基于快速極限學(xué)習(xí)機和差分進化的機場噪聲預(yù)測模型
doi: 10.11999/JEIT150986
-
2.
(中國民航大學(xué)計算機科學(xué)與技術(shù)學(xué)院 天津 300300) ②(南京航空航天大學(xué)計算機科學(xué)與技術(shù)學(xué)院 南京 210016) ③(鹽城師范學(xué)院信息工程學(xué)院 鹽城 224002)
基金項目:
國家自然科學(xué)基金重點項目(61139002)，國家科技支撐計劃課題(2014BAJ04B02)，中央高?；究蒲袠I(yè)務(wù)費專項資金(3122014D032)，中國民航信息技術(shù)科研基地開放基金課題(CAAC- ITRB-201401)
Prediction Model of Airport?Noise Based on Fast Extreme Learning Machine and Differential Evolution
Funds:
The Key Program of the National Natural Science Foundation of China (61139002), The National Key Technology Research and Development Program of the Ministry of Science and Technology of China (2014BAJ04B02), The Fundamental Research Funds for the Central Universities of Ministry of Education of China (3122014D032), The Open Project Foundation of Information Technology Research Base of Civil Aviation Administration of China (CAAC-ITRB-201401)
-
摘要: 該文針對傳統(tǒng)機場噪聲預(yù)測模型存在的建模成本高、實用性差的不足，引入時間序列相空間重構(gòu)理論，提出一種新的基于快速極限學(xué)習(xí)機和差分進化算法的機場噪聲一體化預(yù)測模型。該模型利用相空間重構(gòu)理論對機場噪聲時間序列進行重構(gòu)，并使用快速極限學(xué)習(xí)機對重構(gòu)的相空間矢量進行學(xué)習(xí)建模，同時采用改進的差分進化算法實現(xiàn)對重構(gòu)參數(shù)和模型參數(shù)的同步優(yōu)化選擇，整個建模過程簡潔高效，無需人工干預(yù)。實驗結(jié)果表明，該一體化預(yù)測模型能較好地跟蹤機場噪聲的變化趨勢，且具有較同類模型更小的預(yù)測誤差。
-
關(guān)鍵詞:
- 機場噪聲預(yù)測 /
- 快速極限學(xué)習(xí)機 /
- 差分進化 /
- 相空間重構(gòu)
Abstract: Traditional airport noise prediction models are insufficient for their high modeling cost and poor practicability. In this paper, the time series phase space reconstruction theory is introduced, and a novel integrated airport noise prediction model based on fast extreme learning machine and differential evolution is proposed. In the proposed model, the airport noise time series is reconstructed based on the phase space reconstruction theory, and the fast extreme learning machine is used to model the reconstructed phase space vector. Meanwhile, an improved differential evolution algorithm is adopted to search for the optimal parameter combination of phase space reconstruction parameter and model parameter simultaneously. The whole modeling process of the integrated prediction model is very simple and?efficient without any manual?intervention. Experimental results demonstrate that the proposed model can track the variation tendency of airport noise well and can achieve much more accurate prediction results than its counterparts. -
SARI D, OZKURT N, AKDAG A, et al. Measuring the levels of noise at the Atatrk Airport and comparisons with model simulations[J]. Science of The Total Environment, 2014, 482(6): 472-479. doi: 10.1016/j.scitotenv.2013.07.091. OZKURT N, HAMAMCI S F, and SARI D. Estimation of airport noise impacts on public health. A case study of Adnan Menderes Airport[J]. Transportation Research Part D: Transport and Environment, 2015, 36(5): 152-159. doi: 10. 1016/j.trd.2015.02.002. 陳海燕, 楊冰欣, 徐濤, 等. 基于模糊支持向量回歸的機場噪聲預(yù)測[J]. 