为解决大数据下船舶会遇识别算法效率不高且存在误判等问题,提出一种融合国际海上避碰规则(International Regulations for Preventing Collisions at Sea,COLREGs)的带噪声的基于密度的空间聚类(density-based spatial clustering of applications with noise,DBSCAN)算法,建立船舶会遇识别模型.在DBSCAN算法对邻域内的船舶数量进行统计时,计算船舶间的最近会遇距离(distance to closest point of approach,DCPA)和最近会遇时间(time to closest point of approach,TCPA),初步筛选邻域内的噪声点;基于模糊综合评价模型计算船舶会遇风险,对邻域内的船舶进行二次筛选,实现船舶会遇态势的提取.结果表明:改进后的DBSCAN算法过滤掉传统DBSCAN算法识别到的非会遇局面,并且在同一会遇局面下的船舶数量均保持在4艘以内;输出的会遇船舶风险演变趋势对实际水域内高风险船舶的监控适用性较好,能有效辅助船舶避碰.所提识别模型对保障航行安全和提高海事监管效率具有重要意义.
Abstract
In order to solve the problems of low efficiency and misjudgment of algorithms for identifying ship encounter in big data,an algorithm of density-based spatial clustering of applications with noise(DBSCAN)introducing International Regulations for Preventing Collisions at Sea(COLREGs)is proposed.When DBSCAN algorithm counts the number of ships in the neighborhood,the distance to closest point of approach(DCPA)and the time to closest point of approach(TCPA)are calculated,and the noise points are screened preliminarily;the fuzzy comprehensive evaluation risk model is adopted to calculate the risk of ship encounter,the secondary screening of ships in the neighborhood is carried out,and the ship encounter situations are extracted.The results show the following:the improved DBSCAN algorithm filters out the non-encounter situations identified by the traditional DBSCAN algorithm,and the number of ships in the same encounter situation is kept within 4;the output risk evolution trend of encounter ships has a good applicability to the monitoring of high-risk ships in the actual waters,and can effectively assist ships in collision avoidance.The proposed model is of great significance for ensuring the navigation safety and improving the efficiency of maritime supervision.
density-based spatial clustering of applications with noise(DBSCAN)/International Regulations for Preventing Collisions at Sea(COLREGs)/fuzzy comprehensive evaluation/ship encounter/maritime supervision
维普
万方数据