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.
2019,41(12): 80-86 收稿日期：2019-04-24
DOI：10.3404/j.issn.1672-7649.2019.12.017
分类号：U672.7
基金项目：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）
作者简介：王天语(1996-),男,硕士研究生,研究方向为海洋工程
参考文献：
[1] LIAO L, KÖTTIG F. Review of hybrid prognostics approaches for remaining useful life prediction of engineered systems, and an ap plication to battery life prediction[J]. IEEE Transactions on Reliability, 2014, 63(1): 191–207
[2] LI C J, LEE H. Gear fatigue crack prognosis using embedded model, gear dynamic model and fracture mechanics[J]. Mechanical Systems & Signal Processing, 2005, 19(4): 836–846
[3] SEKER H, ODETAYO M O, PETROVIC D, et al. A fuzzy logic based-method for prognostic decision making in breast and prostate cancers[J]. IEEE Transactions on Information Technology in Biomedicine A Publication of the IEEE Engineering in Medicine & Biology Society, 2003, 7(2): 114–22
[4] STREET W N. A neural network model for prognostic prediction[C]// 1998: 540--546.
[5] MAGLOGIANNIS I, ZAFIROPOULOS E, ANAGNOSTOPOULOS I. An intelligent system for automated breast cancer diagnosis and prognosis using SVM based classifiers[M]. Kluwer Academic Publishers, 2009.
[6] ZHANG J T, LIU Y, ANN L M, et al. Using Bayesian networks to quantify the reliability of a subsea system in the early design[C]// European Safety and Reliability Conference. 2017.
[7] PUI G, BHANDARI J, ARZAGHI E, et al. Risk-based maintenance of offshore managed pressure drilling (MPD) operation[J]. Journal of Petroleum Science & Engineering, 2017
[8] 肖小勇. 船舶柴油机智能诊断技术与应用研究[D]. 武汉: 武汉理工大学, 2013.
[9] 刘晶, 周晓东, 郭明. 基于INMARSAT-B的舰船远程故障诊断系统研究[J]. 国外电子测量技术, 2006, 25(1): 27–30
[10] PEARL J. Reverend bayes on inference engines: a distributed hierarchical approach[C]// AAAI Conference on Artificial Intelligence. AAAI Press, 1982: 133-136.
[11] POURRET O, NAÏM P, MARCOT B. Bayesian networks. A practical guide to applications[J]. Treatise on Geochemistry, 2008, 37(4): 281–304
[12] KOLLER D, FRIEDMAN N. Probabilistic graphical models:principles and techniques - adaptive computation and machine learning[M]. MIT Press, 2009.
[13] 罗潇, 刘旌扬, 王健, 等. 高性能无人帆船软硬件设计[J]. 计算机工程与应用, 2018, 54(9): 265–270
[14] MURPHY K P. Dynamic Bayesian networks: representation, inference and learning[M]. University of California, Berkeley, 2002.
[15] TOMMISKA M T. Efficient digital implementation of the sigmoid function for reprogrammable logic[J]. IEE Proceedings - Computers and Digital Techniques, 2003, 150(6): 403–411
[16] TSYPKIN M. Induction motor condition monitoring: Vibration analysis technique — diagnosis of electromagnetic anomalies[C]// Autotestcon. IEEE, 2017: 1–7.
[17] DING H, ZHANG G C, CHEN L Q. Supercritical vibration of nonlinear coupled moving beams based on discrete Fourier transform[J]. International Journal of Non-Linear Mechanics, 2012, 47(10): 1095–1104
[18] FRANZ K J, HARTMANN H C, SOROOSHIAN S, et al. Verification of national weather service ensemble streamflow predictions for water supply forecasting in the colorado river basin[J]. Journal of Hydrometeorology, 2003, 4(2003): 1105–1118
[19] EPSTEIN E S. A scoring system for probability forecasts of ranked categories[J]. J.appl.meteor, 1969, 8(6): 985–987