南京航空航天大學(xué)學(xué)報, 2013, 45(5): 722-726. CHEN Haiyan, YANG Bingxin, XU Tao, et al. Airport noise prediction based on fuzzy support vector regression[J]. Journal of Nanjing University of Aeronautics Astronautics, 2013, 45(5): 722-726. FILIPPONE A and BERTSCH L. Comparison of aircraft noise models with flyover data[J]. Journal of Aircraft, 2014, 51(3): 1043-1047. doi: 10.2514/1.C032368. GUARNACCIA C, QUARTIERI J, TEPEDINO C, et al. An analysis of airport noise data using a non-homogeneous Poisson model with a change-point[J]. Applied Acoustics, 2015, 91(4): 33-39. doi: 10.1016/j.apacoust.2014.12.002. FILIPPONE A. Aircraft noise prediction[J]. Progress in Aerospace Sciences, 2014, 68(7): 27-63. doi: 10.1016/ j.paerosci.2014.02.001. 徐濤, 燕憲金, 楊國慶. 基于神經(jīng)網(wǎng)絡(luò)集成的單個飛行事件噪聲預(yù)測模型[J]. 中國環(huán)境科學(xué), 2014, 34(2): 539-544. XU Tao, YAN Xianjin, and YANG Guoqing. Prediction model of noise event for single flight based on neural network ensemble[J]. China Environmental Science, 2014, 34(2): 539-544. 徐濤, 楊奇川, 呂宗磊. 一種基于動態(tài)集成學(xué)習(xí)的機場噪聲預(yù)測模型[J]. 電子與信息學(xué)報, 2014, 36(7): 1631-1636. doi: 10.3724/SP.J.1146.2013.01410. XU Tao, YANG Qichuan, and LU Zonglei. A prediction model of airport noise based on the dynamic ensemble learning[J]. Journal of Electronics Information Technology, 2014, 36(7): 1631-1636. doi: 10.3724/SP.J.1146.2013.01410. STORN R and PRICE K. Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces[J]. Journal of Global Optimization, 1997, 11(4): 341-359. doi: 10.1023/A:1008202821328. HUANG G B, ZHU Q Y, and Siew C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1): 489-501. doi: 10.1016/j.neucom.2005.12.126. HOUGH P D and VAVASIS S A. Complete orthogonal decomposition for weighted least squares[J]. SIAM Journal on Matrix Analysis and Applications, 1997, 18(2): 369-392. doi: 10.1137/S089547989528079X. GOLUB G H and VAN LOAN C F. Matrix Computations[M]. Baltimore: JHU Press, 2012: 274-283. PACKARD N H, CRUTCHFIELD J P, FARMER J D, et al. Geometry from a time series[J]. Physical Review Letters, 1980, 45(9): 712-716. doi: 10.1103/PhysRevLett.45.712. TAKENS F. Detecting strange attractors in turbulence[J]. Dynamical Systems and Turbulence, 1981, 898(1): 366-381. KAYACAN E, ULUTAS B, and KAYNAK O. Grey system theory-based models in time series prediction[J]. Expert Systems with Applications, 2010, 37(2): 1784-1789. doi: 10.1016/j.eswa.2009.07.064. ZHANG N, WILLIAMS C, and BEHERA P. Water quantity prediction using least squares support vector machines (LS-SVM) Method[J]. Journal of Systemics, Cybernetics and Informatics, 2014, 2(4): 53-58. AFSHAR K and BIGDELI N. Data analysis and short term load forecasting in Iran electricity market using singular spectral analysis (SSA)[J]. Energy, 2011, 36(5): 2620-2627. doi: 10.1016/j.energy.2011.02.003. 溫冬琴, 王建東. 基于奇異譜分析的機場噪聲時間序列預(yù)測模型[J]. 計算機科學(xué), 2014, 41(1): 267-270. WEN Dongqin and WANG Jiandong. Prediction model for airport-noise time series based on SSA[J]. Computer Science, 2014, 41(1): 267-270. -
計量
- 文章訪問數(shù): 1371
- HTML全文瀏覽量: 180
- PDF下載量: 376
- 被引次數(shù): 0
下載:
