Reinforcement-enhanced deep transfer fusion network for multi-domain transformer fault diagnosis via acoustic signatures
More details
Hide details
1
Binzhou Power Supply Company, State Grid Shandong Electric Power Company
Submission date: 2025-01-16
Final revision date: 2025-06-11
Acceptance date: 2025-06-18
Online publication date: 2025-07-02
Publication date: 2025-07-02
Corresponding author
Mingliang Mu
Binzhou Power Supply Company, State Grid Shandong Electric Power Company
KEYWORDS
TOPICS
ABSTRACT
During operation, power transformers generate continuous vibrational signatures bearing mechanical fault-induced impulses, which constitute the fundamental evidence for equipment condition assessment. To investigate acoustic-fingerprint characteristics under varying operating conditions, this paper proposes a Reinforced Integrated Deep Transfer Learning Network (REDTLN) for multi-fault-domain diagnostics. The methodology first constructs multiple specialized Deep Transfer Learning Networks (DTLNs) using novel kernel Maximum Mean Discrepancy (kMMD) variants, enabling source-specific adaptation to enrich transferable feature representations. Subsequently, a unified unsupervised ensemble framework integrates multi-metric divergence measures, employing a reinforcement-guided combinatorial search algorithm to discover optimal DTLN integration rules. This intelligent fusion mechanism significantly enhances multi-source transfer capability, improving diagnostic accuracy and robustness in dynamic noise environments and complex operational scenarios. Experimental results confirm the model's efficacy in precisely identifying abnormal states while maintaining sustained >95% accuracy for representative faults under diverse acoustic-interference conditions.
FUNDING
This study was supported by Project Supported by the State Grid Shandong Electric Power Company Technology Project Funding (520615240007).
REFERENCES (28)
1.
Tao LY, Yang XH, Zhou XC, et al. A novel transformers fault diagnosis method based on probabilistic neural network and bio-inspired optimizer. Sensors. 2021;21(11):3623.
https://doi.org/10.3390/s21113....
2.
Abbasi AR, Mohammad RM, Mohammad MA. Transformer winding faults detection based on time series analysis. IEEE T. Instrum. Meas. 2021;70:1–10.
https://doi.org/10.1109/TIM.20....
3.
Liu JN, Yao CG, Yu L, et al. Using MLP to locate transformer winding fault based on digital twin. Front. Energy Res. 2023;11:1175808.
https://doi.org/10.3389/fenrg.....
4.
Zeng B, Guo J, Zhu WQ, et al. A transformer fault diagnosis model based on hybrid grey wolf optimizer and LS-SVM. Energies. 2019;12(21):4170.
https://doi.org/10.3390/en1221....
5.
Peng XS, Yang F, Wang GJ, et al. A convolutional neural network-based deep learning methodology for recognition of partial discharge patterns from high-voltage cables. IEEE T. Power Deliver. 2019;34(4): 1460–1469.
https://doi.org/10.1109/TPWRD.....
6.
Besharatifard H, Hasanzadeh S, Heydarian-Forushani E, et al. Acoustic based localization of partial discharge inside oil-fflled transformers, IEEE Access. 2022;10:55288–55297.
https://doi.org/10.1109/ACCESS....
7.
Wu Y, Sun X, Zhang Y, et al. A power transformer fault diagnosis method-based hybrid improved seagull optimization algorithm and support vector machine. IEEE Access. 2022;10:17268–17286.
https://doi.org/10.1109/ACCESS....
8.
Rodriguez-Serna JM, Albarracin-Sanchez R, Garnacho F, et al. Partial discharges measurements for condition monitoring and diagnosis of power transformers: A review. Proc. 6th Int. Adv. Res. Workshop Transformers (ARWtr). 2019:83–88.
https://doi.org/10.23919/ARWtr....
9.
Liu M, Wang P, Zhou Q, et al. Remote fault diagnosis system for power transformer insulation based on RIA model. Proc. IEEE Int. Conf. High Voltage Eng. Appl. (ICHVE). 2016:1–4.
https://doi.org/10.1109/ICHVE.....
10.
Hou L, Bergmann NW. Novel industrial wireless sensor networks for machine condition monitoring and fault diagnosis, IEEE Trans. Instrum. Meas. 2012;61(10):2787–2798.
https://doi.org/10.1109/TIM.20....
11.
Bagheri M, Naderi MS, Blackburn T. Advanced transformer winding deformation diagnosis: Moving from off-line to on-line, IEEE Trans. Dielectr. Electr. Insul. 2012;19(6):1860–18702012.
https://doi.org/10.1109/TDEI.2....
