在現代工業中，旋轉電機廣泛應用於各個場域。隨著長時間運轉，其內部零件易因老化與磨損導致絕緣劣化與機械異常，進而引發突發性停機與重大經濟損失。為有效提升設備可靠性與維護效率，本研究提出一套整合局部放電、振動與電氣絕緣數據的多模態感測融合健康評估方法。實驗設計於實際工業場域進行感測器佈署與數據量測。局部放電檢測方面，採用高頻電流感測器量測局部放電訊號，依據訊號的相位與振幅繪製出局部放電圖譜，觀察局部放電訊號發生之相位與次數，並自圖譜中提取出放電特徵。振動量測部分，使用智慧感測模組擷取三軸振動加速度，透過時域統計分析提取特徵，用以評估旋轉電機之機械異常。最後，輔以近期離線量測之電氣絕緣指標資料，判斷設備絕緣材料之長期劣化程度與受潮情況。結合上述多模態感測特徵後，輸入至多模態神經網路（Multimodal Neural Network）模型，以推論旋轉電機整體健康評估指數。研究結果顯示，透過資料融合與機器學習技術，可顯著提升診斷可靠度與穩健性，較單一檢測手法更能全面掌握旋轉電機健康狀態，為智慧維護與預知保養提供實質應用潛力。

In contemporary industrial contexts, rotating electrical machines are utilized extensively across diverse sectors. With increasing operational duration, the internal components are subject to the effects of aging and wear, which frequently results in unanticipated periods of inactivity and substantial economic losses. This study proposes a multimodal sensing fusion-based method for health assessment that integrates partial discharge (PD), vibration, and electrical insulation data to enhance equipment reliability and maintenance efficiency.
The experimental framework was implemented in actual industrial settings, where sensors were deployed to collect data. For PD detection, high-frequency current transformers (HFCT) measure PD signals, and PD patterns are constructed from the phase and amplitude of these signals. These patterns are utilized to observe the occurrence phase and frequency of PD events, from which representative discharge features are extracted. Measurement of vibration is facilitated by a smart sensing module, which acquires triaxial acceleration data. Subsequently, time-domain statistical analysis is employed to extract features that evaluate mechanical anomalies. Furthermore, recent offline measurements of electrical insulation indicators are incorporated to assess the long-term degradation and moisture conditions of the insulation system.
The features extracted from these sensing modalities are then fed into a multimodal neural network, which serves to estimate a health index of the rotating machine. The experimental results demonstrate that the incorporation of data fusion and machine learning techniques significantly improves diagnostic reliability and robustness. The proposed method offers a more comprehensive understanding of machine health status, with the potential for practical applications in intelligent maintenance and predictive diagnostics.

[1] D. A. Nattrass, "Partial discharge measurement and interpretation," IEEE Electrical insulation magazine, vol. 4, no. 3, pp. 10-23, 2002.
[2] M. Tiboni, C. Remino, R. Bussola, and C. Amici, "A review on vibration-based condition monitoring of rotating machinery," Applied Sciences, vol. 12, no. 3, p. 972, 2022.
[3] G. Stone, M. K. Stranges, and D. G. Dunn, "Common questions on partial discharge testing: A review of recent developments in IEEE and IEC standards for offline and online testing of motor and generator stator windings," IEEE Industry Applications Magazine, vol. 22, no. 1, pp. 14-19, 2015.
[4] J. d. S. Cruz et al., "Partial discharges monitoring for electric machines diagnosis: A review," Energies, vol. 15, no. 21, p. 7966, 2022.
[5] M. Tsypkin, "Induction motor condition monitoring: Vibration analysis technique-A practical implementation," in 2011 IEEE International Electric Machines & Drives Conference (IEMDC), 2011: IEEE, pp. 406-411.
[6] M. Messaoudi and L. Sbita, "Multiple Faults Diagnosis in Induction Motor Using the MCSA Method," International Journal of Signal & Image Processing, vol. 1, no. 3, 2010.
[7] X. Xu, Z. Tao, W. Ming, Q. An, and M. Chen, "Intelligent monitoring and diagnostics using a novel integrated model based on deep learning and multi-sensor feature fusion," Measurement, vol. 165, p. 108086, 2020.
