摘要
随着无人船系统复杂度的增加,对其进行故障预测和健康管理(prognostic and health management,PHM)的需求也随之提升。采用贝叶斯网络建立无人船的可靠性模型,并基于此开展无人船的PHM技术研究。主要探究贝叶斯网络模型在PHM方面的应用,包括利用动态贝叶斯网络进行预测故障,通过参数学习自动生成贝叶斯网络模型。以实验室开发的智能无人船为具体研究对象,针对其动力系统常见的故障点监测模式进行研究,并设计相应的在线监测方案。通过实时监测完整地表达无人船的健康程度,并开发了无人船的健康管理模型。对开发设计的健康管理模型进行实时性和准确性双方面评价,所研发的健康管理技术可以准确地还原无人船的故障分布情况,并快速响应做出故障预测,可以充分评估无人船在不同状态下的实际工作能力。
Related research in the field of unmanned ships has received extensive attention in recent years.As the complexity of unmanned ship systems increases,the need for prognostic and health management(PHM)increases.The Bayesian network is used to establish the reliability model of the unmanned ship.Based on this,the research on the health management system of the unmanned ship is carried out.The application of Bayesian network model in fault diagnosis and prediction is mainly explored.The dynamic Bayesian network is used to predict faults and the Bayesian network model is automatically generated through parameter learning.Taking the intelligent unmanned ship independently developed by the laboratory as the specific research object,online monitoring scheme of the fault point detection mode are designed to fully express the health of the propulsion system of the unmanned ship,thus realizing the development of the unmanned ship.The health management system is evaluated in time consuming and accuracy.The developed system can accurately restore the fault distribution of the ship and respond quickly to fault prediction.The system can fully evaluate the actual working ability of the unmanned ship in different states.
作者
王天语
王鸿东
梁晓锋
易宏
WANG Tian-yu;WANG Hong-dong;LIANG Xiao-feng;YI Hong(State Key Laboratory of Ocean Engineering,Shanghai Jiaotong University,Shanghai 200240,China;Key Laboratory of Marine Intelligent Equipment and Systems,Shanghai Jiaotong University,Shanghai 200240,China)
出处
《舰船科学技术》
北大核心
2019年第23期80-86,共7页
Ship Science and Technology
基金
中国科学院学部咨询评议资助项目(17Z20320037)
上海市青年科技英才扬帆计划资助项目(18YF1411500)
关键词
无人船
可靠性
动态贝叶斯网络
PHM
unmanned ship
reliability
dynamic Bayesian network
health management
