摘要
针对多因素影响下的短航程油耗呈现双峰分布,提出了使用高斯混合聚类(Gaussian mixture model,GMM)和随机森林(random forest,RF)相结合的方法对短航程油耗进行估计。该算法先使用GMM对短航程油耗数据聚类,得到两个不同形状的聚类簇。以不同的采样率对两个聚类簇进行采样,构造子数据集,并对每个子集使用回归树进行训练。将CART回归树并行得到RF用于短航程油耗估计。在同一机型和航线,不同的航班数据上进行对比实验,结果验证了所提算法的有效性。
In view of the bimodal distribution of short-voyage fuel consumption under the influence of multiple factors,a method combining Gaussian mixture clustering(GMM)and random forest(RF)were proposed to estimate the short-voyage fuel consumption.GMM was used to cluster short-voyage fuel consumption data to obtain clusters of two different shapes.The two clusters were sampled at different sampling rates,the sample subset was constructed,and the regression tree was used for each subset.The classification and regression tree(CART)was used in parallel to obtain random forest for short-voyage fuel consumption estimation.The comparison experiments were carried out on the same model and route,and different flight data.The results show the effectiveness of the proposed algorithm.
作者
陈静杰
崔金成
CHEN Jing-jie;CUI Jin-cheng(College of Electronic Information and Automation,Civil Aviation University of China,Tianjin 300300,China)
出处
《科学技术与工程》
北大核心
2019年第24期254-259,共6页
Science Technology and Engineering
基金
中美绿色航线项目(GH201661279)
国家科技支撑计划(2012BAC20B0304)资助
关键词
短航程油耗
高斯混合聚类
采样率
随机森林
short-voyage fuel consumption
Gaussian mixture clustering
sampling rate
random forest