少量样本下基于PCA-BNs的多故障诊断

王进花1,2,3,马雪花1,岳亮辉1,安永胜4,曹洁1

振动与冲击 ›› 2024, Vol. 43 ›› Issue (4) : 288-296.

PDF(1533 KB)
PDF(1533 KB)
振动与冲击 ›› 2024, Vol. 43 ›› Issue (4) : 288-296.
论文

少量样本下基于PCA-BNs的多故障诊断

  • 王进花1,2,3,马雪花1,岳亮辉1,安永胜4,曹洁1
作者信息 +

Multiple fault diagnosis based on PCA-BNs with a small number of samples

  • WANG Jinhua1,2,3, MA Xuehua1, YUE Lianghui1, AN Yongsheng2, CAO Jie1
Author information +
文章历史 +

摘要

针对一些工业设备因有标签故障样本数据少而导致诊断准确率低的问题,提出了一种PCA-BNs主成分分析和斯网络结合的多故障网络模型的建模方法。通过PCA对时序信号进行降维,得到相互独立的故障特征,提高提取故障关键信息的能力;利用融合单故障贝叶斯网络构建多故障贝叶斯网络结构的方法,解决BN建模过程耗时的问题;通过高斯分布与极大似然估计结合的方法确定网络参数,提高少量数据BN建模的精度,实现在少量样本下的故障诊断。实验结果表明,基于PCA-BNs的故障诊断方法在少量样本条件下,能实现高精度的故障诊断,并且有效缩减了算法运行时间。

Abstract

Aiming at the low diagnosis accuracy of some industrial equipment due to the lack of labeled fault sample data, a modeling method of multi fault network model based on PCA-BNs principal component analysis and Bayesian network (PCA-BNs) is proposed. The dimensionality of time series signals is reduced by PCA to obtain independent fault features and improve the ability of extracting key fault information; The method of fusing single fault Bayesian network to construct multi fault Bayesian network structure is used to solve the time-consuming problem of BN modeling process; The combination of Gaussian distribution and maximum likelihood estimation is used to determine the network parameters, improve the accuracy of BN modeling with a small amount of data, and realize fault diagnosis under small samples. The experimental results show that the PCA-BNs fault diagnosis method proposed in this paper can achieve high-precision fault diagnosis under the condition of small samples, and effectively reduce the running time of the algorithm.

引用本文

导出引用
王进花1,2,3,马雪花1,岳亮辉1,安永胜4,曹洁1. 少量样本下基于PCA-BNs的多故障诊断[J]. 振动与冲击, 2024, 43(4): 288-296
WANG Jinhua1,2,3, MA Xuehua1, YUE Lianghui1, AN Yongsheng2, CAO Jie1. Multiple fault diagnosis based on PCA-BNs with a small number of samples[J]. Journal of Vibration and Shock, 2024, 43(4): 288-296