[8] S. A. Mortazavizadeh and S. Mousavi, "A review on condition monitoring and diagnostic techniques of rotating electrical machines," Physical Science International Journal, vol. 4, no. 3, p. 310, 2014.
[9] S. S. Refaat, M. A. Saleh, and S. M. Kameli, "A Review on Partial Discharge Detection Techniques in High Voltage Rotating Machines," in IECON 2024-50th Annual Conference of the IEEE Industrial Electronics Society, 2024: IEEE, pp. 1-7.
[10] G. C. Stone, "A perspective on online partial discharge monitoring for assessment of the condition of rotating machine stator winding insulation," IEEE Electrical Insulation Magazine, vol. 28, no. 5, pp. 8-13, 2012.
[11] G. C. Stone, "Partial discharge diagnostics and electrical equipment insulation condition assessment," IEEE Transactions on Dielectrics and Electrical Insulation, vol. 12, no. 5, pp. 891-904, 2005.
[12] S. M. Tetrault, G. C. Stone, and H. G. Sedding, "Monitoring partial discharges on 4-kV motor windings," IEEE Transactions on Industry Applications, vol. 35, no. 3, pp. 682-688, 2002.
[13] I. F. Carvalho, E. G. da Costa, L. A. M. M. Nobrega, and A. D. d. C. Silva, "Identification of partial discharge sources by feature extraction from a signal conditioning system," Sensors, vol. 24, no. 7, p. 2226, 2024.
[14] A. Abubakar and C. Zachariades, "Phase-resolved partial discharge (PRPD) pattern recognition using image processing template matching," Sensors, vol. 24, no. 11, p. 3565, 2024.
[15] C. Hudon and M. Belec, "Partial discharge signal interpretation for generator diagnostics," IEEE Transactions on Dielectrics and Electrical Insulation, vol. 12, no. 2, pp. 297-319, 2005.
[16] Y.-T. Chen, J.-C. Lai, Y.-M. Jheng, C.-C. Kuo, and H.-C. Chang, "Partial discharge detection for stator winding insulation of motors using artificial neural network," Advances in Mechanical Engineering, vol. 10, no. 7, p. 1687814018786128, 2018.
[17] F.-C. Gu, "Identification of partial discharge defects in gas-insulated switchgears by using a deep learning method," IEEE Access, vol. 8, pp. 163894-163902, 2020.
[18] M. Florkowski, "Classification of partial discharge images using deep convolutional neural networks," Energies, vol. 13, no. 20, p. 5496, 2020.
[19] Q. Liu, X. Liu, and G. Chen, "Study on feature extraction of high speed precision electric machine vibration signal," in 2010 International Conference on Image Analysis and Signal Processing, 2010: IEEE, pp. 466-469.
[20] T. Williams, X. Ribadeneira, S. Billington, and T. Kurfess, "Rolling element bearing diagnostics in run-to-failure lifetime testing," Mechanical systems and signal processing, vol. 15, no. 5, pp. 979-993, 2001.
[21] F. Immovilli, A. Bellini, R. Rubini, and C. Tassoni, "Diagnosis of bearing faults in induction machines by vibration or current signals: A critical comparison," IEEE Transactions on Industry Applications, vol. 46, no. 4, pp. 1350-1359, 2010.
[22] M.-C. Kim, J.-H. Lee, D.-H. Wang, and I.-S. Lee, "Induction motor fault diagnosis using support vector machine, neural networks, and boosting methods," Sensors, vol. 23, no. 5, p. 2585, 2023.
[23] F. Jia, Y. Lei, J. Lin, X. Zhou, and N. Lu, "Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data," Mechanical systems and signal processing, vol. 72, pp. 303-315, 2016.
[24] Y. Zhang, T. Zhou, X. Huang, L. Cao, and Q. Zhou, "Fault diagnosis of rotating machinery based on recurrent neural networks," Measurement, vol. 171, p. 108774, 2021.
