2015

SVM은 높은 수준의 분류 정확도와 유연성을 바탕으로 다양한 분야의 분류분석에서 널리 사용되고 있다. 그러나 집단별 개체수가 상이한 불균형 자료의 분류분석에서 SVM은 다수집단으로 편향되게 분류함수를 추정하므로 소수집단의 분류 정확도가 심각하게 감소하게 된다. 불균형 자료의 분류분석을 위하여 집단별 오분류 비용을 차등 적용하는 가중 $L_2$-norm SVM이 개발되었으나, 이는 릿지 형태의 벌칙함수를 사용하므로 분류함수의 추정에서 불필요한 잡음변수의 제거에는 효율적이지 못하다. 따라서 본 논문에서는 라소 형태의 별칙함수를 사용하고 훈련개체의 오분류 비용을 차등적으로 부여함으로서 불균형 자료의 분류분석에서 변수선택의 기능을 지니는 가중 $L_1$-norm SVM을 제안하였으며, 모의실험과 실제자료의 분석을 통하여 제안한 방법론의 효율적인 성능과 유용성을 확인하였다.