CONSTRUCTION OF MOTOR FAULT DIAGNOSIS MODEL BASED ON TUNABLE INPUT BLSTM NETWORK. SI

Feiyu Liu

View Full Paper

References

  1. [1] K. Y. Y. Keshun, W. P. Puzhou, and G. Y. Yingkui, “Towardefficient and interpretative rolling bearing fault diagnosis viaquadratic neural network with Bi-LSTM,” IEEE Internet ofThings Journal, vol. 11, no. 13, pp. 23002–23019, 2024.
  2. [2] M. Zabin, H. J. Choi, and J. Uddin, “Hybrid deep transferlearning architecture for industrial fault diagnosis using Hilberttransform and DCNN–LSTM,” The Journal of Supercomputing,vol. 79, no. 5, pp. 5181–5200, 2023.
  3. [3] L. Wei, X. Peng, and Y. Cao, “Enhanced fault diagnosis ofrolling bearings using an improved inception-LSTM network,”Nondestructive Testing and Evaluation, vol. 40, no. 7, pp. 3274–3293, 2025.
  4. [4] W. Guo, “Chain fault identification and power grid planningoptimisation in power systems considering multiple scenarios,”International Journal of Power and Energy Systems, vol. 44,no. 10, 2024.
  5. [5] R. Cai, B. Xia, X. M. Zhu, L. Wang, J. R. Gu, and J. G. Tang,“Design of a risk model and analytical decision information sys-tem for power operation in the context of smart grid,” Interna-tional Journal of Power and Energy Systems, vol. 44, no. 10,2024.
  6. [6] C. Ren, H. Li, and J. Lei, “A CNN-LSTM–based model to faultdiagnosis for CPR1000,” Nuclear Technology, vol. 209, no. 9,pp. 1365–1372, 2023.
  7. [7] M. Huang and C. Sheng, “Adaptive-conditional loss and cor-rection module enhanced informer network for long-tailed fault11diagnosis of motor,” Journal of Computational Design and En-gineering, vol. 11, no. 4, pp. 306–318, 2024.
  8. [8] D. Durairaj, T. K. Venkatasamy, and A. Mehbodniya, “Intru-sion detection and mitigation of attacks in microgrid using en-hanced deep belief network,” Energy Sources, Part A: Recovery,Utilization, and Environmental Effects, vol. 46, no. 1, pp. 1519–1541, 2024.
  9. [9] M. E. Akiner and M. Ghasri, “Comparative assessment of deepbelief network and hybrid adaptive neuro-fuzzy inference sys-tem model based on a meta-heuristic optimization algorithmfor precise predictions of the potential evapotranspiration,” En-vironmental Science and Pollution Research, vol. 31, no. 30,pp. 42719–42749, 2024.
  10. [10] Y. Kong, Z. Wang, and Y. Nie, “Unlocking the power of LSTMfor long term time series forecasting,” in Proceedings of theAAAI Conference on Artificial Intelligence, vol. 39, pp. 11968–11976, 2025.
  11. [11] S. Lu, J. Yang, and B. Yang, “Surgical instrument posture es-timation and tracking based on LSTM,” ICT Express, vol. 10,no. 3, pp. 465–471, 2024.
  12. [12] H. Zhang, H. Sun, and L. Kang, “Prediction of health level ofmultiform lithium sulfur batteries based on incremental capacityanalysis and an improved LSTM,” Protection and Control ofModern Power Systems, vol. 9, no. 2, pp. 21–31, 2024.
  13. [13] N. Kavitha, K. R. Soundar, and R. Karthick, “Automatic videocaptioning using tree hierarchical deep convolutional neural net-work and ASRNN-bi-directional LSTM,” Computing, vol. 106,no. 11, pp. 3691–3709, 2024.
  14. [14] R. Jigyasu, V. Shrivastava, and S. Singh, “Deep optimal featureextraction and selection-based motor fault diagnosis using vi-bration,” Electrical Engineering, vol. 106, no. 5, pp. 6339–6358,2024.
  15. [15] J. Guo, Q. He, and F. Gu, “DNOCNet: A novel end-to-endnetwork for induction motor drive systems fault diagnosis underspeed fluctuation condition,” IEEE Transactions on IndustrialInformatics, vol. 20, no. 6, pp. 8284–8293, 2024.
  16. [16] S. H. Hsu, C. H. Lee, and W. F. Wu, “Machine learning-basedonline multi-fault diagnosis for IMS using optimization tech-niques with stator electrical and vibration data,” IEEE Trans-actions on Energy Conversion, vol. 39, no. 4, pp. 2412–2424,2024.
  17. [17] S. Rokocakau, J. Riccio, and G. Tresca, “Fault diagnosis usingshallow neural networks for voltage source inverters in motordrives,” IEEE Transactions on Industry Applications, vol. 60,no. 5, pp. 7038–7047, 2024.
  18. [18] M. Zhang, Z. Zhang, and X. Wang, “The use of attention-enhanced CNN-LSTM models for multi-indicator and time-series predictions of surface water quality,” Water ResourcesManagement, vol. 38, no. 15, pp. 6103–6119, 2024.
  19. [19] Y. Cheng, H. Gu, and D. Song, “Fault diagnosis for drivingmotor with insufficient fault data: a data transfer generationmethod,” The International Journal of Advanced Manufactur-ing Technology, vol. 134, no. 3, pp. 1195–1218, 2024.
  20. [20] Y. Jiang, L. Zheng, and C. Tang, “LSTM-based node-gatedgraph neural network for cross-condition few-shot bearing faultdiagnosis,” IEEE Sensors Journal, vol. 24, no. 3, pp. 3445–3456,2024.
  21. [21] G. Fu, Q. Wei, and Y. Yang, “Bearing fault diagnosis with paral-lel CNN and LSTM,” Mathematical Biosciences and Engineer-ing, vol. 21, no. 2, pp. 2385–2406, 2024.
  22. [22] Q. Zhou and J. Tang, “An interpretable parallel spatial CNN-LSTM architecture for fault diagnosis in rotating machinery,”IEEE Internet of Things Journal, vol. 11, no. 19, pp. 31730–31744, 2024.

Important Links:

Go Back