Abstract
In this study, facing the condition of structural and informational defects and complex correlation in data of fault feature gases for transformers, a transformer fault diagnosis (TFD) method based on the two-dimensional cloud model (2D-CM) under defective data is investigated. Firstly, to solve the problem that the accuracy of TFD is impacted by the completeness of the priori rule set caused by the incompleteness, imbalance and feature redundancy of priori transformer fault information, a data processing framework based on the strengthened Mahalanobis distance self-organizing map (SMSOM) and data generation algorithm is proposed. By applying the data generation algorithm based on the Wasserstein conditional generative adversarial network with gradient penalty and the filtering algorithm of the generated data based on SMSOM, the data set can be expanded evenly and the diversity of feature information in the limited training set can be maximized. Secondly, fault data is converted to cloud concept combination by constructing 2D-CM and adopting the computing method of cloud membership degree under offset space. Finally, TFD is realized by multi-rule fusion reasoning under the complete prior rule knowledge obtained by rule mining from all concept combinations. The experimental results indicate that the proposed data processing framework can make the TFD model based on 2D-CM achieve a diagnostic accuracy of 83.1%, which is superior to other data processing schemes. Moreover, the proposed TFD model based on 2D-CM increases the diagnosis accuracy by 22.8% compared with the traditional 1D-CM.
Similar content being viewed by others
References
Elsisi M, Tran MQ, Mahmoud K et al (2022) Effective IoT-based deep learning platform for online fault diagnosis of power transformers against cyberattacks and data uncertainties. Measurement 190:110686
Ma X, Hu H, Shang Y (2021) A new method for transformer fault prediction based on multifeature enhancement and refined long short-term memory. IEEE Trans Instrum Meas 70:1–11
Ward SA, El-Faraskoury A, Badawi M et al (2021) Towards precise interpretation of oil transformers via novel combined techniques based on DGA and partial discharge sensors. Sensors 21(6):2223
Badawi M, Ibrahim SA, Mansour DEA et al (2022) Reliable estimation for health index of transformer oil based on novel combined predictive maintenance techniques. IEEE Access 10:25954–25972
Zhang Y, Chen HC, Du Y et al (2020) Power transformer fault diagnosis considering data imbalance and data set fusion. High Volt 6(3):543–554
Ghoneim SSM, Mahmoud K, Lehtonen M et al (2021) Enhancing diagnostic accuracy of transformer faults using teaching-learning-based optimization. IEEE Access 9:30817–30832
Emara MM, Peppas GD, Gonos IF (2021) Two graphical shapes based on dga for power transformer fault types discrimination. IEEE Trans Dielectr Electr Insul 28(3):981–987
Lu P, Li W, Huang D (2018) Transformer fault diagnosis method based on graph theory and rough set. J Intell Fuzzy Syst 35(1):223–230
Zhang D, Li C, Shahidehpour M et al (2022) A bi-level machine learning method for fault diagnosis of oil-immersed transformers with feature explainability. Int J Electr Power Energy Syst 134:107356
Kari T, Gao W, Zhao D et al (2018) An integrated method of ANFIS and Dempster-Shafer theory for fault diagnosis of power transformer. IEEE Trans Dielectr Electr Insul 25(1):360–371
Yan G, Jia S, Ding J et al (2019) A time series forecasting based on cloud model similarity measurement. Soft Comput 23(14):5443–5454
Liu HC, Wang LE, Li ZW et al (2018) Improving risk evaluation in FMEA with cloud model and hierarchical TOPSIS method. IEEE Trans Fuzzy Syst 27(1):84–95
Song W, Zhu J (2019) A multistage risk decision making method for normal cloud model considering behavior characteristics. Appl Soft Comput 78:393–406
Yu X, Zheng D, Zhou L (2021) Credit risk analysis of electricity retailers based on cloud model and intuitionistic fuzzy analytic hierarchy process. Int J Energy Res 45(3):4285–4302
Jiao S, Pan Z, Chen Y et al (2020) Cloud annealing: a novel simulated annealing algorithm based on cloud model. IEICE Trans Inf Syst 103(1):85–92
Zang W, Ren L, Zhang W et al (2018) A cloud model based DNA genetic algorithm for numerical optimization problems. Futur Gener Comput Syst 81:465–477
Jin Y, Sun Y, Ma H (2018) A developed artificial bee colony algorithm based on cloud model. Mathematics 6(4):61
