当前位置: X-MOL 学术Ships Offshore Struct. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Sailing status recognition to enhance safety awareness and path routing for a commuter ferry
Ships and Offshore Structures ( IF 1.7 ) Pub Date : 2021-04-10 , DOI: 10.1080/17445302.2021.1907084
Baiheng Wu 1 , Guoyuan Li 1 , Tongtong Wang 1 , Hans Petter Hildre 1 , Houxiang Zhang 1
Affiliation  

ABSTRACT

This paper suggests a framework about how log data are used to develop a classifier to recognise the sailing status of a commuter ferry, which, in turn, serves as a tool of safety awareness. Several sailing scenarios are defined under the expertise’s interpretation based on log data. A classifier is developed by support vector machine algorithm to recognise different scenarios. The classifying precision is getting improved as the database getting larger. Heat maps are drawn statistically to obtain the likelihood site of each sailing status. Contour maps are drawn by interpolation according to heat maps. Based on contour maps, two evaluation items are proposed to reflect the safety level. The safety level term is used for optimising the control. The established classifier has a recognition precision over 96 percent. A path following simulation is executed to verify the effectiveness of the safety level for enhancing sailing safety.



中文翻译:

航行状态识别,以提高通勤渡轮的安全意识和路径规划

摘要

本文提出了一个关于如何使用日志数据开发分类器以识别通勤渡轮的航行状态的框架,而后者又可用作提高安全意识的工具。根据日志数据的专业知识解释定义了几个航行场景。通过支持向量机算法开发分类器以识别不同的场景。随着数据库的变大,分类精度也在不断提高。统计绘制热图以获得每个航行状态的似然位置。轮廓图是根据热图通过插值绘制的。基于等高线图,提出了两个评价项目来反映安全水平。安全级别术语用于优化控制。建立的分类器识别精度超过96%。

更新日期:2021-04-10
down
wechat
bug