Journal of Power Electronics

The Korean Institute of Power Electronics (전력전자학회)
권호 표지
DOI QR코드

DOI QR Code

Attention-parallel multisource data fusion residual network-based open-circuit fault diagnosis of cascaded H-bridge inverters

  • Weiman Yang (College of Electrical and Information Engineering, Lanzhou University of Technology) ;
  • Jianfeng Gu (College of Electrical and Information Engineering, Lanzhou University of Technology) ;
  • Xinggui Wang (College of Electrical and Information Engineering, Lanzhou University of Technology) ;
  • Weinian Wang (College of Electrical and Information Engineering, Lanzhou University of Technology)
  • Received : 2023.09.26
  • Accepted : 2024.01.22
  • Published : 2024.06.20
⟨ Previous Next ⟩

Abstract

Aiming to solve the problems of multiple internal power components, high fault probability, high similarity of the fault features of different power components, difficulty of traditional fault diagnosis feature extraction and low accuracy of fault identification in high-voltage multilevel cascaded H-bridge inverters, this paper presents a fault diagnosis method based on an attention-parallel multisource data fusion residual network. First, a parallel residual neural network model is established, and the extracted multilevel three-phase voltage before filtering and the three-phase current waveform after filtering are converted into two-dimensional image data using a wavelet transform. Subsequently, a feature fusion module is integrated into the network structure to adaptively extract features at different network levels. This module locates key features using the attention mechanism. Then, it fuses useful fault information into feature images using the feature fusion mechanism, enhancing the feature representation capability of the network. Finally, the fault features extracted by the feature fusion module undergo the complete convolution operation. The final enhanced features are used as classification features and classified using a softmax layer. Experimental results demonstrate that the proposed method exhibits high fault diagnosis accuracy and adaptability.

Keywords

Acknowledgement

This work was support by the National Natural Science Foundation of China (No.51867016); Outstanding Youth Fund Project of the Gansu Science Technology Support Program (22JR5RA221); Lanzhou University of Technology Hongliu Excellent Young Talents Funding Project.

