针对风力机叶片在各基本随机变量相互影响下强度极限状态难以界定的问题,提出广义回归神经网络正逆预测结合的风力机叶片强度可靠性分析方法。通过神经网络逆预测模型估算叶片失效时各随机变量状态,利用有限元分析法校核后作为强化样本用于神经网络正预测模型的训练。将该方法构建的神经网络模型与通过更多随机样本构建的模型进行比较。结果表明：前者的学习样本数量减少26%,测试集均方误差降低48.19%,平均绝对百分比误差降低58.24%,因此通过该方法构建的神经网络模型在叶片失效边界区域具有更好的预测性能。利用该模型计算叶片的强度可靠性,进一步验证了该方法的有效性。
Abstract
Aiming at the problem that the strength limit state of wind turbine blade is difficult to be defined under the mutual influence of each basic random variable, a wind turbine blade strength reliability analysis method combining forward and reverse prediction of generalized regression neural network was proposed. The states of each random variable at the time of blade failure were estimated by the reverse prediction model of the neural network, and then used as reinforcement samples for the training of the forward prediction model after calibrated by the finite element analysis method. The neural network model constructed by the above method was compared with that constructed by more random samples. The results show that the number of learning samples of the former is reduced by 26%, and the mean square error and mean absolute percentage error of the test set are reduced by 48.19% and 58.24%, respectively. Therefore, the neural network model constructed by this method has better prediction performance in the blade failure boundary region. Finally the strength reliability of the blade was calculated using the model, which further verified the effectiveness of the method.
关键词
风力机 /
叶片 /
可靠性 /
神经网络 /
强度分析 /
优化设计
Key words
wind turbines /
blades /
reliability /
neural networks /
strength analysis /
optimized design
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李永华, 陈鹏, 田宗睿, 等. 基于改进BP神经网络的结构可靠度计算方法[J]. 机械强度, 2021, 43(6): 1359-1365.
LI Y H, CHEN P, TIAN Z R, et al.Structure reliability calculation method based on improved neural network[J]. Journal of mechanical strength, 2021, 43(6): 1359-1365.
[2] 贾大卫, 吴子燕, 何乡. 基于BP神经网络和Laplace渐进积分法的结构可靠性计算[J]. 固体力学学报, 2021, 42(4): 476-489.
JIA D W, WU Z Y, HE X.A structural reliability analysis method based on the back propagation(BP) neural network and Laplace's method of progressive integration[J]. Chinese journal of solid mechanics, 2021, 42(4): 476-489.
[3] FERRARIO E, PEDRONI N, ZIO E, et al.Bootstrapped Artificial Neural Networks for the seismic analysis of structural systems[J]. Structural safety, 2017, 67: 70-84.
[4] ZHAO H L, YUE Z F, LIU Y S, et al.An efficient reliability method combining adaptive importance sampling and Kriging metamodel[J]. Applied mathematical modelling, 2015, 39(7): 1853-1866.
[5] LI X, GONG C L, GU L X, et al.A sequential surrogate method for reliability analysis based on radial basis function[J]. Structural safety, 2018, 73: 42-53.
[6] 陈松坤, 王德禹. 基于神经网络的蒙特卡罗可靠性分析方法[J]. 上海交通大学学报, 2018, 52(6): 687-692.
CHEN S K, WANG D Y.An improved Monte Carlo reliability analysis method based on neural network[J]. Journal of Shanghai Jiao Tong University, 2018, 52(6): 687-692.
[7] MARZABADI F R, MASDARI M, SOLTANI M R.Application of artificial neural network in aerodynamic coefficient prediction of subducted airfoil[J]. Journal of research in science and engineering, 2020, 2(1): 13-17.
[8] KHARAL A, SALEEM A.Neural networks based airfoil generation for a given using Bezier-PARSEC parameterization[J]. Aerospace science and technology, 2012, 23(1): 330-344.
[9] MEZIANE M A A, ABDELAZIZ H H, TOUNSI A. An efficient and simple refined theory for buckling and free vibration of exponentially graded sandwich plates under various boundary conditions[J]. Journal of sandwich structures & materials, 2014, 16(3): 293-318.
[10] 芦丽丽, 祁文军, 王良英, 等. 2 MW风机叶片的结构设计及静力学分析[J]. 材料科学与工艺, 2017, 25(3): 69-76.
LU L L, QI W J, WANG L Y, et al.Structural designs and statics analysis of 2 MW wind turbine blade[J]. Materials science and technology, 2017, 25(3): 69-76.
[11] 赵峰. 基于响应面法的风力机叶片强度可靠性分析[D]. 保定: 华北电力大学, 2010.
ZHAO F.Strength reliability analysis of wind turbine blade based on response surface method[D]. Baoding: North China Electric Power University, 2010.
[12] 刘旺玉, 张海全, 曾琳. 基于响应面法的仿生风力机叶片可靠性分析[J]. 太阳能学报, 2010, 31(9): 1204-1208.
LIU W Y, ZHANG H Q, ZENG L.Reliability analysis of wind turbine blade based on bionic design[J]. Acta energiae solaris sinica, 2010, 31(9): 1204-1208.
[13] 刘岗, 封周权, 华旭刚, 等. 基于子集模拟法的风机叶片可靠度分析[J]. 计算力学学报, 2019, 36(5): 636-641.
LIU G, FENG Z Q, HUA X G, et al.Reliability computation of wind turbine blades based on subset simulation algorithm[J]. Chinese journal of computational mechanics, 2019, 36(5): 636-641.
[14] 胡国标, 邹益胜, 姜杰, 等. 基于Morris方法的车轴结构参数灵敏度分析[J]. 机械制造, 2015, 53(7): 4-7.
HU G B, ZOU Y S, JIANG J, et al.Sensitivity analysis of axle structural parameter based on the method of Morris[J]. Machinery, 2015, 53(7): 4-7.
基金
重庆市基础与前沿研究计划（cstc2016jcyjA0448）; 重庆市教委科学技术研究项目(KJ1600628); 重庆工商大学研究生创新科研项目 (yjscxx2022-112-158)
PDF(1914 KB)
