| 张智勇,余金,常鹏,徐其丹,李阳.基于数据融合的风电机组噪声预测[J].,2018,37(6):956-962 |
| 基于数据融合的风电机组噪声预测 |
| Wind turbines noise prediction based on data fusion |
| 投稿时间：2018-01-27 修订日期：2018-10-22 |
| 中文摘要: |
| 根据风电机组噪声信号检测复杂的情况,研究风电机组非声学参数的信息熵特征,对机组噪声进行多源数据融合预测。分析基于信息熵的非声学参数的特征提取方法,并对传统的基于遗传算法的支持向量机回归(GA-SVR)的缺陷提出改进,结合实际应用的非声学参数的信息熵特点平衡遗传算法(GA)的终止条件。通过统计分析完成了输入变量的筛选,去除了对预测影响较大的共线性因素,并实现了输入降维提高预测精度和速率。最后应用数据的信息熵特征,训练改进的GA-SVR建立最终的多源数据特征级融合预测模型。通过对比表明基于多源数据融合的预测方法精度最高,预测结果的相对误差平均值为0.7757%,具有实际可行性。 |
| 英文摘要: |
| According to the wind turbine noise signal detection complex situation , researched on Information Entropy Characteristics of Non-acoustic Parameters of Wind Turbine, finished Multi-source data fusion prediction of unit noise. The feature extraction method based on entropy of non-acoustic parameters is analyzed, and analyzed the shortcomings of based on the support vector regression of genetic algorithm (GA-SVR), the improvement was put forward. The termination condition of the genetic algorithm is balanced by the information entropy characteristics of the non-acoustic parameters. The input variables are filtered out through the statistical analysis, and removed the collinear factors that have a greater impact on the forecast. Realized the variable dimension reduction to improve the prediction accuracy and speed. Finally, the information entropy feature of the data is applied to the training and improvement of ga-svr to establish the final multi-source data feature level fusion prediction model. The comparison shows that the accuracy of the prediction method based on multi-source data fusion is the highest, and the relative error of the forecast results is 0.7757%, which is feasible. |
| DOI：10.11684/j.issn.1000-310X.2018.06.018 |
| 中文关键词: 风力发电 噪声预测 多源数据融合 支持向量机回归 遗传算法 |
| 英文关键词: wind power noise prediction Multi-source data fusion support vector regression multiple correlation |
| 基金项目: |
|
| 摘要点击次数: 1801 |
| 全文下载次数: 1806 |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|
