针对舰船智能机舱多源数据处理，建立基于DBSCAN聚类算法的多源数据异常检测方法，包含聚类参数的自动获取及校正，并可根据试验数据进行机器学习和更新。介绍该检测方法的程序框架、子程序的程序流程，并基于机舱中典型的滑油系统进行数据检测测试。经过测试，该检测方法可有效对测试数据进行分析，自动得出并修正聚类参数，且对正常信号相差15%以上的异常数据的检测结果识别度达到100%。本文提出的异常数据检测方法可行有效，可以作为智能机舱数据处理系统的方案之一。
To provide effect method of intelligent engine room multi-source data processing for ship, the multi-source data detecting method based on DBSCAN cluster analysis algorithm was established, which could automatically get the cluster parameters, adjusted and updated based on machine learning. The program frame of the method and flow chart of subprogram were introduced. And a test for lubricating oil system data detection was implemented, which shows the test data could be effectively analyzed and the cluster parameters could be obtained and adjusted. The test indicated that the detecting method recognition rate achieves 100% against abnormal data, 15% differed from normal data. The detecting method was feasible and effective, which could be one of the solutions for intelligent engine room multi-source data processing.
2021,43(9): 156-160 收稿日期：2020-12-18
DOI：10.3404/j.issn.1672-7649.2021.09.031
分类号：TP391
作者简介：陈砚桥(1978-)，男，博士，副教授，主要研究方向为舰船装备保障性工程、舰船动力工程
参考文献：
[1] 刘峻华, 孟清正, 杨涛, 等. 船舶动力装置可组态智能故障诊断系统设计[J]. 中国舰船研究, 2011, 6(2): 77–80
LIU Junhua, MENG Qingzheng, YANG Tao, et al. Design of the configurable intelligent fault diagnosis system of marine power plant[J]. Chinese Journal of Ship Research, 2011, 6(2): 77–80
[2] 肖尚勤, 何刚, 黄金锋, 等. 基于知识库的舰船智能化设计系统[J]. 中国舰船研究, 2010, 5(6): 93–97
XIAO Shangqin, HE Gang, HUANG Jinfeng, et al. A knowledge-based ship intelligent design system[J]. Chinese Journal of Ship Research, 2010, 5(6): 93–97
[3] 张跃文, 孙晓磊, 丁亚委, 等. 船舶动力装置智能诊断系统设计[J]. 中国舰船研究, 2018, 13(6): 140–146
ZHANG Yuewen, SUN Xiaolei, DING Yawei, et al. Design of intelligent diagnosis system for ship power equipment[J]. Chinese Journal of Ship Research, 2018, 13(6): 140–146
[4] 周水庚, 周傲英, 曹晶. 基于数据分区的DBSCAN 算法[J]. 计算机研究与发展, 2000, 37(10): 1153–1159
ZHOU Shuigeng, ZHOU Aoying, CAO Jing. A data-partitioning-based DBSCAN algorithm[J]. Journal of Computer Research and Development, 2000, 37(10): 1153–1159
[5] 吴伟民, 黄焕坤. 基于差分隐私保护的DP-DBScan 聚类算法研究[J]. 计算机工程与科学, 2015, 37(4): 830–834
WU Weimin, HUANG Huankun. A DP-DBScan clustering algorithm based on differential privacy preserving[J]. Computer Engineering and Science, 2015, 37(4): 830–834
[6] 阮嘉琨, 蔡延光, 乐冰. 基于DBSCAN密度聚类算法的高速公路交通流异常数据检测[J]. 工业控制计算机, 2019, 32(7): 92–94
RUAN Jiakun, CAI Yanguang, YUE Bing. Highway traffic flow abnormal data detection based on DBSCAN density clustering algorithm[J]. Industrial Control Computer, 2019, 32(7): 92–94
[7] 潘渊洋, 李光辉, 徐勇军. 基于DBSCAN 的环境传感器网络异常数据检测方法[J]. 计算机应用与软件, 2012, 29(11): 69–72
Pan Yuanyang, Li Guanghui, Xu Yongjun. Abnormal data detection method for environment wireless sensor networks based on DBSCAN[J]. Computer Applications and Software, 2012, 29(11): 69–72
[8] 于重重, 杨扬, 涂序彦, 等. DBSCAN 算法在桥梁健康监测预测模型中的应用[J]. 计算机工程与应用, 2008, 44(12): 224–227
YU Chong- chong, YANG Yang, TU Xu- yan, et al. Application of DBSCAN algor ithm in bridge- health monitor ing pr ediction model[J]. Computer Engineer ing and Applications, 2008, 44(12): 224–227
[9] 蔡怀宇, 陈延真, 卓励然, 等. 基于优化DBSCAN算法的激光雷达障碍物检测[J]. 光电工程, 2019, 46(7): 180514
CAI Huaiyu, CHEN Yanzhen, ZHUO Liran, et al. LiDAR object detection based on optimized DBSCAN algorithm[J]. Opto-Electronic Engineering,, 2019, 46(7): 180514
[10] 郭保青, 朱力强, 史红梅. 基于快速DBSCAN聚类的铁路异物侵限检测算法[J]. 仪器仪表学报, 2012, 33(2): 241–247
GUO Baoqing, ZHU Liqiang, SHI Hongmei. Intrusion detection algorithm for railway clearance with rapid DBSCAN clustering[J]. Chinese Journal of Scientific Instrument, 2012, 33(2): 241–247
[11] 荣秋生, 颜君彪, 郭国强. 基于DBSCAN聚类算法的研究与实现[J]. 计算机应用, 2004, 24(4): 45–46
RONG Qiusheng, YAN Junbiao, GUO Guoqiang. Research and implementation of clustering algorithm based on DBSCAN[J]. Computer Applications, 2004, 24(4): 45–46
