液体火箭发动机的分层贝叶斯变分推理故障诊断方法  

Fault Diagnosis of Liquid Rocket Engine Based on Hierarchical Bayesian Network Variational Inference

作　　者：刘久富[1] 丁晓彬 汪恒宇 王彪[1] 刘海阳[2] 杨忠[1] 王志胜[1] LIU Jiufu;DING Xiaobin;WANG Hengyu;WANG Biao;LIU Haiyang;YANG Zhong;WANG Zhisheng(College of Automation Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing,Jiangsu 211106,China;School of Electronic Science and Engineering,Southeast University,Nanjing,Jiangsu 211189,China)

机构地区：[1]南京航空航天大学自动化学院,江苏南京211106 [2]东南大学电子信息工程学院,江苏南京211189

出　　处：《北京理工大学学报》2022年第3期289-296,共8页Transactions of Beijing Institute of Technology

基　　金：国家自然科学基金资助项目(61473144)。

摘　　要：针对稀疏数据场景下,传统的多项式-狄利克雷模型存在一定的分类精度问题,提出一种基于变分推理的分层贝叶斯网络的参数估计方法.通过在传统的多项式-狄利克雷模型中引入超先验,构建出的分层多项式-狄利克雷模型可用于贝叶斯网络中的条件分布估计.对分层多项式-狄利克雷模型的先验依赖结构进行分析研究,提出一种快速准确的自组织变分推理算法.与传统的分类模型相比,本文提出的分层多项式-狄利克雷模型在处理小数据集液体火箭发动机的故障分类中有显著的性能提高.In order to improve classification accuracy of traditional multinomial-Dirichlet model in sparse data scenario,a hierarchical Bayesian network parameter estimation method was proposed based on variational inference.Introducing a hyper-prior into the traditional multinomial-Dirichlet model,the hierarchical multinomial-Dirichlet model was constructed to estimate the conditional distribution in Bayesian networks.Analyzing the prior dependency structure of hierarchical multinomial-Dirichlet model,a fast and accurate self-organizing variational reasoning algorithm was developed.Compared with the traditional classification model,the hierarchical multinomial-Dirichlet model proposed in this paper shows a significant performance improvement in dealing with the fault classification problem of liquid rocket engines with small data sets.

关 键 词：贝叶斯网络 液体火箭发动机 分层多项式-狄利克雷模型 变分推理算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]