参考文献

[1] 陈晓露,王瑞璇,王晶等.基于混合型判别分析的工业过程监控及故障诊断[J].自动化学报,2020,46(8):1600-1614. Chen Xiaolu, Wang Ruixuan, Wang Jing, et al. Industrial process monitoring and fault diagnosis based on mixed discriminant analysis [J]. Acta Automatica Sinica, 2020,46 (8): 1600-1614. [2] 刘建昌,权贺,于霞等.基于参数优化VMD和样本熵的滚动轴承故障诊断[J].自动化学报,2021. Liu Jianchang, Quan He, Yu Xia, et al. Rolling bearing fault diagnosis based on parameter optimization VMD and sample entropy [J]. Acta Automatica Sinica, 2021. [3] 韩敏,李宇,韩冰.基于改进结构保持数据降维方法的故障诊断研究[J].自动化学报,2021,47(2):338-348. Han Min, Li Yu, Han Bing. Research on fault diagnosis based on improved structure preserving data dimensionality reduction method [J]. Acta Automatica Sinica, 2021,47 (2): 338-348. [4] 王进花,朱恩昌,曹洁,余萍.基于修正IMM的风机变桨系统故障诊断方法[J].北京航空航天大学学报,2020,46(08):1460-1468. Wang Jinhua, Zhu Enchang, Cao Jie, Yu Ping. Fault diagnosis method of fan pitch system based on modified IMM [J]. Journal of Beijing University of Aeronautics and Astronautics, 2020,46 (08): 1460-1468. [5] de Souza R P P, Agulhari C M, Goedtel A, et al. Inter-turn short-circuit fault diagnosis using robust adaptive parameter estimation[J]. International Journal of Electrical Power & Energy Systems, 2022, 139: 107999. [6] Liu Y, Ferrari R, Wu P, et al. Fault diagnosis of the 10MW Floating Offshore Wind Turbine Benchmark: A mixed model and signal-based approach[J]. Renewable Energy, 2021, 164: 391-406. [7] 王贡献, 张淼, 胡志辉,等. 基于多尺度均值排列熵和参数优化支持向量机的轴承故障诊断[J]. 振动与冲击, 2022, 41(1):8. Wang Gongxian, Zhang Miao, Hu Zhihui, et al Bearing fault diagnosis based on multi-scale mean permutation entropy and parameter optimization support vector machine [J] Vibration and Shock, 2022, 41 (1): 8. [8] Wang H , Xu J , Yan R , et al. Intelligent Bearing Fault Diagnosis Using Multi-Head Attention-Based CNN[J]. Procedia Manufacturing, 2020, 49:112-118. [9] Chu, Caiyuan, et al. A novel multi-scale convolution model based on multi-dilation rates and multi-attention mechanism for mechanical fault diagnosis.[J].Digital Signal Processing,2021,122: 103355. [10] Zhu X , Hou D , Zhou P , et al. Rotor fault diagnosis using a convolutional neural network with symmetrized dot pattern images[J]. Measurement, 2019,138:526-535. [11] Khan T , Alekhya P , Seshadrinath J . Incipient Inter turn Fault Diagnosis in Induction motors using CNN and LSTM based Methods[C]. 2018 IEEE Industry Applications Society Annual Meeting (IAS). IEEE, 2018. [12] 孔子迁,邓蕾,汤宝平,韩延.基于时频融合和注意力机制的深度学习行星齿轮箱故障诊断方法[J].仪器仪表学报,2019, 40 (06):221-227. Kong Ziqian, Deng Lei, Tang Baoping, Han Yan. Fault diagnosis method of deep learning planetary gearbox based on time-frequency fusion and attention mechanism [J] Journal of Instrumentation, 2019, 40 (06): 221-227. [13] Zhao M , Kang M , Tang B , et al. Deep Residual Networks With Dynamically Weighted Wavelet Coefficients for Fault Diagnosis of Planetary Gearboxes[J]. IEEE Transactions on Industrial Electronics, 2018, 65(5):4290-4300. [14] 郭伟,邢晓松.基于改进卷积生成对抗网络的少样本轴承智能诊断方法[J].中国机械工程,2022,33(19):2347-2355. Guo Wei, Xing Xiaosong. Intelligent diagnosis method for bearings with few samples based on improved convolutional generative adversarial networks [J]. China Mechanical Engineering, 2022,33 (19): 2347-2355 [15] 祝世丰. 贝叶斯网络分类模型研究及其在小样本故障诊断中的应用[D]. 哈尔滨工业大学.机电工程学院.2009. Zhu Shifeng Research on Bayesian Network Classification Model and Its Application in Small Sample Fault Diagnosis [D] Harbin University of Technology. College of Mechanical and Electrical Engineering. 