Gu B, Zhang T, Meng H et al (2021) Short-term forecasting and uncertainty analysis of wind power based on long short-term memory, cloud model and non-parametric kernel density estimation. Renewable Energy 164:687–708
Dong X, Gao D, Li J et al (2021) Evaluation model on uncertainty of the wind turbine state. Sustain Energy Technol Assess 46:101303
Liao R, Zhang Y, Yang L et al (2014) A cloud and evidential reasoning integrated model for insulation condition assessment of high voltage transformers. Int Trans Electr Energy Syst 24(7):913–926
Jia C, Liu L, Gu X et al (2017) A novel link quality prediction algorithm for wireless sensor networks. Comput Sci Inf Syst 14(3):719–734
Wang M, Wang X, Liu Q et al (2020) A novel multi-dimensional cloud model coupled with connection numbers theory for evaluation of slope stability. Appl Math Model 77:426–438
Du J, Sun M (2020) Hierarchical assessment method of transformer condition based on weight-varying grey cloud model. Trans China Electrotech Soc 35(20):4306–4316
Lee S, Kim J, Lee G et al (2021) Prediction of aquatic ecosystem health indices through machine learning models using the WGAN-based data augmentation method. Sustainability 13(18):10435
Costa P, Galdran A, Meyer MI et al (2017) End-to-end adversarial retinal image synthesis. IEEE Trans Med Imaging 37(3):781–791
Pesteie M, Abolmaesumi P, Rohling RN (2019) Adaptive augmentation of medical data using independently conditional variational auto-encoders. IEEE Trans Med Imaging 38(12):2807–2820
Alves E, Leal A, Lopes M et al (2021) Performance analysis among predictive models of lightning occurrence using artificial neural networks and SMOTE. IEEE Lat Am Trans 19(5):755–762
Yi H, Jiang Q, Yan X et al (2020) Imbalanced classification based on minority clustering SMOTE with wind turbine fault detection application. IEEE Trans Ind Inf 17(9):5867–5875
Li J, He H, Li L (2018) CGAN-MBL for reliability assessment with imbalanced transmission gear data. IEEE Trans Instrum Meas 68(9):3173–3183
Yang D, Qin J, Pang Y et al (2021) A novel double-stacked autoencoder for power transformers DGA signals with imbalanced data structure. IEEE Trans Ind Electron 69(2):1977–1987
Gouda OE, El-Hoshy SH, Hassan HELT (2018) Proposed three ratios technique for the interpretation of mineral oil transformers based dissolved gas analysis. IET Gener Transm Distrib 12(11):2650–2661
Liu HC, Luan X, Li ZW et al (2017) Linguistic Petri nets based on cloud model theory for knowledge representation and reasoning. IEEE Trans Knowl Data Eng 30(4):717–728
Rigamonti M, Baraldi P, Alessi A et al (2018) An ensemble of component-based and population-based self-organizing maps for the identification of the degradation state of insulated-gate bipolar transistors. IEEE Trans Reliab 67(3):1304–1313
Guo Z, Pu Z, Du W et al (2022) Improved adversarial learning for fault feature generation of wind turbine gearbox. Renew Energy 185:255–266
Wickramasinghe CS, Amarasinghe K, Manic M (2019) Deep self-organizing maps for unsupervised image classification. IEEE Trans Industr Inf 15(11):5837–5845
Sun S (2021) Segmentation-based adaptive feature extraction combined with mahalanobis distance classification criterion for heart sound diagnostic system. IEEE Sens J 21(9):11009–11022
Sun S, Wang H, Chang Z et al (2018) On the mahalanobis distance classification criterion for a ventricular septal defect diagnosis system. IEEE Sens J 19(7):2665–2674
Zeng S, Wang X, Duan X et al (2020) Kernelized mahalanobis distance for fuzzy clustering. IEEE Trans Fuzzy Syst 29(10):3103–3117
Duval M, DePabla A (2001) Interpretation of gas-in-oil analysis using new IEC publication 60599 and IEC TC 10 databases. IEEE Electr Insul Mag 17(2):31–41
Benmahamed Y, Teguar M, Boubakeur A (2017) Application of SVM and KNN to Duval Pentagon 1 for transformer oil diagnosis. IEEE Trans Dielectr Electr Insul 24(6):3443–3451
Acknowledgements
The authors gratefully acknowledge the support of the National Natural Science Foundation of China (61803233).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
See Fig. 13.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Bai, X., Zang, Y., Li, J. et al. Transformer fault diagnosis method based on two-dimensional cloud model under the condition of defective data. Electr Eng 106, 1–13 (2024). https://doi.org/10.1007/s00202-023-01964-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00202-023-01964-7