基于贝叶斯改进结构算法的回转窑故障诊断模型研究

摘要/Abstract

摘要： 针对现有改进互信息爬山(MI&HC)算法精度低、耗时长及简化爬山(SHC)算法产生大量冗余边的问题，提出一种新的结构学习算法,即改进爬山(IHC)算法。通过计算互信息链得到贝叶斯初始结构，利用条件独立性测试以及对孤立节点进行处理来加边补充贝叶斯初始结构得到完全结构，利用改进的爬山搜索算子对完全结构进行搜索直到得出最优结构。将该算法与爬山(HC)算法、MI&HC算法、SHC算法进行比较，仿真结果表明，IHC算法能够得到较高准确率的模型,时间开销最小而且产生的冗余边数远远少于SHC算法产生的冗余边数。最后基于IHC算法，结合某回转窑数据进行训练，得到了回转窑工艺参数的故障诊断模型，对回转窑的烧成带温度实现了较为准确的故障诊断。

关键词: 改进贝叶斯结构算法, 互信息及条件独立性测试, 故障诊断, 水泥回转窑

Abstract: The improved mutual information hill climbing algorithm (MI&HC) had less accuracy and time consuming, and the simplified hill-climbing(SHC) algorithm generated lots of redundant edges. Aiming at these problems, this paper proposed a new Bayesian structure learning algorithm, improved hill-climbing(IHC).Firstly,this algorithm calculated the mutual information chains to obtain the Bayesian initial structure.Secondly, this algorithm utilized conditional independence tests and dealt with isolated nodes to supplement the initial structures to obtain the completed structure.Finally,the algorithm utilized improved search operators of HC to search for the optimal structure based on completed structure.The simulation results show that:compared with hill-climbing(HC),MI&HC and SHC algorithm, the IHC algorithm may obtain a more accurate and more rapid model, the redundant edges generated by IHC are far less than SHC.In the end,based on IHC algorithm and combined with some rotary kiln operating data, the fault diagnosis model of processing parameters may be constructed and a precise fault diagnosis of burning zone temperature in the rotary kiln is realized.

Key words: improved structure learning algorithm of Bayesian, mutual information and conditional independence test, fault diagnosis, cement rotary kiln

中图分类号:

TH165

刘彬1;刘永记1;刘浩然1;李雷2;孙美婷1. 基于贝叶斯改进结构算法的回转窑故障诊断模型研究[J]. 中国机械工程.

LIU Bin1;LIU Yongji1;LIU Haoran1;LI Lei2;SUN Meiting1. A Study of Fault Diagnosis Model of Rotary Kiln Based on Improved Structural Algorithm of Bayesian[J]. China Mechanical Engineering.

参考文献

[1]陈东宁,姚成玉,党振，等.基于T-S模糊故障树和贝叶斯网络的多态液压系统可靠性分析[J].中国机械工程,2013,24(7):899-905.
CHEN Dongning, YAO Chengyu, DANG Zhen， et al. Reliability Analysis of Multi-state Hydraulic System Based on T-S Fuzzy Fault Tree and Bayesian Network[J].China Mechanical Engineering,2013,24(7):899-905.

[2]马德仲.基于贝叶斯网络和多源信息构建可靠性分析模型方法研究[D].哈尔滨：哈尔滨理工大学,2015.
MA Dezhong.Research on Constructing Reliability Analysis Model Based on Bayesian Networks and Multi-source Information[D]. Harbin：Harbin University of Science and Technology,2015.

[3]CHENG J, GREINER R, KELLY J,et al. Learning Bayesian Networks from Data: An Information-theory Based Approach[J]. Artificial Intelligence,1998,137(1/2):43-90.

[4]TSAMARDINOS I,BROWN L E, ALIFERIS C F.The Max-min Hill-climbing Bayesian Network Structure Learning Algorithm[J]. Machine Learning,2006,65(1):31-78.

[5]金焱,胡云安,张瑾,等.互信息与爬山法相结合的贝叶斯网络结构学习[J].计算机应用与软件,2012,29(9):122-125.
JIN Yan, HU Yun'an, ZHANG Jin, et al. Bayesian Network Structure Learning Combining Mutual Information with Hill Climbing Algorithm[J]. Computer Applications and Software,2012,29(9):122-125.

