• Wind and Structures
• /
• 제36권6호
• /
• pp.423-434
• /
• 2023

Aerodynamic force coefficients are generally obtained from traditional wind tunnel tests or computational fluid dynamics (CFD). Unfortunately, the techniques mentioned above can sometimes be cumbersome because of the cost involved, such as the computational cost and the use of heavy equipment, to name only two examples. This study proposed to build a deep neural network model to predict the aerodynamic force coefficients based on data collected from CFD simulations to overcome these drawbacks. Therefore, a series of CFD simulations were conducted using different geometric parameters to obtain the aerodynamic force coefficients, validated with wind tunnel tests. The results obtained from CFD simulations were used to create a dataset to train a multilayer perceptron artificial neural network (ANN) model. The models were obtained using three optimization algorithms: scaled conjugate gradient (SCG), Bayesian regularization (BR), and Levenberg-Marquardt algorithms (LM). Furthermore, the performance of each neural network was verified using two performance metrics, including the mean square error and the R-squared coefficient of determination. Finally, the ANN model proved to be highly accurate in predicting the force coefficients of similar bridge sections, thus circumventing the computational burden associated with CFD simulation and the cost of traditional wind tunnel tests.

• 대한소아치과학회지
• /
• 제23권4호
• /
• pp.788-799
• /
• 1996

The purpose of this study was to determine the accuracy of the prediction methods which are frequently used in the clinic, such as Moyers', Tanaka and Johnston's, Song's Hixon and Oldfather's, Kaplan's, Smith's. These prediction methods were compared to the data, which were obtained from 100 Kyung-Hee University students (50 males and 50 females) with normal occlusion of permanent dentition, using a retrospective statistical analysis. The standard periapical radiopgraphs for the lower premolars using 16-inch long cone technique and the yellow stone dental casts were taken from each samples. The mesiodistal widths of 4 incisors, canine, premolars were measured on the dental casts, and those of premolars were measured on the radiographs. The correlation coefficients, paired samples t-tests, regression coefficients between the actual measuredments of the samples and the predicted measurements of each methods were analyzed. The results obtained were as follows: 1. The prediction methods using periapical radiographs tended to show a stronger correlation than the methods using dental casts; the correlation coefficients between the actual widths of the lower canine and premolars and the predicted widths of the tested methods were higher in Smith, Kaplan, Hixon & Oldfater, and Tanaka & Johnston (p<0.001). 2. The Moyers' probability chart at 65 % showed a tendency toward the least difference between the actual measurements and the predicted widths of the lower canine and the premolars, and the methods of Smith, Kaplan, Tanaka & Johnston also showed a less difference. 3. By means of evaluation in correlation coefficients and paired smaples t-tests, the Smith and Tanaka & Johnston in male, and the Moyers' 65 % and Song in female showed a high tendency toward accurate methods. 4. The regression equations by models that are derived from the study were as follows: Male(Lt.) :Y=10.799+0.475X Femle(Lt.) :Y= 7.427+0.609X (Rt.) :Y=11.043+0.462X (Rt.) :Y= 8.475+0.556X 5. The regression equations by radiographs that are dericed from the study were as follows: Male(Lt.) :Y=6.5651+0.9720X Femle(Lt.) :Y=4.8656+1.0632X (Rt.) :Y=7.8610+0.9060X (Rt.) :Y=4.5483+1.0843X

• Computers and Concrete
• /
• 제29권 6호
• /
• pp.433-444
• /
• 2022

Concrete's compressive strength is widely studied in order to understand many qualities and the grade of the concrete mixture. Conventional civil engineering tests involve time and resources consuming laboratory operations which results in the deterioration of concrete samples. Proposing efficient non-destructive models for the prediction of concrete compressive strength will certainly yield advancements in concrete studies. In this study, the efficiency of using radial basis function neural network (RBFNN) which is not common in this field, is studied for the concrete compressive strength prediction. Complementary studies with back propagation neural network (BPNN), which is commonly used in this field, have also been carried out in order to verify the efficiency of RBFNN for compressive strength prediction. A total of 13 input parameters, including novel ones such as cement's and fly ash's compositional information, have been employed in the prediction models with RBFNN and BPNN since all these parameters are known to influence concrete strength. Three different train: test ratios were tested with both models, while different hidden neurons, epochs, and spread values were introduced to determine the optimum parameters for yielding the best prediction results. Prediction results obtained by RBFNN are observed to yield satisfactory high correlation coefficients and satisfactory low mean square error values when compared to the results in the previous studies, indicating the efficiency of the proposed model.

