• International Journal of Advanced Culture Technology
• /
• 제11권4호
• /
• pp.393-405
• /
• 2023

Accurate prediction of wind speed and power is vital for enhancing the efficiency of wind energy systems. Numerous solutions have been implemented to date, demonstrating their potential to improve forecasting. Among these, deep learning is perceived as a revolutionary approach in the field. However, despite their effectiveness, the noise present in the collected data remains a significant challenge. This noise has the potential to diminish the performance of these algorithms, leading to inaccurate predictions. In response to this, this study explores a novel feature engineering approach. This approach involves altering the data input shape in both Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) and Autoregressive models for various forecasting horizons. The results reveal substantial enhancements in model resilience against noise resulting from step increases in data. The approach could achieve an impressive 83% accuracy in predicting unseen data up to the 24th steps. Furthermore, this method consistently provides high accuracy for short, mid, and long-term forecasts, outperforming the performance of individual models. These findings pave the way for further research on noise reduction strategies at different forecasting horizons through shape-wise feature engineering.

• 한국태양에너지학회 논문집
• /
• 제32권2호
• /
• pp.87-94
• /
• 2012

In this study, we found a relationship between wind shear exponent, ${\alpha}$, and a few factors such as the wind speed, $V$, ruggedness index($RIX$), and the Weibull shape parameter, $k$ of sites in complex terrain in Korea. Wind shear exponents in main wind directions were calculated using wind speed data measured for one year from various heights of eleven meteorological masts in Gangwon province. It was found from the analysis that the reciprocal of the wind shear exponent can be expressed by an exponentially decaying function with respect to a multiple of $V$, $RIX$ and $k$. This result is considered useful to be used to characterize wind characteristics of specific sites in complex terrain in Korea with limited information.

• 대한기계학회논문집B
• /
• 제20권1호
• /
• pp.255-265
• /
• 1996

Up to the present the study on the performance prediction of HAWT was performed mainly by assuming the axial flow. So in this paper we aimed at the fully non-axial flow of HAWT. For this purpose, we defined the wind turbine pitch angle in addition to the yaw angle to specify the arbitrary wind direction. And we adopted the Glauert method as the basic analysis method then modified this method suitably for our goal. By comparing the computational results obtained by this modified new Glauert method with the experimental results, it was proved that our method was a very efficient method. And on the basis of the reliability of this method we considered the effect of all the design parameters and presented the optimum blade geometry and the optimum operating condition to gain the best performance curve.

• 대한토목학회논문집
• /
• 제29권3A호
• /
• pp.209-216
• /
• 2009

풍하중이 지배적인 구조물의 경우에 정확한 설계풍속의 산정은 구조적 안정성뿐만 아니라 경제성까지도 좌우하게 된다. 본 연구에서는 광양대교 현장에 설치된 관측탑에서 약 1년간 측정한 풍속을 사용하여 풍환경을 분석하였고, MCP(Measure-Correlate-Predict) 방법을 적용하여 관측치로부터 장기 풍속을 추정하였다. 그 결과를 보면, 광양만은 바다이지만 개활지에 가까운 풍속 특성을 나타내고 있으며, 조도지수는 고도에 따라 달라지는 것으로 나타났다. 아울러 풍향에 따라 난류강도와 조도지수가 상당히 차이나는 것으로 나타났다. MCP 방법으로 추정한 200년빈도 설계풍속은 초기설계치보다 20 m/s이상 낮았으며, 실측된 풍속과 거스트계수를 고려한 설계풍하중은 초기설계치의 36%밖에 안되는 것으로 나타났다. 이를 볼 때 국부적인 지형의 영향으로 추정한 교량 현장의 풍환경과 직접 측정한 풍환경은 차이가 나므로, 경제적이고 안전한 설계를 위해서는 단기간이라도 현장 풍환경 관측이 필요하다고 판단된다.

• 한국환경과학회지
• /
• 제21권4호
• /
• pp.517-533
• /
• 2012

This study calculated wind speed at the height of 10 m using a disaster prediction model(Florida Public Hurricane Loss Model, FPHLM) that was developed and used in the United States. Using its distributions, a usable information of surface wind was produced for the purpose of disaster prevention when the typhoon attack. The advanced research version of the WRF (Weather Research and Forecasting) was used in this study, and two domains focusing on South Korea were determined through two-way nesting. A horizontal time series and vertical profile analysis were carried out to examine whether the model provided a resonable simulation, and the meteorological factors, including potential temperature, generally showed the similar distribution with observational data. We determined through comparison of observations that data taken at 700 hPa and used as input data to calculate wind speed at the height of 10 m for the actual terrain was suitable for the simulation. Using these results, the wind speed at the height of 10 m for the actual terrain was calculated and its distributions were shown. Thus, a stronger wind occurred in coastal areas compared to inland areas showing that coastal areas are more vulnerable to strong winds.

