• 제목/요약/키워드: resampling simulation

검색결과 52건 처리시간 0.022초

STFT를 이용한 회전체의 진동신호 분석 기법 (Analysis Technique for the Vibration Signal of Revolution Machine Using the STFT)

  • 박종연;박준용;최원호
    • 산업기술연구
    • /
    • 제24권A호
    • /
    • pp.67-73
    • /
    • 2004
  • The purpose of this study is to analyze the vibration signal of the revolution machine using the STFT(Short Time Fourier Transform). It is common to analyze the frequency of signal through FFT algorithm with the fixed sampling rate. However, in this situation the order spectrum information useful rather than the general frequency information with the fixed sampling rate. In this paper, the resampling technique was used for getting the information of order spectrum. In resampling process, the arithmetic amount and MSE(Mean Square Error) for various kinds of the signal interpolation was compared and presented the propriety of the interpolation method while developing analysis equipment. Order tracking was implemented using signal interpolation method which it has selected. Then the analyzed results were obtained through simulation using the STFT technique.

  • PDF

Novel FFT Acquisition Scheme with Baseband Resampling for Multi-GNSS Receivers

  • Jinseok, Kim;Sunyong, Lee;Hung Seok, Seo
    • Journal of Positioning, Navigation, and Timing
    • /
    • 제12권1호
    • /
    • pp.59-65
    • /
    • 2023
  • A GNSS receiver must perform signal acquisition to estimate the code phase and Doppler frequency of the incoming satellite signals, which are essential information for baseband signal processing. Modernized GNSS signals have different modulation schemes and long PRN code lengths from legacy signals, which makes it difficult to acquire the signals and increases the computational complexity and time. This paper proposes a novel FFT/Inverse-FFT with baseband resampling to resolve the aforementioned challenges. The suggested algorithm uses a single block only for the FFT and thereby requires less hardware resources than conventional structures such as Double Block Zero Padding (DBZP). Experimental results based on a MATLAB simulation show this algorithm can successfully acquire GPS L1C/A, GPS L2C, Galileo E1OS, and GPS L5.

Bootstrapping Regression Residuals

  • Imon, A.H.M. Rahmatullah;Ali, M. Masoom
    • Journal of the Korean Data and Information Science Society
    • /
    • 제16권3호
    • /
    • pp.665-682
    • /
    • 2005
  • The sample reuse bootstrap technique has been successful to attract both applied and theoretical statisticians since its origination. In recent years a good deal of attention has been focused on the applications of bootstrap methods in regression analysis. It is easier but more accurate computation methods heavily depend on high-speed computers and warrant tough mathematical justification for their validity. It is now evident that the presence of multiple unusual observations could make a great deal of damage to the inferential procedure. We suspect that bootstrap methods may not be free from this problem. We at first present few examples in favour of our suspicion and propose a new method diagnostic-before-bootstrap method for regression purpose. The usefulness of our newly proposed method is investigated through few well-known examples and a Monte Carlo simulation under a variety of error and leverage structures.

  • PDF

Resampling-based Test of Hypothesis in L1-Regression

  • Kim, Bu-Yong
    • Communications for Statistical Applications and Methods
    • /
    • 제11권3호
    • /
    • pp.643-655
    • /
    • 2004
  • L$_1$-estimator in the linear regression model is widely recognized to have superior robustness in the presence of vertical outliers. While the L$_1$-estimation procedures and algorithms have been developed quite well, less progress has been made with the hypothesis test in the multiple L$_1$-regression. This article suggests computer-intensive resampling approaches, jackknife and bootstrap methods, to estimating the variance of L$_1$-estimator and the scale parameter that are required to compute the test statistics. Monte Carlo simulation studies are performed to measure the power of tests in small samples. The simulation results indicate that bootstrap estimation method is the most powerful one when it is employed to the likelihood ratio test.

A New Method of Simulation Output Analysis : Threshold Bootstrap

  • Kim, Yun-Bae-
    • 한국시뮬레이션학회:학술대회논문집
    • /
    • 한국시뮬레이션학회 1993년도 제3회 정기총회 및 추계학술발표회
    • /
    • pp.2-2
    • /
    • 1993
  • Inference for discrete event simulations usually relies on either independent replications or, if each simulation run is expensive, the method of batch means applied to a single replications. We present a new method, threshold bootstrap, which equals or exceeds the performance of independent replications or batch means. The method works by resampling runs of data created when a stationary time series crosses a threshold level, such as the sample mean of series. Computational results show that the threshold bootstrap matches or exceeds the performance of these alternative methods in estimating the standard deviation of the sample mean and producing valid confidence intervals.

