魏淑娟^1,2,3,5,齐咏生^1,2,3,刘利强^1,2,3,李永亭^1,2,3,高学金⁴

• 1:内蒙古工业大学 电力学院，内蒙古 呼和浩特 010080
• 2:大规模储能技术教育部工程研究中心，内蒙古 呼和浩特 010080
• 3:内蒙古自治区高等学校智慧能源技术与装备工程研究中心，内蒙古 呼和浩特 010080
• 4:北京工业大学 信息学部，北京 100080

摘要(Abstract)：

针对复杂工业过程故障溯源时间长,且溯源过程受到多个因素的关联和影响,导致故障溯源效果差等问题,提出一种集成块降图形套索(BDGL)与条件互信息(CMI)的传递熵故障溯源算法。首先引入了优化的BDGL对子组进行建模,有效降低计算复杂度;之后应用传递熵进行因果分析,得到传递熵主要变量对,通过计算CMI,分析主要突出变量的直接和间接因果关系;最后根据溯源过程,确定精简的工业过程故障溯源图,分析故障根本原因,使得故障过程恢复。以冷水机组数据和田纳西-伊斯曼(TE)工业过程数据为研究对象,进行了故障溯源因果分析,验证了该溯源方法的有效性和实用性。该方法不仅提高了故障溯源方法的效率,还增强了结果的准确性和可解释性。

关键词(KeyWords)： 图形套索;传递熵;条件互信息;因果推理;工业过程;故障溯源

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金(62363029,62241309);内蒙古科技计划(2020GG0283,2021GG0164);内蒙古自然科学基金(2022MS06018,2021MS06018)。

作者(Author): 魏淑娟^1,2,3,5,齐咏生^1,2,3,刘利强^1,2,3,李永亭^1,2,3,高学金⁴

DOI: 10.3969/j.issn.1003-9015.2025.05.010

参考文献(References)：

• [1] SINGH V, GANGSAR P, PORWAL R, et al. Artificial intelligence application in fault diagnostics of rotating industrial machines: A state-of-the-art review [J].Journal of Intelligent Manufacturing, 2023, 34(3): 931-960.
  [2] KHAN N, AMMAR TAQVI S A. Machine learning an intelligent approach in process industries: A perspective and overview [J].ChemBioEng Reviews, 2023, 10(2): 195-221.
  [3] 徐斌, 陆军, 丁进良. 基于因果结构学习的复杂工业过程异常分层根因分析方法: 第35届中国过程控制会议论文集[C]. 三亚:中国自动化学会过程控制专业委员会, 中国自动化学会, 2024: 1275. XU B, LU J, DING J L. Hierarchical root cause analysis method for complex industrial processes based on causal structure learning: Proceedings of the 35th China Process Control Conference [C]. Sanya: Professional Committee of Process Control, Chinese Society of Automation, 2024: 1275.
  [4] 钱小毅, 王利鑫, 姜兴宇, 等. 基于交互监测与连通性模型的化工过程故障传播分析[J/OL]. 化工学报, 1-14[2025-03-22]. http://kns.cnki.net/kcms/detail/11.1946.TQ.20250313.1152.002.html. QIAN X Y, WANG L X, JIANG X Y, et al. Fault propagation analysis of chemical process based on interactive monitoring and connectivity model [J/OL].CIESC Journal, 1-14[2025-03-22]. http://kns.cnki.net/kcms/detail/11.1946.TQ.20250313.1152.002.html.
  [5] 孙丽华, 王文静, 朱宏涛, 等. 基于故障相关变量因果关系分析的工业过程故障根因诊断[J]. 化工自动化及仪表, 2024, 51(6): 1035-1044. SUN L H, WANG W J, ZHU H T, et al. Fault's root causes diagnosis of the industrial process based on the causality analysis of fault related variables [J].Control and Instruments in Chemical Industry, 2024, 51(6): 1035-1044.
  [6] SHANNON C E. A mathematical theory of communication [J].The Bell System Technical Journal, 1948, 27(3): 379-423.
  [7] CHATZISAVVAS K C, MOUSTAKIDIS C C, PANOS C P. Information entropy, information distances, and complexity in atoms [J].The Journal of Chemical Physics, 2005, 123(17): 174111.
  [8] SCHREIBER T. Measuring information transfer [J].Physical Review Letters, 2000, 85(2): 461-464.
  [9] MENG Q Q, ZHU Q X, GAO H H, et al. A novel scoring function based on family transfer entropy for Bayesian networks learning and its application to industrial alarm systems [J].Journal of Process Control, 2019, 76: 122-132.
  [10] WANG Y, HESTMO R H, VINOGRADOV A. Early sub-surface fault detection in rolling element bearing using acoustic emission signal based on a hybrid parameter of energy entropy and deep autoencoder [J].Measurement Science and Technology, 2023, 34(6): 064008.
  [11] SU J J, WANG D Z, ZHANG Y N, et al. Capturing causality for fault diagnosis based on multi-valued alarm series using transfer entropy [J].Entropy, 2017, 19(12): 663.
  [12] YU W J, YANG F. Detection of causality between process variables based on industrial alarm data using transfer entropy [J].Entropy, 2015, 17(8): 5868-5887.
  [13] ELVIRA-ORTIZ D A, SAUCEDO-DORANTES J J, OSORNIO-RIOS R A, et al. An entropy-based condition monitoring strategy for the detection and classification of wear levels in gearboxes [J].Entropy, 2023, 25(3): 424.
  [14] GERMÁN-SALLÓ Z. Entropy indices based fault detection [J].Procedia Manufacturing, 2020, 46: 549-554.
  [15] GUO J Y, ZHAO W J, LI Y. Fault detection in multimodal processes based on the local entropy double subspace [J].Transactions of the Institute of Measurement and Control, 2023, 45(7): 1323-1336.
  [16] XIAO D Y, QIN C J, YU H G, et al. Unsupervised deep representation learning for motor fault diagnosis by mutual information maximization [J].Journal of Intelligent Manufacturing, 2021, 32(2): 377-391.
  [17] PU H Y, LIU J, CHEN Z, et al. Research on fault diagnosis method based on structural causal model in Tennessee Eastman process: 7th International Conference on Computing, Control and Industrial Engineering [C]. Singapore: Springer, 2023: 851-864.
  [18] WANG Z W, LIANG B Y, GUO J J, et al. Fault diagnosis based on fusion of residuals and data for chillers [J].Processes, 2023, 11(8): 2323.
  [19] XU H X, REN T Y, MO Z D, et al. A fault diagnosis model for Tennessee Eastman processes based on feature selection and probabilistic neural network [J].Applied Sciences, 2022, 12(17): 8868.
  [20] CHEN J W, ZHAO C H. Multi-lag and multi-type temporal causality inference and analysis for industrial process fault diagnosis [J].Control Engineering Practice, 2022, 124: 105174.
  [21] YU W K, ZHAO C H, HUANG B, et al. An unsupervised fault detection and diagnosis with distribution dissimilarity and lasso penalty [J].IEEE Transactions on Control Systems Technology, 2024, 32(3): 767-779.
  [22] FAN Y Q, CUI X Y, HAN H, et al. Feasibility and improvement of fault detection and diagnosis based on factory-installed sensors for chillers [J].Applied Thermal Engineering, 2020, 164: 114506.
  [23] MUSTAFA F E, AHMED I, BASIT A, et al. An adaptive metaheuristic optimization approach for Tennessee Eastman process for an industrial fault tolerant control system [J].PLoS One, 2024, 19(2): e0296471.