| 83 | 0 | 12 |
| 下载次数 | 被引频次 | 阅读次数 |
针对工业设备故障诊断中常面临的样本量大、参数繁杂等问题，提出了一种新型可扩展置信规则库模型（Extended Belief Rule Base, EBRB），该模型具有良好的可解释性和合理性，便于技术人员根据模型输出进行可靠的决策。首先，运用极致梯度提升方法对大量特征进行重要性评估，选取最具诊断价值的特征，有效降低问题维度；然后，在推理阶段，引入投影协方差矩阵自适应策略优化方法进行参数优化，从而提升模型性能；最后，在输出阶段，采用基于阈值的方式限制激活规则数量，并使用改进的证据推理引擎，以提高推理效率和准确性。结果表明：提出的EBRB在多个故障诊断任务中表现优异，在滚动体故障诊断中，准确率达98.15%，与K最邻近模型并列第一；在内圈故障诊断中，准确率为90.74%，优于所有其他对比模型；在外圈故障诊断中，准确率为88.89%，同样高于其他对比模型。实验结果验证了该模型在处理复杂工业设备故障诊断任务中的高准确性和鲁棒性，为工业设备故障诊断领域提供了一种新的有效解决方案。
Abstract：To address the problems of large sample sizes and complex parameters in industrial equipment fault diagnosis, a novel EBRB(Extended Belief Rule Base)model was proposed.This model had excellent interpretability and rationality, making it easy for technical personnel to make reliable decisions based on model outputs. First, the model employed the eXtreme Gradient Boosting method to assess the importance of numerous features and selected the most diagnostically-relevant ones, effectively reducing the dimensionality of the problem. Then, in the inference stage, the projection covariance matrix adaptive evolutionary strategy method was introduced to optimize the parameters, thereby improving the model's performance. Finally, in the output stage, a threshold-based approach was adopted to limit the number of activated rules, and an improved evidential reasoning engine was utilized to enhance inference efficiency and accuracy. The experimental results indicate that the proposed EBRB model performs exceptionally well in multiple fault diagnosis tasks. In the fault diagnosis of rolling elements, it achieves an accuracy of 98.15%, tying for first place with the K-nearest neighbors model. In the fault diagnosis of the inner circles, the model attains an accuracy of 90.74%, surpassing all the other comparative models. In the fault diagnosis of the outer circles, the model achieves an accuracy of 88.89%, which exceeds that of other comparative models. The results verify the high accuracy and robustness of the model in complex industrial equipment fault diagnosis tasks, thereby providing a new effective solution in the field of industrial equipment fault diagnosis.
[1]周玉蓉，张巧灵，于广增，等．基于声信号的工业设备故障诊断研究综述[J]．计算机工程与应用，2023,59(7):51-63.ZHOU Y R,ZHANG Q L,YU G Z,et al.Review of acoustic signal-based industrial equipment fault diagnosis[J].Computer Engineeringand Applications,2023,59(7):51-63.
[2] WEN L,LI X Y,GAO L,et al.A new convolutional neural network-based data-driven fault diagnosis method[J].IEEE Transactions on Industrial Electronics,2018,65(7):5990-5998.
[3] ZHANG L, XIA H, CHA B. Deep learning based fault diagnosis for chemical process with statistical feature fusion[C]//2023 42nd Chinese Control Conference(CCC). Piscataway, NJ, USA:IEEE,2023:8515-8520.
[4] JARDINE A K S,LIN D M,BANJEVIC D.A review on machinery diagnostics and prognostics implementing condition-based maintenance[J]. Mechanical Systems and Signal Processing, 2006, 20(7):1483-1510.
[5] LEE J,NI J,DJURDJANOVIC D,et al.Intelligent prognostics tools and e-maintenance[J].Computers in Industry,2006,57(6):476-489.
[6] LEI Y G,YANG B,JIANG X W,et al.Applications of machine learning to machine fault diagnosis:a review and roadmap[J]. Mechanical Systems and Signal Processing,2020,138:106587.
[7]胡茑庆，陈徽鹏，程哲，等．基于经验模态分解和深度卷积神经网络的行星齿轮箱故障诊断方法[J]．机械工程学报，2019,55(7):9-18.HU N Q,CHEN H P,CHENG Z,et al.Fault diagnosis for planetary gearbox based on EMD and deep convolutional neural networks[J]. Journal of Mechanical Engineering,2019,55(7):9-18.