2009. [16] Wu G , J Tong , Zhang L , et al. Framework for fault diagnosis with multi-source sensor nodes in nuclear power plants based on a Bayesian network[J]. Annals of Nuclear Energy, 2018, 122:297-308. [17] Wang Y , Yang H , Yuan X , et al. An improved Bayesian network method for fault diagnosis[J]. IFAC-Papers OnLine, 2018, 51( 21):341-346. [18] J Wang, Wang Z , Stetsyuk V , et al. Exploiting Bayesian networks for fault isolation: A diagnostic case study of diesel fuel injection system[J]. ISA Transactions, 2019, 86:276-286. [19] Hu, Min, Chen, et al. A machine learning bayesian network for refrigerant charge faults of variable refrigerant flow air conditioning system[J]. ENERGY AND BUILDINGS, 2018,158:668-676. [20] Wang Z , Wang L , Tan Y , et al. Fault detection based on Bayesian network and missing data imputation for building energy systems[J]. Applied Thermal Engineering, 2021, 182:116051. [21] Lcla B , Aaj C . On overview of PCA application strategy in processing high dimensionality forensic data[J]. Microchemical Journal, 2021,169:106608. [22] Pu H A , Qy B , Fz A , et al. Double L 2,p - norm based PCA for Feature Extraction[J]. Information Sciences, 2021,573:345-359. [23] Santi M . An objective, principal-component -analysis (PCA) based, method which improves the quartz -crystal -microbalance (QCM) sensing performance[J]. Sensors and Actuators A: Physical, 2020, 315:112323. [24] 梁潇, 王海峰, 郭进,等. 基于贝叶斯网络的列控车载设备故障诊断方法[J]. 铁道学报, 2017(08):96-103. Liang Xiao, Wang Haifeng, Guo Jin, et al Fault diagnosis method of train control on-board equipment based on Bayesian network [J] Journal of Railways, 2017 (08): 96-103. [25] Pang T , Yu T , Song B . A Bayesian network model for fault diagnosis of a lock mechanism based on degradation data[J]. Engineering Failure Analysis, 2021, 122:105225. [26]王康,齐金平,周亚辉,李少雄,赵睿虎,郭浩.基于离散时间贝叶斯网络的列控中心可靠性分析[J].中国机械工程,2021, 32 (04): 390-398. Wang Kang, Qi Jinping, Zhou Yahui, Li Shaoxiong, Zhao Ruihu, Guo Hao. Reliability analysis of train control center based on discrete time Bayesian network [J] China Mechanical Engineering, 2021, 32 (04): 390-398. [27]王宁,王宇航,蔡志强等.基于贝叶斯网络的涡轴航空发动机性能优化策略[J].西北工业大学学报,2021,39(2):375-381. Wang Ning, Wang Yuhang, Cai Zhiqiang, et al. Performance optimization strategy of turboshaft aeroengine based on Bayesian network [J]. Journal of Northwest Polytechnical University, 2021,39 (2): 375-381 [28] 高洁. 基于贝叶斯网络的复杂工业过程故障诊断问题研究[D]. 浙江大学.2019. Gao Jie Research on Fault Diagnosis of Complex Industrial Process Based on Bayesian Network [D] Zhejiang University, 2019 [29] Lessmeier C, Kimotho J K , Zimmer D , et al. Condition Monitoring of Bearing Damage in Electromechanical Drive Systems by Using Motor Current Signals of Electric Motors: A Benchmark Data Set for Data-Driven Classification[C]. European Conference of the Prognostics and Health Management Society. 2016. [30]Han, T., Liu, C., Yang, W., & Jiang, D. (2019). Learning transferable features in deep convolutional neural networks for diagnosing unseen machine conditions. ISA Transaction . [31] Arellano-Espitia, F., Delgado-Prieto, M., Martinez-Viol, V., Saucedo-Dorantes, J. J., & Osornio-Rios, R. A. (2020). Deep Learning Based Methodology for Fault Diagnosis in Electromechanical Systems. Sensors, 20(14), 3949. [32]王晓玉,刘桂芳,韩宝坤等.堆叠自编码器在样本不充足下的轴承故障诊断方法[J].噪声与振动控制,2021,41(02):100-104+110. Wang Xiaoyu, Liu Guifang, Han Baokun, et al. A bearing fault diagnosis method for stacked autoencoders with insufficient samples [J]. Noise and Vibration Control, 2021,41 (02): 100-104+110

PDF(1533 KB)

327

Accesses

0

Citation

Detail

段落导航
相关文章

/