A fault diagnosis method for coal mills based on Bayesian network under imbalanced data conditions

张涛; 邵毅; 刘乐源; 郝欣; 胡绍宇

doi:10.19666/j.rlfd.202503025

English

您当前的位置：

首页 >

文章列表页 >

A fault diagnosis method for coal mills based on Bayesian network under imbalanced data conditions

Thermal Power Generation Vol. 54, Issue 11, Pages: 117-125(2025)

更新时间：2026-08-11

- A fault diagnosis method for coal mills based on Bayesian network under imbalanced data conditions
- 作者机构：
  
  1. 辽宁东科电力有限公司
  2. 东北大学信息科学与工程学院
- 作者简介：
- 基金信息：
- DOI：10.19666/j.rlfd.202503025
  CLC： TM621
- Published：2025
- 稿件说明：
移动端阅览
[1]张涛,邵毅,刘乐源,等.基于贝叶斯网络的非均衡数据下磨煤机故障诊断方法[J],2025,54(11):117-125.
[1]张涛,邵毅,刘乐源,等.基于贝叶斯网络的非均衡数据下磨煤机故障诊断方法[J],2025,54(11):117-125. DOI： 10.19666/j.rlfd.202503025.

DOI：10.19666/j.rlfd.202503025.

摘要

针对燃煤电厂磨煤机制粉系统故障诊断中因数据分布不均衡导致的少数类故障诊断精度低、可解释性差的问题，提出一种融合SMOTE数据增强、Dirichlet先验平滑与贝叶斯网络的故障诊断方法。通过SMOTE技术对少数类故障样本进行特征空间扩展，缓解数据稀缺性；结合Dirichlet先验平滑优化贝叶斯网络条件概率估计，解决样本缺乏导致的零概率问题；构建分层贝叶斯网络架构，融合领域知识与数据驱动结构学习，实现故障节点快速推断与属性节点间接推断的双模式诊断策略。实验基于真实工业数据，在非均衡数据场景下，所提方法具有较高的诊断精度与可解释性，为磨煤机故障诊断提供兼具实时性、准确性及透明性的解决方案。

Abstract

To address the challenges of low diagnostic accuracy and poor interpretability for minority fault classes caused by imbalanced data distribution in coal mill pulverizing systems of coal-fired power plants

a fault diagnosis method integrating SMOTE data enhancement

Dirichlet prior smoothing

and Bayesian networks is proposed. The SMOTE technology expands the feature space of minority fault samples to alleviate data scarcity

while Dirichlet prior smoothing optimizes conditional probability estimation in Bayesian networks

resolving zero-probability issues caused by insufficient samples. A hierarchical Bayesian network architecture is constructed by incorporating domain knowledge and data-driven structure learning

enabling a dual-mode diagnosis strategy that combines rapid fault node inference with indirect attribute node analysis. The experimental results based on real industrial data demonstrate that the proposed method achieves high diagnostic accuracy and interpretability under imbalanced data scenarios. The solution provides real-time performance

precision

and transparency for coal mill fault diagnosis

offering significant engineering value.

关键词

Keywords

references

樊帅,肖军.锅炉制粉系统故障诊断方法[J].热力发电, 2015, 44(2):13-17.FAN Shuai, XIAO Jun. Fault diagnosis method of pulverizing system in utility boilers[J]. Thermal Power Generation, 2015, 44(2):13-17.

钱虹,张现涛.基于PCA-FINCH的磨煤机故障诊断方法[J].热力发电, 2023, 52(9):147-154.QIAN Hong, ZHANG Xiantao. Fault diagnosis method of coal mill based on PCA-FINCH[J]. Thermal Power Generation, 2023, 52(9):147-154.

姚天杨,茅大钧,韩万里.基于DPC-MND和多元状态估计的磨煤机故障预警研究[J].控制工程, 2024,31(5):928-937.YAO Tianyang, MAO Dajun, HAN Wanli. Research on fault warning of coal mills based on DPC-MND and multivariate state estimation technique[J]. Control Engineering of China, 2024, 31(5):928-937.

袁存波,田亮.基于改进证据理论的中速磨煤机故障诊断[J].华北电力大学学报(自然科学版), 2022, 49(6):84-91.YUAN Cunbo, TIAN Liang. Fault diagnosis of medium speed coal mill based on improved evidence theory[J].Journal of North China Electric Power University(Natural Science), 2022, 49(6):84-91.

JIANG X, ZHENG J, ZHUANG X, et al. Ensemble data augmentation for imbalanced fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2023,72:1-12.

赵小强,李森.不平衡数据下的轻量化轴承故障诊断方法[J].电子测量与仪器学报, 2024, 38(10):244-254.ZHAO Xiaoqiang, LI Sen. Fault diagnosis method for lightweight bearings under unbalanced data[J]. Journal of Electronic Measurement and Instrumentation, 2024,38(10):244-254.

毕凤荣,郭明智,毕晓阳,等.数据不平衡情况下的柴油机故障诊断方法[J].天津大学学报(自然科学与工程技术版), 2024, 57(8):810-820.BI Fengrong, GUO Mingzhi, BI Xiaoyang, et al. Diesel engine fault diagnosis method for imbalanced data[J].Journal of Tianjin University(Science and Technology),2024, 57(8):810-820.

