基于Elman神经网络的风电场噪声预测模型

Wind Farm Noise Forecasting Based on Elman Neural Network

针对风电场噪声易受风速风向等多因素影响的特点,引入具有动态递归性能的Elman神经网络,综合考虑风速、风向和距离三个主要因素的影响,建立了基于Elman神经网络的风电场噪声预测模型,并以某风电场为例,选取基于无指向性经验拟合预测模型作为对比模型,分别预测风电场噪声,绘制风电场噪声等值线地图。结果表明,基于Elman神经网络的风电场噪声预测模型具有更高的拟合相关性系数,且噪声预测更符合实际情况。

Considering the wind farm noise affected by multiple factors, such as wind speed and direction, a dynamic recursive Elman neural network was introduced. Wind farm noise forecasting model based Elman neural network was es- tablished by considering the influence of wind speed, direction and distance. Taking a wind farm for an example, the model was comparecl with the empirical study based on non-directional noise attenuation formula. The wind farm noise was predicted and the noise contour map was plotted. Experimental results show that the proposed model has a higher fit- ting correlation coefficient, and the predicted noise accords with the actual situation.