• 농업과학연구
• /
• 제47권4호
• /
• pp.1029-1037
• /
• 2020

The machine learning algorithm has been widely used in water-related fields such as water resources, water management, hydrology, atmospheric science, water quality, water level prediction, weather forecasting, water discharge prediction, water quality forecasting, etc. However, water quality prediction studies based on the machine learning algorithm are limited compared to other water-related applications because of the limited water quality data. Most of the previous water quality prediction studies have predicted monthly water quality, which is useful information but not enough from a practical aspect. In this study, we predicted the dissolved oxygen (DO) using recurrent neural network with long short-term memory model recurrent neural network long-short term memory (RNN-LSTM) algorithms with hourly- and daily-datasets. Bugok Bridge in Oncheoncheon, located in Busan, where the data was collected in real time, was selected as the target for the DO prediction. The 10-month (temperature, wind speed, and relative humidity) data were used as time prediction inputs, and the 5-year (temperature, wind speed, relative humidity, and rainfall) data were used as the daily forecast inputs. Missing data were filled by linear interpolation. The prediction model was coded based on TensorFlow, an open-source library developed by Google. The performance of the RNN-LSTM algorithm for the hourly- or daily-based water quality prediction was tested and analyzed. Research results showed that the hourly data for the water quality is useful for machine learning, and the RNN-LSTM algorithm has potential to be used for hourly- or daily-based water quality forecasting.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 정기총회 및 추계학술대회 논문집
• /
• pp.150-157
• /
• 2011

Nowadays, high speed train has settled down as a fast and convenient environment-friendly transportation and it's need is gradually increasing. However increased train speed leads to increased aerodynamic noise, which causes critically affects comfortability of passengers. Especially, the pantograph of high speed train is protruded out of train body, which is the main factor for increased aerodynamic noise. Since aerodynamic noise caused pantograph should be measured in high speed, it is difficult to measure it and to analysis aerodynamic noise characteristics due to the various types of pantograph. In this research, aerodynamic noise of pantograph is predicted by CFD (Computational Fluid Dynamic) and FW-H (Ffowcs Williams-Hawkings) equation. Also, Wind tunnel test results and numerical simulation results were compared. As a result, Simulation results predicting sound pressure level is very similar with wind tunnel test result. This research will draw major factor in aerodynamic noise of pantograph and will be utilized for predict sound pressure level of pantograph.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2007년도 춘계학술대회 논문집
• /
• pp.119-125
• /
• 2007

The equation of Resistance to motion of the Korean high-speed train has been calculated and evaluated using train speed measurements gathered from coasting tests in the speed range from 30km/h to 300km/h and wind tunnel test of 1/25th scale model. The factors of resistance to motion have been decomposed into various coefficients which compose the coefficients of Davis equation referring the general resistance to motion equation of KTX train. The coefficients of Korean high-speed train has been calculated using the measurements of coasting tests and the results of wind tunnel test has been implemented to consider the minor shape modification after the coasting tests.

• 한국환경과학회지
• /
• 제18권8호
• /
• pp.927-932
• /
• 2009

Wind turbine noise become main environmental problem as wind energy have been installed all around. Noise from large wind turbine give annoyance to listener, moreover it increase loading to whole system by restricting blade tip speed. However accurate noise mechanism of wind turbine is not yet examined. This paper reviewed noise source and analysis theory. Broadband noise if main component of wind turbine noise and airfoil self noise is main noise source. These make acoustic analogy hard to apply for analysis. For this reason, experimental equation is method for wind turbine noise prediction up to now. Spectrum analysis shows that vortex shedding noise exists around $1k{\sim}2k$ Hz. This region is most sensitive frequency range to human. Thus it is necessary to reduce this noise source.

• Wind and Structures
• /
• 제5권2_3_4호
• /
• pp.151-164
• /
• 2002

Predictions of the pedestrian level wind speeds for the downtown area of Auckland that have been obtained by wind tunnel and computational fluid dynamic (CFD) modelling are presented. The wind tunnel method involves the observation of erosion patterns as the wind speed is progressively increased. The computational solutions are mean flow calculations, which were obtained by using the finite volume code PHOENICS and the $k-{\varepsilon}$ turbulence model. The results for a variety of wind directions are compared, and it is observed that while the patterns are similar there are noticeable differences. A possible explanation for these differences arises because the tunnel prediction technique is sensitivity to gust wind speeds while the CFD method predicts mean wind speeds. It is shown that in many cases the computational model indicates high mean wind speeds near the corner of a building while the erosion patterns are consistent with eddies being shed from the edge of the building and swept downstream.