[25] Z. Chen and W. Li, "Multisensor feature fusion for bearing fault diagnosis using sparse autoencoder and deep belief network," IEEE Transactions on instrumentation and measurement, vol. 66, no. 7, pp. 1693-1702, 2017.
[26] J. Penman, H. Sedding, B. Lloyd, and W. Fink, "Detection and location of interturn short circuits in the stator windings of operating motors," IEEE transactions on Energy conversion, vol. 9, no. 4, pp. 652-658, 1994.
[27] S. Nandi, H. A. Toliyat, and X. Li, "Condition monitoring and fault diagnosis of electrical motors—A review," IEEE transactions on energy conversion, vol. 20, no. 4, pp. 719-729, 2005.
[28] M. Benco, R. Hudec, P. Kamencay, M. Zachariasova, and S. Matuska, "An advanced approach to extraction of colour texture features based on GLCM," International Journal of Advanced Robotic Systems, vol. 11, no. 7, p. 104, 2014.
[29] S. Sun, Y. Sun, G. Xu, L. Zhang, Y. Hu, and P. Liu, "Partial discharge pattern recognition of transformers based on the gray-level co-occurrence matrix of optimal parameters," Ieee Access, vol. 9, pp. 102422-102432, 2021.
[30] X. Peng, C. Zhou, D. M. Hepburn, M. D. Judd, and W. H. Siew, "Application of K-Means method to pattern recognition in on-line cable partial discharge monitoring," IEEE Transactions on Dielectrics and Electrical Insulation, vol. 20, no. 3, pp. 754-761, 2013.
[31] E. A. Burda, G. V. Zusman, I. S. Kudryavtseva, and A. P. Naumenko, "An overview of vibration analysis techniques for the fault diagnostics of rolling bearings in machinery," Shock and Vibration, vol. 2022, no. 1, p. 6136231, 2022.
[32] N. Tandon, "A comparison of some vibration parameters for the condition monitoring of rolling element bearings," Measurement, vol. 12, no. 3, pp. 285-289, 1994.
[33] S. Durgam, L. N. Bawankule, and P. S. Khindkar, "Prediction of fault detection based on vibration analysis for motor applications," in 2021 4th Biennial International Conference on Nascent Technologies in Engineering (ICNTE), 2021: IEEE, pp. 1-5.
[34] J. Ngiam, A. Khosla, M. Kim, J. Nam, H. Lee, and A. Y. Ng, "Multimodal deep learning," in ICML, 2011, vol. 11, pp. 689-696.
[35] J. Wang, P. Fu, L. Zhang, R. X. Gao, and R. Zhao, "Multilevel information fusion for induction motor fault diagnosis," IEEE/ASME Transactions on Mechatronics, vol. 24, no. 5, pp. 2139-2150, 2019.
[36] T. A. Shifat and J.-W. Hur, "ANN assisted multi sensor information fusion for BLDC motor fault diagnosis," IEEE Access, vol. 9, pp. 9429-9441, 2021.
[37] G. Stone, H. Sedding, C. Chan, and C. Wendel, "Comparison of low frequency and high frequency PD measurements on rotating machine stator windings," in 2018 IEEE Electrical Insulation Conference (EIC), 2018: IEEE, pp. 349-352.
[38] A. Suresh and K. Shunmuganathan, "Image texture classification using gray level co-occurrence matrix based statistical features," European Journal of Scientific Research, vol. 75, no. 4, pp. 591-597, 2012.
[39] R. Zhao, R. Yan, Z. Chen, K. Mao, P. Wang, and R. X. Gao, "Deep learning and its applications to machine health monitoring," Mechanical Systems and Signal Processing, vol. 115, pp. 213-237, 2019.
[40] J. Xiong, Q. Zhang, J. Wan, L. Liang, P. Cheng, and Q. Liang, "Data fusion method based on mutual dimensionless," IEEE/ASME Transactions on mechatronics, vol. 23, no. 2, pp. 506-517, 2017.
[41] R. P. Singh and M. Siddh, "Health Index & Life Expentancy of HV Motor," IJSRD–International Journal of Science Technology & Enginering, vol. 2, no. 10, 2016.