• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
• /
• pp.211-214
• /
• 1996

This paper propose a method for pattern recogniton using spectrum analyzer and fuzzy ARTMAP. Contour sequences obtained from 2-D planar images represent the Euclidean distance between the centroid and all boundary pixels of the shape, and are related to the overall shape of the images. The Fourier transform of contour sequence and spectrum analyzer are used as a means of feature selection and data reduction. The three dimensional spectral feature vectors are extracted by spectrum analyzer from the FFT spectrum. These Spectral feature vectors are invariant to shape translation, rotation, and scale transformations. The fuzzy ARTMAP neural network which is combined with two fuzzy ART modules is trained and tested with these feature vectors. The experiments include 4 aircrafts and 4 industrial parts recognition process are presented to illustrate the high performance of this proposed method in the ion problems of noisv shapes.

• 한국의류산업학회지
• /
• 제15권4호
• /
• pp.620-629
• /
• 2013

This study examines the rustling sound characteristics of electrospun nanofiber web laminates according to layer structures. This study assesses mechanical properties and frictional sounds (such as SPL); in addition, Zwicker's psychoacoustic parameters (such as Loudness (Z), Sharpness (Z), Roughness (Z), and Fluctuation strength (Z)) were calculated using the Sound Quality Program (ver.3.2, B&K, Denmark). The result determined how to control these characteristics and minimize rustling sounds. A total of 3 specimens' frictional sound (generated at 0.63 m/s) was recorded using a Simulator for Frictional Sound of Fabrics (Korea Patent No. 10-2008-0105524) and SPLs were analyzed with a Fast Fourier Transformation (FFT). The mechanical properties of fabrics were measured with a KES-FB system. The SPL value of the sound spectrum showed 6.84~58.47dB at 0~17,500Hz. The SPL value was 61.2dB for the 2-layer PU nanofiber web laminates layered on densely woven PET(C1) and was the highest at 65.1dB for the 3-layer PU nanofiber web laminates (C3). Based on SPSS 18.0, it was shown that there is a correlation between mechanical properties and psychoacoustic characteristics. Tensile properties (LT), weight (T), and bending properties (2HB) showed a high correlation with psychoacoustic characteristics. Tensile linearity (LT) with Loudness (Z) showed a negative correlation coefficient; however, weight (T) with Sharpness (Z) and Roughness (Z), and bending hysteresis (2HB) with Roughness (Z) indicated positive correlation coefficients, respectively.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 춘계종합학술대회
• /
• pp.227-230
• /
• 2007

SAR의 마이크로파를 이용하면 악 기상환경 및 주야간에도 해양의 관측이 가능하다. SAR의 해양표면에 대한 영상은 표면바람장과 관련된 대기적 현상에 관한 많은 정보를 가지고 있다. SAR로부터 추출되는 풍속의 정보는 다양하게 이용된다. SAR 영상으로부터 해상풍을 산출하기 위해서는 바람산출모델에 SAR 영상으로부터 추출한 풍향 자료와 후방산란계수 값을 입력하여 풍속을 산출한다. SAR 영상으로부터 구한 파향 스펙트럼은 항상 파향에 있어서 $180^{\circ}$의 상반된 두 정점을 보여주는데 이는 영상에 적용한 2차원 FFT의 결과이다. 파향에 있어서의 이러한 모호성은 육지의 위치라든지, 바람의 방향 혹은 수치모델 결과 등을 이용하여 결정하여야 한다. 이전에는 ENV14.0 을 이용해서 RadarSat-1 SAR 영상으로부터 DN 값을 추출한 후 다시 SN(Sigma Nought)으로 변환하는 것은 각각의 파일들을 수동적으로 처리를 해야 했기 때문에 많은 시간이 들었다. 이러한 수동적인 작업을 프로그램을 작성해서 SN(Sigma Nought) 값으로 변환을 하였다. 그 후 SN(Sigma Nought)로부터 풍향을 산출하는 과정에 있으며, 현재 풍향은 $180^{\circ}$의 모호성을 갖고 있기 때문에 좀 더 연구가 필요한 상황이다.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1997년도 추계학술대회
• /
• pp.555-558
• /
• 1997