YUE Y, HAMID R K, LEN G, et al. MSIFT:a novel endto-end mechanical fault diagnosis framework under limited&imbalanced data using multi-source information fusion[J]. Expert Systems with Applications, 2025, 274:126947.

李川,伍依凡,杨帅.不平衡分布的数据驱动故障诊断的研究进展[J].仪器仪表学报, 2023, 44(8):181-197.LI Chuan, WU Yifan, YANG Shuai. Research progress of fault diagnostics driven by imbalanced data distribution[J]. Chinese Journal of Scientific Instrument,2023, 44(8):181-197.

WANG C J, XU Z L. An intelligent fault diagnosis model based on deep neural network for few-shot fault diagnosis[J]. Neurocomputing, 2021, 456:550-562.

ZHU J, JIANG Q, SHEN Y, et al. Application of recurrent neural network to mechanical fault diagnosis:a review[J].Journal of Mechanical Science and Technology, 2022,36(2):527-542.

SABERI A N, BELAHCEN A, SOBRA J, et al.LightGBM-based fault diagnosis of rotating machinery under changing working conditions using modified recursive feature elimination[J]. IEEE Access, 2022, 10:81910-81925.

LIANG Z, ZHANG L, WANG X. A novel intelligent method for fault diagnosis of steam turbines based on TSNE and XGBoost[J]. Algorithms, 2023, 16(2):98.

王晓霞,李雷孝,林浩. SMOTE类算法研究综述[J].计算机科学与探索, 2024, 18(5):1135-1159.WANG Xiaoxia, LI Leixiao, LIN Hao. Survey of research on SMOTE type algorithms[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(5):1135-1159.

DEY I, PRATAP V. A comparative study of SMOTE,borderline-SMOTE, and ADASYN oversampling techniques using different classifiers[C]//2023 3rd international conference on smart data intelligence(ICSMDI), IEEE, 2023:294-302.

周萱,吴伟丽.基于改进SMOTE不均衡样本处理和IHPO-DBN的变压器故障诊断方法研究[J].电力系统保护与控制, 2024, 52(11):21-30.ZHOU Xuan, WU Weili. Transformer fault diagnosis method based on improved SMOTE unbalanced sample processing and IHPO-DBN[J]. Power System Protection and Control, 2024, 52(11):21-30.

刘云鹏,和家慧,许自强,等.基于SVM SMOTE的电力变压器故障样本均衡化方法[J].高电压技术, 2020,46(7):2522-2529.LIU Yunpeng, HE Jiahui, XU Ziqiang, et al. Equalization method of power transformer fault sample based on SVM SMOTE[J]. High Voltage Engineering, 2020, 46(7):2522-2529.

HOU Y, YANG A, GUO W, et al. Bearing fault diagnosis under small data set condition:a Bayesian network method with transfer learning for parameter estimation[J].IEEE Access, 2022, 10:35768-35783.

郑伟,姚远,刘乐源,等.基于贝叶斯网络的制粉系统安全控制方法[J].控制工程, 2023, 30(3):560-569.ZHENG Wei, YAO Yuan, LIU Leyuan, et al. Safety operation control for the coal pulverizing system based on Bayesian network[J]. Control Engineering of China, 2023,30(3):560-569.

MINJIE F, HAIDONG S, MINGHUI S, et al. Utilizing Bayesian generalization network for reliable fault diagnosis of machinery with limited data[J]. KnowledgeBased Systems, 2024, 305:112628.

DOOYOUL L, INU L, YOUNGCHAN K, et al. Sensor set optimization by functional model and Bayesian network for fault diagnosis of turbine generator lubrication system[J]. Engineering Applications of Artificial Intelligence, 2024, 138(B):109416.

张栋良,汪刘峰,洪勤勤,等.基于模糊贝叶斯网络的汽轮机组故障诊断研究[J].计算机仿真, 2022, 39(7):476-481.ZHANG Dongliang, WANG Liufeng, HONG Qinqin,et al. Research on fault diagnosis of turbo-generator set based on fuzzy Bayesian network[J]. Computer Simulation, 2022, 39(7):476-481.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Publicity Resources

基于故障树与模糊贝叶斯网络的电抗器故障风险评估

Review of fault monitoring and diagnosis for induced draft fans in power stations

MULTISENSOR INFORMATION MERGING TECHNOLOGY AND IT'S APPLICATION IN VIBRITION FAULT DIAGNOSIS OF ROTARY MACHINES

APPLICATION OF EXTENDED Petri NETWORK INTO FAULT DIAGNOSIS OF THERMAL POWER UNITS

APPLICATION OF MULTI-DIMENSIONAL BP NEURAL NETWORK IN FAULT DIAGNOSIS OF BOILERS

Related Author

刘亚乐

马宏忠

陈昱同

刘华冬

赵恒鑫

王毅

何新

李明昊

Related Institution

河海大学电气与动力工程学院

西安热工研究院有限公司

Changsha University of Science and Technology

North China Electric Power University

⁰