[6]刘浩然,吕晓贺,李轩,等.基于Bayesian改进算法的回转窑故障诊断模型研究[J].仪器仪表学报,2015,36(7):1554-1561.
LIU Haoran, LYU Xiaohe, LI Xuan,et al. A study of Fault Diagnosis Model of Rotary Kiln Based on Improved Algorithm of Bayesian[J]. Chinese Journal of Scientific Instrument,2015,36(7):1554-1561.

[7]邓歆,孟洛明.基于贝叶斯网络的通信网告警相关性和故障诊断模型[J].电子与信息学报,2007,29(5):1182-1186.
DENG Xin,MENG Luoming. Bayesian Networks Based Alarm Correlation and Fault Diagnosis in Communication Networks[J]. Journal of Electronics & Information Technology,2007,29(5):1182-1186.

[8]刘浩然,马明,李世昭,等.一种应用于故障诊断中的高效推理算法[J].控制与决策,2015,30(11):2033-2040.
LIU Haoran, MA Ming, LI Shizhao,et al. An Effective Inference Algorithm for Fault Diagnosis[J].Control and Decision,2015,30(11):2033-2040.

[9]LI B H, LI Z G. Improved Algorithm Based on Mutual Information for Learning Bayesian Network Structures in the Space of Equivalence Classes[J]. Multimedia Tools & Applications,2012,60(1):129-137.

[10]PENSAR J, NYMAN H,LINTUSAARI J, et al. The Role of Local Partial Independence in Learning of Bayesian Networks[J]. International Journal of Approximate Reasoning,2016,69(C):91-105.

[11]关菁华.基于依赖分析的贝叶斯网络结构学习和分类器的研究与实现[D]. 长春：吉林大学, 2005.
GUAN Jinghua.Bayesian Network Structure Learning Based on Dependency Analysis and the Research and Realization of the Classifier[D]. Changchun：Jilin University,2005.

[12]朱明敏, 刘三阳, 杨有龙.基于最大主子图分解的贝叶斯网络等价类学习算法[J].控制与决策,2012,27(10):1499-1504.
ZHU Mingmin, LIU Sanyang,YANG Youlong. Structural Learning Bayesian Network Equivalence Classes Via Maximal Prime Decomposition[J], Control and Decision,2012,27(10):1499-1504.

[13]李景囡.基于依赖分析的贝叶斯网络结构学习算法研究[D]. 西安：西安电子科技大学,2014.
LI Jingnan.Research on Dependence Analysis Based Algorithms for Bayesian Network Structure Learning[D]. Xi'an: Xidian University,2014.

[14]高晓光, 赵欢欢, 任佳.基于蚁群优化的贝叶斯网络学习[J].系统工程与电子技术,2010,32(7):1509-1512.
GAO Xiaoguang, ZHAO Huanhuan, REN Jia. Bayesian Network Learning on Algorithm Based on
Ant Colony Optimization[J]. Systems Engineers and Electronics,2010,32(7):1509-1512.

[15]徐小力,刘秀丽,蒋章雷,等.基于主观贝叶斯推理的多传感器分布式故障检测融合方法[J].机械工程学报,2015,51(7):91-98.
XU Xiaoli, LIU Xiuli, JIANG Zhanglei, et al. Multi-sensor Distributed Fault Detection Method Based on Subjective Bayesian Reasoning[J].Journal of Mechanical Engineering,2015,51(7):91-98.

[16]郭峰.基于模糊ARX模型的水泥回转窑预测控制算法研究[D]. 秦皇岛:燕山大学,2012.
GUO Feng. Research of Predictive Control Algorithm on the Cement Rotary Kiln Based on Fuzzy ARX Model[D]. Qinhuangdao: Yanshan University,2012.

[17]杨宇,高晓光,郭志高.小数据集条件下基于数据再利用的BN参数学习[J].自动化学报,2015,41(12):2058-2071.
YANG Yu, GAO Xiaoguang, GUO Zhigao. Learning BN Parameters with Small Data Sets Based by Data Reutilization[J], Acta Automatica Sinica,2015,41(12):2058-2071.