A Dynamic Adam Based Deep Neural Network for Fault Diagnosis of Oil-Immersed Power Transformers

This paper presents a Dynamic Adam and dropout based deep neural network (DADDNN) for fault diagnosis of oil-immersed power transformers. To solve the problem of incomplete extraction of hidden information with data driven, the gradient first-order moment estimate and second-order moment estimate are used to calculate the different learning rates for all parameters with stable gradient scaling. Meanwhile, the learning rate is dynamically attenuated according to the optimal interval. To prevent over-fitted, we exploit dropout technique to randomly reset some neurons and strengthen the information exchange between indirectly-linked neurons. Our proposed approach was utilized on four datasets to learn the faults diagnosis of oil-immersed power transformers. Besides, four benchmark cases in other fields were also utilized to illustrate its scalability. The simulation results show that the average diagnosis accuracies on the four datasets of our proposed method were 37.9%, 25.5%, 14.6%, 18.9%, and 11.2%, higher than international electro technical commission (IEC), Duval Triangle, stacked autoencoders (SAE), deep belief networks (DBN), and grid search support vector machines (GSSVM), respectively.

[1]  Jing Wu,et al.  A Novel Integrated Method to Diagnose Faults in Power Transformers , 2018, Energies.

[2]  Ruijin Liao,et al.  A New Support Vector Machine Model Based on Improved Imperialist Competitive Algorithm for Fault Diagnosis of Oil-immersed Transformers , 2017 .

[3]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Ke Wang,et al.  A Transformer Fault Diagnosis Model Using an Optimal Hybrid Dissolved Gas Analysis Features Subset with Improved Social Group Optimization-Support Vector Machine Classifier , 2018, Energies.

[5]  Mehdi Bagheri,et al.  Transformer Fault Condition Prognosis Using Vibration Signals Over Cloud Environment , 2018, IEEE Access.

[6]  Shuaibing Li,et al.  Interpretation of DGA for transformer fault diagnosis with complementary SaE-ELM and arctangent transform , 2016, IEEE Transactions on Dielectrics and Electrical Insulation.

[7]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[8]  Sheng-wei Fei,et al.  Fault diagnosis of power transformer based on support vector machine with genetic algorithm , 2009, Expert Syst. Appl..

[9]  Gehao Sheng,et al.  Prediction of Dissolved Gas Concentrations in Transformer Oil Based on the KPCA-FFOA-GRNN Model , 2018 .

[10]  Shakeb A. Khan,et al.  A comprehensive comparative study of DGA based transformer fault diagnosis using fuzzy logic and ANFIS models , 2015, IEEE Transactions on Dielectrics and Electrical Insulation.

[11]  Chia-Hung Lin,et al.  Grey clustering analysis for incipient fault diagnosis in oil-immersed transformers , 2009, Expert Syst. Appl..

[12]  Michel Duval,et al.  A review of faults detectable by gas-in-oil analysis in transformers , 2002 .

[13]  Jian Li,et al.  A hybrid algorithm based on s transform and affinity propagation clustering for separation of two simultaneously artificial partial discharge sources , 2015, IEEE Transactions on Dielectrics and Electrical Insulation.

[14]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[15]  Tao Yu,et al.  Dissolved Gas Analysis Principle-Based Intelligent Approaches to Fault Diagnosis and Decision Making for Large Oil-Immersed Power Transformers: A Survey , 2018 .

[16]  Ruijin Liao,et al.  Study on Quantitative Correlations between the Ageing Condition of Transformer Cellulose Insulation and the Large Time Constant Obtained from the Extended Debye Model , 2017 .

[17]  Vaibhava Goel,et al.  Annealed dropout training of deep networks , 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

[18]  Gerasimos Rigatos,et al.  Power transformers’ condition monitoring using neural modeling and the local statistical approach to fault diagnosis , 2016 .

[19]  Chengxiong Mao,et al.  Analysis and Simulation of Fault Characteristics of Power Switch Failures in Distribution Electronic Power Transformers , 2013 .

[20]  D. Linhjell,et al.  Dielectric response of mineral oil impregnated cellulose and the impact of aging , 2007, IEEE Transactions on Dielectrics and Electrical Insulation.

