主冷凝器作为舰船蒸汽动力装置的主要设备运行中发生战损，故障模式复杂、不确定性较大，传统故障诊断方法难以有效解决。本文提出采用贝叶斯网络故障建模的方法解决这一难题，建立具有时间序列特性的动态多连片贝叶斯网络模型。通过实验分析表明模型准确可靠，不仅能够进行从故障原因到现象的正向推理，还能进行故障现象到原因的反向推理，可为蒸汽动力设备的故障诊断提供有效决策。
As one of main steam power equipments on ship, main condenser makes battle damages in operation. Fault modes of main condenser are complex and uncertain, which traditional fault diagnosis method is difficult to solve. This paper presents a modeling method of Bayesian network to solve the problem and establish dynamic and contiguous Bayesian network model with time series character. The experiment shows that the model is accurate and reliable. The model can not only make forward inference from fault reasons to phenomenon, but also make backward inference from fault phenomenon to reasons, which can provide effective decision to fault diagnosis of steam power equipments.
2016,38(10): 107-110 收稿日期：2016-6-17
DOI：10.3404/j.issn.1672-7619.2016.10.021
分类号：U261.163+1
基金项目：国家自然科学基金资助项目（51579242）；湖北省自然科学基金资助项目（2013CFB440）
作者简介：许伟(1987-),男,博士研究生,研究方向为动力机械及热力系统的设计、仿真与优化。
参考文献：
[1] 初珠立, 杨自春, 梁洁, 等. 主冷凝器损伤的模糊随机特性及贝叶斯网络分析[J]. 哈尔滨工程大学学报, 2012, 33(10):1217-1222. CHU Z L, YANG Z C, CHEN G B, et al. Damage analysis of the main condenser based on fuzzy random Bayesian networks[J].Journal of Harbin Engineering University, 2012, 33(12):1217-1222.
[2] 李海军, 马登武, 刘霄等. 贝叶斯网络理论在装备故障诊断中的应用[M]. 北京:国防工业出版社, 2009.
[3] 陈海洋, 高晓光, 樊昊. 变结构DDBNs的推理算法与多目标识别[J]. 航空学报, 2010, 31(11):2222-2227. CHEN H Y, GAO X G, FAN H. Reasoning algorithm of variable structure and target recognition[J]. Acta Aeronautica Etastonautica, 2010, 31(11):2222-2227
[4] Y XIANG. Comparison of mutiagent inference methods in multiply sectioned Bayesian networks[J]. International Journal of Approximate Reasoning, 2003, 33:235-254.
[5] Y XIANG. A probabilistic framework for cooperative multi-agent distributed interpretation and optimization of communication[J]. Artificial Intelligence, 1996, 87:295-342.
[6] AN Xiang-dong, YANG Xiang, NICK C. Dynamic multiagent probabilistic inference[J] International Journal of Approximate Reasoning,2008, 48:185-213.
[7] 苏艳琴, 徐廷学, 张文娟. 粗糙集和贝叶斯网络融合故障诊断方法[J]. 舰船科学技术, 2013, 35(3):91-93. SU Y Q, XU T X, ZHANG W J, Rough sets and Bayesian network fusion fault diagnosis methods[J]. Ship Science and Technology, 2013,35(3):91-93
[8] 付尧, 曾凡明, 陈于涛, 等. 舰用柴油机冷却水系统贝叶斯状态推理方法[J]. 舰船科学技术, 2014, 36(8):42-45, 52. FU Yao, ZENG Fan-ming, CHEN, Yu-tao. Study on the bayesian reasoning methods for marine disel chill water system[J]. Ship Science and Technology, 2014, 36(8):42-45