[8]董家祥，翟纪宇，马昕，等．知识驱动的机械设备故障诊断[J]．计算机科学，2023,50(5):82-92.DONG J X,ZHAI J Y,MA X,et al.Mechanical equipment fault diagnosis driven by knowledge[J].Computer Science,2023,50(5):82-92.
[9]邓丰，陈依林，曾哲，等．数据-知识联合驱动的配电网高阻接地故障检测方法[J]．中国电机工程学报，2024,44(24):9618-9633.DENG F, CHEN Y L, ZENG Z, et al. Combined data-knowledge driven detection method for high impedance faultsin distribution networks[J].Proceedings of the CSEE, 2024, 44(24):9618-9633.
[10] LIU J,MARTINEZ L,CALZADA A,et al.A novel belief rule base representation, generation and its inference methodology[J]. KnowledgeBased Systems,2013,53:129-141.
[11] CALZADA A, LIU J, NUGENT C D, et al.Sensor-based activity recognition using extended belief rule-based inference methodology[C]//Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway,NJ,USA:IEEE,2014:2694-2697.
[12] YANG L H,WANG S H,YE F F,et al.Environmental investment prediction using extended belief rule-based system and evidential reasoning rule[J]. Journal of Cleaner Production, 2021, 289:125661.
[13] WANG Y M, YE F F, YANG L H. Extended belief rule based system with joint learning for environmental governance cost prediction[J]. Ecological Indicators,2020,111:106070.
[14] YE F F,YANG L H,LU H T,et al.A novel data-driven decision model based on extended belief rule base to predict China’s carbon emissions[J]. Journal of Environmental Management, 2022,318:115547.
[15]FU C,HOU B B,XUE M,et al.Extended belief rule-based system with accurate rule weights and efficient rule activation for diagnosis of thyroid nodules[J]. IEEE Transactions on Systems, Man,and Cybernetics:Systems,2023,53(1):251-263.
[16]YANG L H,YE F F,WANG Y M,et al.Extended belief rule-based system using bi-level joint optimization for environmental investment forecasting[J].Applied Soft Computing,2023,140:110275.
[17]ZHANG A, GAO F, YANG M, et al. A new rule reduction and training method for extended belief rule base based on DBSCAN algorithm[J].International Journal of Approximate Reasoning,2020,119:20-39.
[18]HUANG H Y,LIN Y Q,SU Q,et al.An ensemble approach for extended belief rule-based systems with parameter optimization[J]. International Journal of Computational Intelligence Systems,2019,12(2):1371-1381.
[19] QIU Y G,ZHOU J,KHANDELWAL M,et al.Performance evaluation of hybrid WOA-XGBoost,GWO-XGBoost and BO-XGBoost models to predict blast-induced ground vibration[J]. Engineering with Computers,2022,38(5):4145-4162.
[20] HU G X, HE W, SUN C, et al. Hierarchical belief rule-based model for imbalanced multi-classification[J].Expert Systems with Applications,2023,216:119451.
[21] MENON L, ANTENEODO C. Random search with resetting in heterogeneous environments[J].Physical Review E,2024,110(5-1):054111.
[22] ZHOU X J,ZHAO C N,HUANG Y Q,et al.Improved fractional-order gradient descent method based on multilayer perceptron[J]. Neural Networks,2025,183:106970.
[23] MAHBOUBI N, XIE J Y, HUANG B. Pointby-point transfer learning for Bayesian optimization:An accelerated search strategy[J]. Computers&Chemical Engineering,2025,194:108952.
[24] QIU M Q, ZHAO Z B. Bearing fault diagnosis using a novel coding-statistic feature combined with NNC[J]. Journal of Vibroengineering, 2022, 24(5):848-861.
[25] PENG X J, ZHANG B K, GAO D. Research on fault diagnosis method of rolling bearing based on 2DCNN[C]//2020 Chinese Control And Decision Conference(CCDC).Piscataway,NJ,USA:IEEE,2020:693-697.
基本信息:
DOI：10.20189/j.cnki.CN/61-1527/E.202502002
中图分类号:TH17
引用信息:
[1]冯树成,贺维,马宁等.基于可扩展置信规则库的工业设备故障诊断方法[J].火箭军工程大学学报,2025,39(02):13-21.DOI:10.20189/j.cnki.CN/61-1527/E.202502002.
基金信息:
火箭军工程大学重点实验室开放基金（AAIE-2023-0102）