• 대한기계학회논문집A
• /
• 제33권3호
• /
• pp.210-217
• /
• 2009

This paper presents the analytical prediction of stability lobes in milling. The stability lobes are obtained by measuring the frequency response function (FRF) of a machining center at the cutting point of the end mill cutter, identifying cutting constants, and approximating cutting force coefficients. The stability lobes are experimentally verified through cutting tests.

• 대한의용생체공학회:의공학회지
• /
• 제10권2호
• /
• pp.83-88
• /
• 1989

This paper is a study on the design of adptive filter for QRS complex detection. We propose a simple adaptive algorithm to increase capability of noise cancelation in QRS complex detection with two stage adaptive filter. At the first stage, background noise is removed and at the next stage, only spectrum of QRS complex components is passed. Two adaptive filters can afford to keep track of the changes of both noise and QRS complex. Each adaptive filter consists of prediction error filter and FIR filter The impulse response of FIR filter uses coefficients of prediction error filter. The detection rates for 105 and 108 of MIT/BIH data base were 99.3% and 97.4% respectively.

• 방송공학회논문지
• /
• 제20권6호
• /
• pp.862-870
• /
• 2015

HEVC 표준에서 율-왜곡 최적화(RDO) 과정은 좋은 압축 성능을 보이지만 상대적으로 많은 부호화 시간이 요구된다. RDO 과정의 부호화 시간을 줄이기 위해서 본 논문에서는 변환 계수와 CBF(Coded Block Flag) 이용한 고속 인트라 예측 방법을 제안한다. 제안된 고속 인트라 압축방법은 HM16.0 참조SW의 RMD(Rough Mode Decision)를 통해 나온 인트라 예측모드의 후보 수를 3개로 줄이고 이산 여현 변환(Discrete Cosine Transform) 계수 분포와 비교하여 예측 모드의 수를 한 번 더 줄인다. 이후 RDO를 수행하기 전, 양자화된 DCT 계수값이 모두 0이 되는 후보가 있으면 RDO과정 없이 그 후보를 선택하는 방법이다. 제안된 방법은 HEVC 부호화 보다 비트율이 2.5% 중가했지만 평균 55%의 부호화 속도 향상을 얻는다.

• 전기학회논문지
• /
• 제59권4호
• /
• pp.759-761
• /
• 2010

In order to monitor operating performance of contaminated outdoor insulators, a wavelet-based flashover prediction method is proposed. In most cases, the low-frequency components, namely, fundamental, $3^{rd}$, and $5^{th}$ harmonic components have been mainly used for the sake of the spectral analysis of the leakage current. However, in this paper, the detail coefficients of wavelet transform representing high-frequency components are used as important information to predict a flashover in the contaminated insulator. Experimental results verify that the proposed method has a superior capability for flashover prediction.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.961-964
• /
• 1995

For geometric accuracy in the net shape machining, the problem of tool deflection should be resolved in some fashion. In particular, this is crucial in finish cut operation where slim tools are used. The purpose of this paper is to verify the validity and effectiveness of the prediction model of the machined surface. Experimental results are presented for the cut of steel material with HSS endmill of diameter 6mm on machining center. The results shows that 1) the machining error due totool deflection is serious even in the low cutting load, 2) by using the mechanistic simulation model with experimental coefficients, the machining error was predicted with maximum prediction error of 10% which was significantly reduced to the desired level by the path modification method.

• 한국항공운항학회지
• /
• 제19권1호
• /
• pp.24-28
• /
• 2011

This paper reviews a ceiling prediction method based on a mesoscale meteorological modeling system in South Korea. The study was motivated by the tendency of higher model ceiling height than the observed in daily operational forecasts. The goal of the paper is to report an effort to improve the operational ceiling prediction skill by conducting numerical experiments controlling a model parameter. In a case experiment, increasing constant values used in the relationship between extinction coefficients and concentration showed better performance, indicating a short-term strategy for operational local ceiling forecast improvement.

• 설비공학논문집
• /
• 제13권4호
• /
• pp.262-270
• /
• 2001

This paper deals with a prediction method for the condensation of ternary refrigerant mixture inside a horizontal smooth tube. Based on some reliable assumptions, the governing equations for the local heat and mass transfer characteristics are derived, and the prediction for the condensation of ternary zeotropic refrigerant mixtures composed of HFC32/HFC125/HFC134a, including R407C, is carried out. The local values of vapor quality, thermodynamic states at bulk vapor, vapor-liquid interface and bulk liquid, mass flux etc. are obtained for a constant wall temperature and a constant wall heat flux conditions, and the effects of the composition of HFC32/HFC125/HFC134a on heat transfer characteristics are examined. The prediction result is also compared with experimental data for condensation of ternary refrigerant mixtures. The predicted wall temperature distribution has a similar trend with experimental data but the predicted local heat transfer coefficients are 20-30% higher than the experimental data.