  • PDF

노이즈 환경에서 입자 군집 최적화 알고리즘의 성능 향상을 위한 통계적 가설 검정 기반 리샘플링 기법의 적용 (Application of Resampling Method based on Statistical Hypothesis Test for Improving the Performance of Particle Swarm Optimization in a Noisy Environment)

  • 최선한
    • 한국시뮬레이션학회논문지
    • /
    • 제28권4호
    • /
    • pp.21-32
    • /
    • 2019
  • 군집에 대한 사회적 행동 모델에 영감을 받은 군집 최적화 알고리즘은 복잡한 최적화 문제 해결에서부터 인공 신경망의 학습에까지 활용되는 대표적인 메타휴리스틱 최적화 알고리즘 중의 하나이다. 하지만 이 알고리즘은 기본적으로 확률적 노이즈가 존재하지 않는 결정적인 환경에서 개발되었기 때문에, 많은 경우 확률적 노이즈가 존재하는 실제 문제에 적용하기에 어려움이 있었다. 본 논문에서는 이를 개선하기 위하여 불확실 평가 기법이라고 정의되는 통계적 가설 검정 기반의 리샘플링 기법을 적용한다. 이 기법을 통하여 입자 군집 최적화 알고리즘의 성능에 가장 큰 영향을 미치는 입자들의 전역 최적을 정확하게 찾으므로 노이즈 환경에서 입자들이 최적해로 보다 정확하고 빠르게 수렴하도록 한다. 다양한 벤치마크 문제들에 대한 기존 알고리즘들과의 비교 실험 결과는 제안하는 알고리즘의 개선된 성능을 입증하고, 사례 연구의 결과는 본 연구의 필요성을 강조한다. 본 연구 결과가 4차 산업혁명 시대에 디지털 트윈 등을 통한 시뮬레이션 기반 시스템 최적화에 효과적으로 적용될 수 있을 것이라 기대한다.

재표집방법에 의한 공정관리지수의 신뢰구간 (Confidence Interval for Capability Process Indices by the Resampling Method)

  • 남경현
    • 한국신뢰성학회지:신뢰성응용연구
    • /
    • 제1권1호
    • /
    • pp.55-63
    • /
    • 2001
  • In this paper, we utilize the asymptotic variance of $C_{pk}$ to propose a two-sided confidence interval based on percentile-t bootstrap method. This confidence interval is compared with the ones based on the standard and percentile bootstrap methods. Simulation results show that percentile-t bootstrap method is preferred to other methods for constructing the confidence interval.l.

  • PDF

파티클 필터 알고리즘을 이용한 다기능레이더 표적 추적 필터 설계 (Design of the Target Estimation Filter based on Particle Filter Algorithm for the Multi-Function Radar)

  • 문준
    • 한국군사과학기술학회지
    • /
    • 제14권3호
    • /
    • pp.517-523
    • /
    • 2011
  • The estimation filter in radar systems must track targets' position within low tracking error. In the Multi-Function Radar(MFR), ${\alpha}-{\beta}$ filter and Kalman filter are widely used to track single or multiple targets. However, due to target maneuvering, these filters may not reduce tracking error, therefore, may lost target tracks. In this paper, a target tracking filter based on particle filtering algorithm is proposed for the MFR. The advantage of this method is that it can track targets within low tracking error while targets maneuver and reduce impoverishment of particles by the proposed resampling method. From the simulation results, the improved tracking performance is obtained by the proposed filtering algorithm.

Detection of Rotor Bar Faults in Field Oriented Controlled Induction Motors

  • Akar, Mehmet
    • Journal of Power Electronics
    • /
    • 제12권6호
    • /
    • pp.982-991
    • /
    • 2012
  • In this study, a new method has been presented for the detection of broken rotor bar (BRB) faults in inverter driven induction motors controlled via Field Oriented Control (FOC). To this end, a FOC controlled induction motor with a BRB fault was modeled using the Matlab/Simulink program. Experiments were carried out using the prepared simulation model at various loads and operating speeds. The motor current and speeds were monitored for healthy, 1, 2 and 3 BRB faults. The Resampling Based Order Tracking Analysis (RB-OTA) method was applied to the monitored signals. The obtained results were compared by using the classic Fast Fourier Transform (FFT) method. When the obtained results were analyzed via the FFT method no information regarding any faults was determined in the run up or run down regions of the motor and the presented method gave very good results. The reliability of the proposed method was validated with experimental results. The main innovative part of this study is that the RB-OTA method was implemented on the induction motor current signal for detecting BRB faults.

온주밀감에서 률응애의 공간분포분석 및 표본추출법 (Dispersion Indices and Sequential Sampling Plan for the Citrus Red Mite, Panonychus citri (McGregor) (Acari: Tetranychidae) on Satsuma Mandarin on Jeju Island)

  • 송정흡;이창훈;강상훈;김동환;강시용;류기중
    • 한국응용곤충학회지
    • /
    • 제40권2호
    • /
    • pp.105-109
    • /
    • 2001
  • 귤응애의 예찰방법을 개발하기 위하여 제주지역의 온주밀감원에서 귤응애 분산형태에 대해 2개년(1999~2000년)에 걸쳐 잎 표본에 대하여 각 조사일에 평균밀도를 조사하였다. Taylor's power law와 Iwao's patchiness regression을 이용하여 분산지수를 비교하였으며, 잎 표본 조사에서는 일반적으로 Taylor's power law가 Iwao's patchiness regression보다 평균-분산 관계를 더 잘 나타내었다. Taylor's power law의 기울기와 절편은 조사한 포장 간에 차이가 없었으며, 여기에서 얻어진 상수값을 이용하여 잎 표본 조사에 의한 귤응애 약 .성충에 대한 고정정확도수준에서의 표본조사법을 개발하였다. 이 조사법에 대해 resampling 기법을 이용하여 독립된 4개의 조사자료를 이용하여 분석한 결과 실질 고정정확도(D)값이 요구되는 D값보다 항상 낮았으며, 나무당 귤응애 밀도가 8마리 이상에서 필요한 조사 나무수는 18주보다 작았다.

  • PDF