Page 132 - 201806

962 2018 年 11 月

于GA-SVR中建立风电机组噪声预测模型。实验结 motor noise characteristics based on neural netword[J].
果表明，基于改进的 GA-SVR结合多源数据特征级 Journal of Vibration and Shock, 2004, 23(4): 51–57.
[10] 梁栋, 张凤琴, 陈大武, 等. 一种基于决策树和遗传算法 -BP
融合理论的思想，建立了预测模型并对风电机组噪
神经网络的组合预测模型 [J]. 中国科技论文, 2015, 10(2):
声进行预测仿真，得到了较为精确的预测结果，其相 169–174.
对误差也较小，可以为风电机组的噪声信号检测及 Liang Dong, Zhang Fengqin, Chen Dawu, et al. A com-
早期故障诊断研究提供一定的参考。 posite prediction model based on decision tree and GA-
BPNN[J]. China Sciencepaper, 2015, 10(2): 169–174.
[11] Xu L F, Zhao Q, Chen Y R, et al. Single spectrum end
参 考 文 献 point predict of BOF with SVM[J]. World Academy of Sci-
ence, Engineering and Technology, 2010, 4(2): 189–191.
[12] 王晓景, 黎敏, 阳建宏, 等. 结合相空间和 LS-SVM 的风机状
[1] 吴宏钢. 风力发电机组振动检测及噪声评估研究 [D]. 重庆:
态预测方法 [J]. 中国科技论文, 2013, 8(8): 743–746.
重庆大学, 2010.
Wang Xiaojing, Li Min, Yang Jianhong, et al. Trend pre-
[2] Kuwano S, Yano T, Kageyama T, et al. Social survey on
diction for condition of fans based on phase space and least
wind turbine noise in Japan[J]. Noise Control Engineering
squares support vector machine[J]. China Sciencepaper,
Journal, 2014, 62(6): 503–520.
2013, 8(8): 743–746.
[3] Son E, Kim H, Kim H, et al. Integrated numerical
[13] GB/T 22516-2008/IEC 61400-11:2002 风力发电机组噪声
method for the prediction of wind turbine noise and the
测量方法 [S].
long range propagation[J]. Current Applied Physics, 2010,
[14] Atici U. Prediction of the strength of mineral admixture
10(2): S316–S319.
concrete using multivariable regression analysis and an
[4] Tachibana H. Outcome of systematic research on wind
artificial neural network[J]. Expert Systems with Appli-
turbine noise in Japan[C]. Inter-Noise 2014, Australian
cations, 2011, 38(8): 9609–9618.
Acoustical Society, 2014.
[15] Alin A. Multicollinearity[J]. Wiley Interdisciplinary Re-
[5] 徐冠基, 柏林, 刘小峰, 等. 基于多元线性回归分析的风机噪
view: Computational Statistics, 2010, 2(3): 370–374.
声预测的研究 [J]. 中国测试, 2010, 36(5): 21–23.
[16] 彭珊. 线性回归模型中关于异常点的若干问题的分析 [D]. 哈
Xu Guanji, Bo Lin, Liu Xiaofeng, et al. Research on noise
尔滨: 东北林业大学, 2014.
prediction of wind turbine based on multiple linear regres-
sion analysis[J]. China Measurement & Test, 2010, 36(5): [17] 化柏林, 李广建. 大数据环境下多源信息融合的理论与应用探
讨 [J]. 图书情报工作, 2015, 59(16): 5–10.
21–23.
[6] 程静, 王维庆, 何山. 基于回归分析与 BP 神经网络的风机噪 Hua Bolin, Li Guangjian. Discussion on theory and ap-
声预测 [J]. 噪声与振动控制, 2013, 33(6): 49–52, 123. plication of multi-source information fusion in big data
Cheng Jing, Wang Weiqing, He Shan. Noise prediction of environment[J]. Library and Information Service, 2015,
59(16): 5–10.
wind turbines based on regeression analysis and BP neu-
ral network[J]. Noise and Vibration Control, 2013, 33(6): [18] 刘同明, 夏祖勋, 解洪成. 数据融合技术及其应用 [M]. 北京:
49–52, 123. 国防工业出版社, 1988.
[7] Liu H, Mi X W, Li Y F. Comparison of two new intelli- [19] Baydaroglu O, Kocak K. SVR-based prediction of evapo-
gent wind speed forecasting approaches based on wavelet ration combined with chaotic approach[J]. Journal of Hy-
packet decomposition, complete ensemble empirical mode drology, 2014, 508(508): 356–363.
decomposition with adaptive noise and artificial neural [20] Sanz-Garcia A, Femandez-Ceniceros J, Antonanzas-
networks[J]. Energy Conversion and Management, 2018, Torres F, et al. GA-PARSIMONY: A GA-SVR approach
155: 188–200. with feature selection and parameter optimization to ob-
[8] 郭伟, 左曙光, 陈瑞峰, 等. 风机非稳态噪声信号分析 [J]. 噪 tain parsimonious solutions for predicting temperature
声与振动控制, 2010, 30(1): 78–81. settings in a continuous annealing furnace[J]. Applied Soft
Guo Wei, Zuo Shuguang, Chen Ruifeng, et al. Analysis Computing, 2015, 35: 13–28.
of unsteady noise signal of fans[J]. Noise and Vibration [21] Gao R Z, Zhang J J, Shang Y M, et al. An improve genetic
Control, 2010, 30(1): 78–81. algorithm based on fixed point algorithms[J]. Journal of
[9] 蒋伟康, 严莉. 基于神经网络的电机噪声性能在线检测技术研 Computers, 2012, 7(5): 1109–1115.
究 [J]. 振动与冲击, 2004, 23(4): 51–57. [22] 胡良平. 现代统计学与 SAS 应用 [M]. 北京: 军事医学科学出
Jiang Weikang, Yan Li. Resear on online detection of 版社, 2000.