A new approach to silent MR imaging using a rotating DC gradient has been explored and experimentally studied. As is known, acoustic or sound noise has been one of the major problems in handling patients, mainly due to the fast gradient pulsings in interaction with the main magnetic field. The sound noise is also proportionally louder as the magnetic field strength becomes larger. In this article, we have described a new imaging technique using a mechanically rotating DC gradient coil as an approach toward silent MR imaging, i.e., a mechanically rotated DC gradient effectively replaces both the phase encoding as well as the readout gradient pulsings and data obtained in this manner provides a set of project ion data which later can be used or the projection reconstructionorwithsomeinterpolation techniques one can also perform conventional 2-D FFT (Fast Fourier Transform) image reconstruction. We found, with this new technique, that the sound noise intensity compared with the conventional imaging technique, such as spin echo sequence, is reduced down to -20.7 dB or about 117.5 times. The experimental pulse sequence and its principle are described and images obtained by the new silent MR imaging technique are reported.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권3호
• /
• pp.121-138
• /
• 2024

Artificial intelligence is crucial to manufacturing productivity. Understanding the difficulties in producing disruptions, especially in linear feed robot systems, is essential for efficient operations. These mechanical tools, essential for linear movements within systems, are prone to damage and degradation, especially in the LM guide, due to repetitive motions. We examine how explainable artificial intelligence (XAI) may diagnose wafer linear robot linear rail clearance and ball screw clearance anomalies. XAI helps diagnose problems and explain anomalies, enriching management and operational strategies. By interpreting the reasons for anomaly detection through visualizations such as Class Activation Maps (CAMs) using technologies like Grad-CAM, FG-CAM, and FFT-CAM, and comparing 1D-CNN with 2D-CNN, we illustrates the potential of XAI in enhancing diagnostic accuracy. The use of datasets from accelerometer and torque sensors in our experiments validates the high accuracy of the proposed method in binary and ternary classifications. This study exemplifies how XAI can elucidate deep learning models trained on industrial signals, offering a practical approach to understanding and applying AI in maintaining the integrity of critical components such as LM guides in linear feed robots.

• 한국기계가공학회지
• /
• 제18권9호
• /
• pp.29-35
• /
• 2019

The structure of the machinery industry due to the 4th industrial revolution is changing from precision and durability to intelligent and smart machinery through sensing and interconnection(IoT). There is a growing need for research on prognostics and health management(PHM) that can prevent abnormalities in processing machines and accurately predict and diagnose conditions. PHM is a technology that monitors the condition of a mechanical system, diagnoses signs of failure, and predicts the remaining life of the object. In this study, the vibration generated during machining is measured and a classification algorithm for normal and fault signals is developed. Arbitrary fault signal is collected by changing the conditions of un stable supply cutting oil and fixing jig. The signal processing is performed to apply the measured signal to the learning model. The sampling rate is changed for high speed operation and performed machine learning using raw signal without FFT. The fault classification algorithm for 1D convolution neural network composed of 2 convolution layers is developed.

• 한국전자파학회논문지
• /
• 제16권4호
• /
• pp.427-437
• /
• 2005

본 논문에서는 디지털 방송에서 요구되는 디지털 오디오 레벨에 대한 주관적 음향 레벨, 즉 라우드니스의 계측 알고리즘을 실시간화 하는 방법을 제안한다. 이를 위해 객관적 오디오 품질 분석을 위한 권고안인 ITU-RBS1387-1의 분석 결과를 토대로 FFT 기반의 라우드니스 계측 알고리즘을 구현하고, 이 알고리즘을 참조테이블(look-up table)을 이용하여 실시간화 하는 방법을 제시하였다. 그리고 이 알고리즘의 성능과 계측 시간 분석을 위해 23개의 순음과 30개의 디지털사운드 샘플을 적용하고, 그 결과를 분석하였다. 실험결과를 살펴보면, 실시간화 된 알고리즘의 계측값은 실시간화 방법이 적용되지 않은 원래 알고리즘과 비교할 때, spectral spreading관련 참조테이블의 레벨 해상도가 $10\;\cal{dB}$로 상당히 큰 경우에도 $2\;\%$미만의 차이를 보여 매우 양호한 측정 결과를 보였다. 계측 시간의 감소 효과를 살펴보면, 알고리즘 전체적으로는 1/21 정도로 실행시간이 줄었으며, 가장 계측시간 점유비율이 근 청각필터 그룹변 에너지 계산 시간은 1/450로 줄어들고, 여기 패턴을 구하는 계산 시간도 약1/3.57로 좋은 계측 시간 단축 효과를 얻었다. 결론적으로 제안한 알고리즘을 통해 향후 DSP 기반의 완전 실시간 라우드니스 미터를 구현할 가능성을 확보하게 되었다.

• 한국지능시스템학회논문지
• /
• 제19권6호
• /
• pp.743-748
• /
• 2009

본 논문은 2차원 연속 웨이블릿을 이용하여 조명에 의한 불균일한 휘도성분을 제거하여 TFT Display 핵심 부품인 편광필름 영상내의 결함을 검사 할 수 있는 방법을 제안한다. 영상 신호는 불균일한 휘도 분포와 노이즈 신호, 그리고 결함 신호로 구성되어 있다. 영상의 2차원 웨이블릿 변환은 스케일이 다른 여러 성분이 중첩된 다해상도 구조를 형성한다. 본 논문에서는 1차원 미분 가우시안 웨이블릿을 적용하여 영상에 중첩되어 있는 다해상도 성분 중 배경 휘도 성분을 효율적으로 추출하여 제거하는 전처리 기법을 제안한다. 이를 이용하여 원 영상에서 배경 성분을 분리할 수 있어 보다 신뢰성 있게 결함을 검출할 수 있다.

• 한국전산유체공학회:학술대회논문집
• /
• 한국전산유체공학회 2011년 춘계학술대회논문집
• /
• pp.407-413
• /
• 2011

VIC (Vortex-In-Cell) method for viscous incompressible flow is presented to simulate the wake behind a modified NACA16 foil. With uniform rectangular grid, the velocity in field is calculated using streamfunction from vorticity field by solving the Poisson equation in which FFT(Fast Fourier Transform) is combined with 2nd order finite difference scheme. Here, LES(Large Eddy Simulation) with Smagorinsky model is applied for turbulence calculation. Effective viscosity is formulated using magnitude of strain tensor(or vorticity). Then the turbulent diffusion as well as viscous diffusion becomes particle strength exchange(PSE) with averaged eddy viscosity. The well-established panel method is combined to obtain the irrotational velocity and to apply the no-penetration boundary condition on the body panel. And wall diffusion is used for no-slip condition numerical results of turbulent stresses are compared with experimental results (Bourgoyne, 2003). Before comparing process, LES(Large Eddy Simulation) SGS(Subgrid scale) stress is transformed Reynolds averaged stress (Winckelmans, 2001).

• 자원환경지질
• /
• 제33권2호
• /
• pp.101-109
• /
• 2000

The gravity measurement has been carried out to study the deep geologic structure at 331 gravity stations with an interval of 1∼1.5 km along the national road which crosses the southern part of the Korean peninsula from Pohang to Manripo. The Bouguer gravity anomalies were obtained from the observed gravity values, and interpreted by means of upward continuation using FFT (Fast Fourier Transform), Fourier-series method and nonlinear 2-D inversion method to determine the depths of Conrad and Moho discontinuities. The linear regression relations between elevations and gravity anomalies were also obtained to test isostasy in the study area. The depth of Conrad discontinuty is 13km between Pohang and Daegu, 16.5 km between Kimchon and Okchon, 9.7 km between Okchon and Daejeon, and 16.3 km near Manripo. The depth of Moho discontinuty is 32km between Pohang and Daegu, 35 km between Kimchon and Okchon, 28.7 km between Okchon and Daejeon, 40.5 km between Daejeon and Kongju, and 34.5 km between Kongju and Manripo. The result of testing isotasy indicates that the crust of this area seems to be not in perfect isostatic equilibrium but in a little undercompensated sate.