摘要
现有的噪声预测模型主要采用机器学习的方法预测单一噪声监测点,无法从全局上对噪声的影响范围和大小进行整体评估和预测。为此,提出一种基于航迹间面积的航迹相似性度量方法,结合航迹数据、飞行速度、飞机发动机推力等因素,构建适合机场噪声预测的多噪声影响因素航迹聚类模型。将使用该模型获得的聚类结果导入机场噪声预测模型软件INM(integrated noise model),实验分析结果表明,簇内航迹对机场周围的噪声影响范围和大小相似,能够更好地度量航迹之间的相似性,航迹聚类效果更好。
The existing noise prediction model mainly adopts machine learning methods to predict single noise monitoring point value, which is unable to estimate and forecast the scope and area of the noise in its totality. A flight tracks similarity measure method based on the measure of area between in the flight tracks was presented, combined with tracks data, aircraft speeds and aircraft engine thrust, multi-noise factors flight tracks clustering model for airport noise prediction was built. The flight tracks clustering results were put into INM （integrated noise model）. The experimental results show that the noise influence area and noise value made by the flight tracks within the same cluster are very similar, and the proposed model can measure the flight tracks similarity more profitably and the results of flight tracks clustering are better.
出处
《计算机工程与设计》
北大核心
2015年第12期3349-3354,共6页
Computer Engineering and Design
基金
国家自然科学基金重点项目(61139002)
国家863高技术研究发展计划基金项目(2012AA063301)
国家科技支撑计划基金项目(2014BAJ04B02)
中国民用航空局科技基金项目(MHRD201006
MHRD201101)
中央高校基本科研业务费专项基金项目(3122013P013
3122013C005)
关键词
航迹相似性
航迹聚类
K-medoids
聚类有效性评价
噪声预测
flight tracks similarity
flight tracks clustering
K-medoids
cluster validity assessment
airport noise prediction