[21]  V. Miranda,et al.  Diagnosing Faults in Power Transformers With Autoassociative Neural Networks and Mean Shift , 2012, IEEE Transactions on Power Delivery.

[22]  Ruijin Liao,et al.  Grey Relational Analysis for Insulation Condition Assessment of Power Transformers Based Upon Conventional Dielectric Response Measurement , 2017 .

[23]  Michel Duval,et al.  Interpretation of gas-in-oil analysis using new IEC publication 60599 and IEC TC 10 databases , 2001 .

[24]  Sherif S. M. Ghoneim,et al.  Intelligent prediction of transformer faults and severities based on dissolved gas analysis integrated with thermodynamics theory , 2018 .

[25]  Junhui Zhao,et al.  Dissolved Gases Forecasting Based on Wavelet Least Squares Support Vector Regression and Imperialist Competition Algorithm for Assessing Incipient Faults of Transformer Polymer Insulation , 2019, Polymers.

[26]  Jawad Faiz,et al.  Dissolved gas analysis evaluation in electric power transformers using conventional methods a review , 2017, IEEE Transactions on Dielectrics and Electrical Insulation.

[27]  Laurent Lamarre,et al.  The duval pentagon-a new complementary tool for the interpretation of dissolved gas analysis in transformers , 2014, IEEE Electrical Insulation Magazine.

[28]  Hanbo Zheng,et al.  An anomaly identification model for wind turbine state parameters , 2018, Journal of Cleaner Production.

[29]  Mohammadreza Yazdchi,et al.  A Novel AE Based Algorithm for PD Localization in Power Transformers , 2013 .

[30]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[31]  Soon-Ryul Nam,et al.  An Accurate CT Saturation Classification Using a Deep Learning Approach Based on Unsupervised Feature Extraction and Supervised Fine-Tuning Strategy , 2017 .

[32]  Dianhui Wang,et al.  Global Convergence of Online BP Training With Dynamic Learning Rate , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[33]  Nagy I. Elkalashy,et al.  Integrated ANN-based proactive fault diagnostic scheme for power transformers using dissolved gas analysis , 2016, IEEE Transactions on Dielectrics and Electrical Insulation.

[34]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[35]  Linong Wang,et al.  Improved Fuzzy C-Means Clustering for Transformer Fault Diagnosis Using Dissolved Gas Analysis Data , 2018 .

[36]  Cheng Haozhong,et al.  Fault diagnosis of power transformer based on multi-layer SVM classifier , 2005 .

[37]  R. Rogers.  IEEE and IEC Codes to Interpret Incipient Faults in Transformers, Using Gas in Oil Analysis , 1978, IEEE Transactions on Electrical Insulation.

[38]  Abdolrahman Peimankar,et al.  Evolutionary multi-objective fault diagnosis of power transformers , 2017, Swarm Evol. Comput..

[39]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[40]  Tapan Kumar Saha,et al.  Smart Transformer for Smart Grid—Intelligent Framework and Techniques for Power Transformer Asset Management , 2015, IEEE Transactions on Smart Grid.

[41]  Angel Javier Quispe Carita,et al.  Bayesian Networks applied to Failure Diagnosis in Power Transformer , 2013, IEEE Latin America Transactions.

[42]  A. P. S. Braga,et al.  Application of an artificial neural network in the use of physicochemical properties as a low cost proxy of power transformers DGA data , 2012, IEEE Transactions on Dielectrics and Electrical Insulation.

[43]  Chia-Yu Lin,et al.  Hybrid Real-Time Matrix Factorization for Implicit Feedback Recommendation Systems , 2018, IEEE Access.

[44]  Y. Zhang,et al.  Aging condition assessment of transformer oil-immersed cellulosic insulation based upon the average activation energy method , 2019, Cellulose.

[45]  Gehao Sheng,et al.  Dissolved gas analysis of insulating oil for power transformer fault diagnosis with deep belief network , 2017, IEEE Transactions on Dielectrics and Electrical Insulation.

[46]  Shensheng Tang,et al.  Reliability modeling of power transformers with maintenance outage , 2014 .