12.
Portilla WH, Mayor GA, Guerra JP, et al. Detection of transformer faults using frequency-response traces in the low-frequency bandwidth, IEEE Trans. Ind. Electron. 2014;61(9):4971–4978.
https://doi.org/ 10.1109/TIE.2013.2282605.
13.
Guo H, Hou B, Jing Y, et al. Method for balancing short circuit impedance of multi-split rectiffer transformer, in Proc. IEEE Int. Conf. Appl. Supercond. Electromagn. Devices (ASEMD). 2020:1–2.
https://doi.org/10.1109/ASEMD4....
14.
Moradzadeh A, Pourhossein K, Mohammadi-Ivatloo B, et al. Locating inter-turn faults in transformer windings using isometric feature mapping of frequency response traces. IEEE Trans. Ind. Informat. 2021;17(1):6962–69702021.
https://doi.org/10.1109/TII.20....
15.
Nurmanova V, Bagheri M, Zollanvari A, et al. A new transformer FRA measurement technique to reach smart interpretation for inter-disk faults. IEEE Trans. Power Del. 2019;34(4):1508–1519.
https://doi.org/10.1109/TPWRD.....
16.
Gomez-Luna E, Aponte Mayor G, Gonzalez-Garcia C, et al. Current status and future trends in frequency-response analysis with a transformer in service. IEEE Trans. Power Del. 2013;28(2):1024–1031.
https://doi.org/10.1109/TPWRD.....
17.
Tenbohlen S, Beura CP, Siegel M. Condition assessment of power transformers by UHF PD measurements, in Proc. 9th Int. Conf. Condition Monitor. Diagnosis (CMD). 2022:5–10.
https://doi.org/10.23919/CMD54....
18.
Liao R, Guo C, Wang K, et al. Adaptive optimal kernel time-frequency representation technique for partial discharge ultra-high-frequency signals classiffcation, Electric Power Compon. Syst. 2015;43(4):449–460.
https://doi.org/10.1080/153250....
19.
Vu-Cong T, Dalstein M, Toigo C, et al. Partial discharge measurement in DC GIS: Comparison between conventional and UHF methods, in Proc. IEEE Conf. Electr. Insul. Dielectric Phenomena (CEIDP). 2021:607–610.
https://doi.org/10.1109/CEIDP5....
20.
Faiz J, Soleimani M. Assessment of computational intelligence and conventional dissolved gas analysis methods for transformer fault diagnosis, IEEE Trans. Dielectr. Electr. Insul. 2018;25(5):1798–1806.
https://doi.org/10.1109/TDEI.2....
21.
Bacha K, Souahlia S, Gossa M. Power transformer fault diagnosis based on dissolved gas analysis by support vector machine, Electric Power Syst. Res. 2012;83(1):73–79.
https://doi.org/10.1016/j.epsr....
22.
Yan R, Gao RX. Hilbert–Huang transform-based vibration signal analysis for machine health monitoring, IEEE Trans. Instrum. Meas. 2006;55(6): 2320–2329.
https://doi.org/10.1109/TIM.20....
23.
Li R, He D. Rotational machine health monitoring and fault detection using EMD-based acoustic emission feature quantiffcation, IEEE Trans. Instrum. Meas. 2012;61(4):990–1001.
https://doi.org/10.1109/TIM.20....
24.
Sun M, Bai X, Zhang W, et al. Jointed task of multi-scale CNN based power transformer fault diagnosis with vibration and sound signals, in Proc. Panda Forum Power Energy (PandaFPE). 2023:1761–1765.
https://doi.org/10.1109/PandaF....
25.
Dang XJ, Wang FH, Zhang X. Cochlear fflter cepstral coefffcients of acoustic signals for mechanical faults identiffcation of power transformer, in Proc. IEEE Sustain. Power Energy Conf. (iSPEC). 2019:1195–1200.
https://doi.org/10.1109/iSPEC4....
26.
Han S, Wan X, Lai Y, et al. DC bias diagnosis of power transformer with soundprint features, in Proc. 7th Int. Conf. Cyber Secur. Inf. Eng. 2022:213–217.
https://doi.org/10.1145/355881....
27.
Li X, Liao X, Lu D, et al. A robust classification method for power transformer status recognition based on sound signals, in Proc. 5th Int. Conf. Power Energy Eng. (ICPEE). 2021:153–157.
https://doi.org/10.1109/ICPEE5....
28.
Stone GC, Stranges MK, Dunn DG. 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 Ind. Appl. Mag. 2016;22(1):14–19
https://doi.org/10.1109/MIAS.2....