References

  1. Lee, S.S.: Single-stage switched-capacitor module (S3CM) topology for cascaded multilevel inverter. IEEE Trans. Power Electron. 33(10), 8204-8207 (2018) 
  2. Lou, H., Mao, C., Wang, D., et al.: Fundamental modulation strategy with selective harmonic elimination for multilevel inverters. IET Power Electronics. 7(8), 2173-2181 (2014) 
  3. Ma, Y.J., Tan, L.Q., Ma, K., et al.: Fault diagnosis and location method for half-bridge MMC-HVDC submodule. High Volt. Eng. 48(11), 4600-4609 (2022) 
  4. Han, J.X., Zhang, Z., Yin, X.G., et al.: Research on internal open-circuit fault characteristics and location method of cascaded power electronic transformer. Proc. CSEE 40(19), 6071-6084 (2020) 
  5. Ma, M.Y., Ling, F., Sun, Y.R., et al.: Review of intelligent fault diagnosis methods for three-phase voltage inverters. Proc. CSEE 40(23), 7683-7699 (2020) 
  6. Xiao, Y.Y., Shen, Y., Yang, F., et al.: Open fault detection of cascade H-bridge converter power unit based on fault state variable integral. Power Syst. Technol. 45(11), 4213-4225 (2021) 
  7. Wang, T., Qi, J., Xu, H., et al.: Fault diagnosis method based on FFT-RPCA-SVM for cascaded-multilevel inverter. ISA Trans. 60, 156-163 (2016) 
  8. Li, H., Kang, J., Li, W.: Fault diagnosis of three-level inverters based on ensemble empirical mode decomposition and deep neural network. In: Conference Proceedings of 2021 International Joint Conference on Energy, Electrical and Power Engineering. Singapore. Springer Nature Singapore. pp. 207-216 (2022) 
  9. Yuan, Q., Tu, Q., Yan, L., et al.: Fault diagnosis of H-bridge cascaded five-level inverter based on improved support vector machine with gray wolf algorithm. Energy Rep. 9, 485-495 (2023) 
  10. Manjunath, T.G., Vikramathithan, A.C., Girish, H.: Analysis of total harmonic distortion and implementation of inverter fault diagnosis using artificial neural network. J. Phys. Conf. Ser. 2161(1), 012060 (2022) 
  11. Chen, S., Zhang, X.G.: Fault diagnosis of cascade H-bridge multilevel Inverter based on wavelet packet energy entropy and random forest. J. Nanjing Univ. 56(2), 284-289 (2019) 
  12. Cherif, B.D.E., Bendiabdellah, A., Tabbakh, M.: An automatic diagnosis of an inverter IGBT open-circuit fault based on HHTANN. Electr. Power Compon. Syst. 48(6-7), 589-602 (2020) 
  13. Shen, H.L., Tang, X., Luo, Y.F., et al.: Open-circuit fault diagnosis and sample condition analysis of three-phase inverter based on CNN. J. Natl. Univ. Def. Sci. Technol. 44(06), 163-172 (2022) 
  14. Du, B., He, Y., Zhang, C.: Intelligent diagnosis of cascaded H-bridge multilevel inverter combining sparse representation and deep convolutional neural networks. IET Power Electron. 14(6), 1121-1137 (2021) 
  15. He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770-778 (2016) 
  16. Diez-Olivan, A., Del Ser, J., Galar, D., et al.: Data fusion and machine learning for industrial prognosis: trends and perspectives towards Industry 40. Inf. Fusion 50, 92-111 (2019) 
  17. Hoang, D.T., Kang, H.J.: A motor current signal-based bearing fault diagnosis using deep learning and information fusion. IEEE Trans. Instrum. Meas. 69(6), 3325-3333 (2019) 
  18. Zhao, Y.Y., He, Y.G., Xing, Z.K., et al.: Open-circuit fault diagnosis method for DAB converter based on information fusion and deep residual shrinkage network. Electr. Power Autom. Equip. 43(02), 112-118 (2019) 
  19. Wu, X.Q., Liu, C., Li, R., et al.: Four-quadrant operation control technology for high-voltage direct-mounted large-capacity systems with battery energy storage and reactive power compensation. In: Proceedings of the CSEE. pp. 1-14 (2023) 
  20. Yang, X.D., Wang, C.L., Shi, L.P.: Research on IGBT open-circuit fault diagnosis for H-bridge inverter. Electr. Mach. Control 18(5), 112-118 (2014) 
  21. Zhao, K., Cheng, F., Ji, W.: Variable step adaptive kurtogram method based on empirical wavelet transform for rolling bearing fault diagnosis. J. Mech. Sci. Technol. 36(6), 2695-2708 (2022) 
  22. Wen, Z.P., Chen, J., Liu, L.H., et al.: Fault diagnosis of wind turbine gearbox based on wavelet transform and optimized CNN. J. Zhejiang Univ. 56(6), 1212-1219 (2022) 
  23. Li, X., Wang, W., Hu, X., et al.: Selective kernel networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 510-519 (2019) 
  24. Zhang, S., Liu, Z., Chen, Y., et al.: Selective kernel convolution deep residual network based on channel-spatial attention mechanism and feature fusion for mechanical fault diagnosis. ISA Trans. 133, 369-383 (2023) 
  25. Li, Z., Lam, H.F., Hu, J.: Adaptive resize-residual deep neural network for fault diagnosis of rotating machinery. Struct. Health Monit. 22(4), 2193-2213 (2023) 
  26. Liu, C., He, D., Chen, Y., et al.: Rolling bearing fault diagnosis of train running gear based on optimized deep residual network. In: 2021 5th International Conference on Automation, Control and Robots (ICACR). IEEE. pp. 168-172 (2021) 
  27. Zhou, Y., Shang, Q., Guan, C.: Three-phase asynchronous motor fault diagnosis using attention mechanism and hybrid CNN-MLP by multi-sensor information. IEEE Access 11, 98402-98414 (2023) 
  28. Wang, D., Li, Y., Jia, L., et al.: Novel three-stage feature fusion method of multimodal data for bearing fault diagnosis. IEEE Trans. Instrum. Meas. 70, 1-10 (2021) 
  29. Yang, W.M., Wang, W.N., Wang, X.G., et al.: Fault diagnosis method of cascaded H-Bridge inverter based on EEMD-MPE. In: International Conference on Wireless Power Transfer. pp. 938-950 (2022) 
  30. Shen, Y., Miao, B.: Open circuit fault diagnosis strategy for switch of three level inverter. J. Syst. Simul. 30(8), 3058-3065 (2019) 
  31. Yan, J.Y., Dong, Z., Fang, Y., et al.: Fault diagnosis of double bridge parallel excitation power unit based on 1D-CNN-LSTM hybrid neural network model. Power Syst. Technol. 45(5), 2025-2032 (2021)