Research of fault diagnosis and prediction based on Bayesian networks and time series model for meta-action

Abstract

Nowadays, electromechanical products have complex structures and a higher incidence of failures. However, traditional fault prediction methods lack accuracy, causing maintenance delays. To address this, a precise fault diagnosis and prediction model based on BN (Bayesian Network) and time series, grounded in MA (Meta-Action) theory, is proposed in this research. Firstly, the FMA (Function-Motion-Action) method decomposes electromechanical products into simpler MA and MAU (Meta-action Unit), reflecting the quality characteristics of the entire product. Next, the BN model is constructed with MA and fault phenomenon as nodes, enabling the diagnosis of faulty MA. Meanwhile, the vibration signal is saved as the standard time series and the database is established. Thirdly, to compare the similarity between different time series, a time series model is constructed. A distance dissimilarity matrix is established by calculating the ED (Euclidean distance) between abnormal and standard time series. The DTW (Dynamic Time Warping) algorithm is applied to compute the warping cost between signals and identify the optimal warping path. Early warnings are issued based on the cumulative costs along each optimal path, focusing on the fault mode and faulty MA with the lowest cumulative cost. Finally, experimental analysis is conducted on the CNC (Computer Numerical Control) rotary table of a specific domestic machining center model, A comparative study using multiple methods showed that the fault prediction accuracy of the proposed method reached 90.51%, demonstrating the model’s ability to effectively predict various fault types. Besides, the macro-mean recall reached 0.896, highlighting the model’s strong performance in multi-fault classification with unbalanced data and reduced sensitivity to sample size. These results confirmed the superiority of the method proposed in this research. Furthermore, the method is applicable to other electromechanical products with structures similar to CNC machine tools.

Keywords

Meta-action Bayesian network diagnosis time series model optimal warping path

Get full access to this article

View all access options for this article.

References

Ding

Xiong

Cheng

, et al. Safety performance evaluation of intelligent valve port independent electro-hydraulic control system. J Mech Eng 2024; 60(04): 101–112.

Liu

Mvungi

ESB

Zhang

, et al. Fault diagnosis in partially observable petri nets with quantum Bayesian learning. Appl Sci 2023; 14(1): 52.

Liu

Bao

Wind turbine fault diagnosis method based on resampling denoising and principal component analysis with wide convolutional deep neural networks. Power Gener Technol 2023; 44(6): 824–832.

Aboshosha

Hamad

HA.

Employing adaptive fuzzy computing for RCP intelligent control and fault diagnosis. Nucl Sci Tech 2023; 34(9): 138.

Soares

JLL

Costa

Moura

, et al. Fault diagnosis of belt conveyor idlers based on gradient boosting decision tree. Int J Adv Manuf Technol 2024; 132(7-8): 3479–3510.

Wang

Zhang

Dong

Research on mechanical bearing fault diagnosis method based on fuzzy neural network. Ind Control Comput 2024; 37(01): 24–25.

Prasad

KVSR

Singh

. Spectrum prediction indicating bearing state in induction motor by forced vibration analysis and fuzzy logic technique. J Fail Anal Prev 2023; 23(5): 2204–2214.

Liao

Discovering prognostic features using genetic programming in remaining useful life prediction. IEEE Trans Ind Electron 2014; 61(5): 2464–2472.

Feng

Smith

Randall

, et al. Vibration-based monitoring and prediction of surface profile change and pitting density in a spur gear wear process. Mech Syst Signal Process 2022; 165: 108319.

10.

Feng

Zhang

, et al. Digital twin-driven intelligent assessment of gear surface degradation. Mech Syst Signal Process 2023; 186: 109896.

11.

Frizzo Stefenon

Zanetti Freire

dos Santos Coelho

, et al. Electrical insulator fault forecasting based on a wavelet neuro-fuzzy system. Energies 2020; 13(2): 484.

12.

Zhang

Wang

, et al. Distributed deep learning enabled prediction on cutting tool wear and remaining useful life. Proc IMechE, Part B: J Engineering Manufacture 2023; 237(14): 2203–2213.

13.

Chen

Zhang

Wang

, et al. Prediction of DC motor brush state based on particle filtering algorithm. Opt Photon 2024; 22(04): 49–54.

14.

Guo

Niu

, et al. Fault probability prediction of power transformers over the entire life cycle based on Bayesian algorithm. Electron Des Eng 2023; 31(13): 32–35.

15.

Feng

, et al. A review of vibration-based gear wear monitoring and prediction techniques. Mech Syst Signal Process 2023; 182: 109605.

16.

Zhang

Shi

, et al. Comprehensive extraction technology of key quality characteristics of meta-action unit for CNC machine tools design. Proc IMechE, Part B: J Engineering Manufacture 2023; 238(12): 1805–1814.

17.

, et al. Predictive analysis of the precision remaining useful life of CNC machine tools based on meta-action unit. Proc IMechE, Part B: J Engineering Manufacture 2024; 239(1-2): 185–197.

18.

. Research on active elimination technology for early faults of electromechanical products. Chongqing: Chongqing University, 2022.

19.

Huang

Ran

, et al. Assembly reliability control technology based on motion unit fault modeling. J Central South Univ 2018; 49(09): 2197–2205.

20.

Ren

Development overview and research trends of Bayesian decision theory. Stud Philos Sci Technol 2013; 30(02): 1–7.

21.

Cui

Zhang

Shi

, et al. A method for satellite time series anomaly detection based on fast-DTW and improved-KNN. Chin J Aeronaut 2023; 36(2): 149–159.

22.

Song

Cui

, et al. Load curve clustering method based on Euclidean dynamic time warping distance and entropy weight method. Autom Electr Power Syst 2020; 44(15): 87–94.

23.

Teeraratkul

O’Neill

Lall

Shape-based approach to household electric load curve clustering and prediction. IEEE Trans Smart Grid 2017; 9(5): 5196–5206.

24.

Song

Cui

, et al. Load curve clustering method based on improved piecewise linear representation combined with dynamic time warping. Autom Electr Power Syst 2021; 45(02): 89–96.

25.

Qiu

Song

Noise-robust dynamic time warping algorithm. SPE Comput Appl 2023; 43(06): 1855–1860.

26.

Tang

Research on similarity measurement algorithm for time series based on DTW. Jiangnan University, 2023.

27.

Wen

, et al. A novel method of key meta-action unit integrated identification for CNC machine tool reliability. Comput Ind Eng 2023; 177: 109073.

28.

Research on fault tracing and analysis technology of CNC machine tools based on elemental actions. Chongqing University, 2021.

29.

Ran

Zhang

Quality characteristic association analysis of computer numerical control Machine tool based on meta-action assembly unit. Adv Mech Eng 2016; 8(1): 1–10.

30.

Tong

Cheng

. Fault diagnosis method for automotive networks based on information fusion using Bayesian networks. ISRN Automot Eng 2015; 37(10): 1190–1194.

31.

Tang

Gao

Dynamic time warping algorithm with adaptive weighting of extreme points. Comput Eng 2023; 49(07): 150–160.

32.

Guo

Yang

, et al. CUDA-based parallelization of time-weighted dynamic time warping algorithm for time series analysis of remote sensing data. Comput Geosci 2022; 164: 105122.