基于聚类分析的船舶主机频繁工作区性能评估

The Performance Evaluation of Marine Engine Frequent Operating Regions Based on Clustering Analysis

以营运船舶定速航行的主机频繁工作区及其营运能效为目的,对目标船舶能效数据进行分析.运用MATLAB进行数据清洗,得到定速航行时的能效数据;采用K均值聚类算法进行聚类,得到了主机不同频繁工作区下的聚类点;用距离评价函数对聚类效果及最佳聚类数K进行验证;使用二次多项式法对数据进行拟合,得到主机负荷与油耗率关系曲线,关系曲线显示总体上油耗率随着负荷的增加而降低.当主机功率为5 161.44 kW时,油耗率为180.5 g/(kW·h);主机功率为7 135.89 kW时,油耗率为177.41 g/(kW·h).结果表明,该方法可用于分析主机频繁工作区并进行性能评估,也可为船舶能效管理计划的制定提供参考.

In this paper, the energy efficiency data was analyzed to study the frequent operating regions of the main engine and its operating energy efficiency during the constant speed sailing of the target ship. The energy efficiency data of the target ship were obtained by cleaning the data with MATLAB. The clustering points under different frequent operating regions of the main engine were obtained by using K-means clustering algorithm.And the clustering effect and the optimal clustering number K were calculated by distance evaluation function.Finally, the relationship between engine load and fuel consumption rate was obtained by fitting the data with quadratic polynomial method.As a whole, the fuel consumption rate decreases with the increase of load. When the main engine power was 5 161.44 kW, the fuel consumption rate was 180.5 g/(kW·h), and when the main engine power was 7 135.89 kW, the fuel consumption rate was 177.41 g/(kW·h). The results showed that the method can be used to analyze the frequent operating regions of main engine and evaluate the performance, and can also provide reference for the formulation of ship energy efficiency management plan.