Identification of internal fault against external abnormalities in power transformer using hierarchical ensemble extreme learning machine technique

Raichura, Maulik; Chothani, Nilesh; Patel, Dharmesh

doi:10.1049/iet-smt.2019.0102

Cited by 32 publications

(12 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Adaptive approach with ANN and PSO-based techniques are elaborated in [36] in a good manner, yet, an operational period of the suggested configuration is not calculated. Recently, RVM (relevance vector machine) [37] and HE-ELM (hierarchical ensemble extreme learning machine) [38] grounded algorithms are elaborated by considering all the system and fault parameters for improving transformer fault classification accuracy. However, the achieved classification accuracy is high, but a collection of real-time training data from the field is a major problem.…”

Section: Classifier and Decomposing Techniquesmentioning

confidence: 99%

“…(1) Simply reveal extreme details and hence rises convolution (2) No guarantee concerning the extracted details and relation with each essential section (3) Simply cause involvement with efficient movement. (4) efficient decomposition is producing disparagement on the procedure (5) cause problem in the gathering of definite training data in the actual field (6) trained staff required [31][32][33][34][35][36][37][38][39][40][41] 4…”

Section: External Fault Conditionsmentioning

confidence: 99%

See 1 more Smart Citation

Review of methodologies used for detection of magnetising inrush and fault conditions in power transformer

Raichura

Chothani

Patel³

2021

IET Energy Syst Integration

View full text Add to dashboard Cite

Reliable and dedicated protection of the transformer is the main requirement in the power system due to the supervision of a highly expensive equipment transformer. Nonlinear characteristics of the transformer give mysterious behaviour for the period of inrush and Current transformer saturation conditions. As a stagnant and electro-magnetic device, a transformer is mainly affected by self-inrush. The saturation of the core itself is a very critical situation that becomes a hindrance for fault discrimination. This article involves the elaboration of the effect of inrush on transformer operation, past research practices for the discrimination of inrush with the faulty condition, and a definite method to recognise inrush and fault condition of the transformer. More than 50 reputed journal articles, various book chapters, and books with research thesis thoroughly studied to review the inrush and fault discrimination conditions. A comparative analysis is prepared to suggest the identification of transformer abnormalities. Moreover, a total harmonics distortion (THD)-based solution proposed for discrimination of the inrush condition from fault and other abnormal conditions using the short time Fourier transform technique. Hardware setup for 2 kVA transformer developed in the laboratory to study different inrush phenomena and altered fault conditions. Simulation and hardware results show various effects of inrush and fault with individual harmonic and THD-based analysis. The collection of real-time data is further used based on laboratory hardware setup to enhance real-time protection schemes for power transformers.This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

show abstract

Section: Classifier and Decomposing Techniquesmentioning

confidence: 99%

Section: External Fault Conditionsmentioning

confidence: 99%

Review of methodologies used for detection of magnetising inrush and fault conditions in power transformer

Raichura

Chothani

Patel³

2021

IET Energy Syst Integration

View full text Add to dashboard Cite

show abstract

“…The support vector machines (SVM) algorithm combined with the wavelet analysis technique was used to discriminate PD [ 18 ]. Based on dissolved gas analysis (DGA), more scholars adopted the artificial neural network (ANN), the polynomial neural network (PNN), etc., [ 19 , 20 , 21 ]. Moreover, some studies have optimized the algorithms to achieve better results [ 22 , 23 , 24 ].…”

Section: Introductionmentioning

confidence: 99%

Diagnosis of Partial Discharge Based on the Air Components for the 10 kV Air-Insulated Switchgear

Tan

Zhang

et al. 2022

Sensors

View full text Add to dashboard Cite

Partial discharge (PD) is a common phenomenon of insulation aging in air-insulated switchgear and will change the gas composition in the equipment. However, it is still a challenge to diagnose and identify the defect types of PD. This paper conducts enclosed experiments based on gas sensors to obtain the concentration data of the characteristic gases CO, NO2, and O3 under four typical defects. The random forest algorithm with grid search optimization is used for fault identification to explore a method of identifying defect types through gas concentration. The results show that the gases concentration variations do have statistical characteristics, and the RF algorithm can achieve high accuracy in prediction. The combination of a sensor and a machine learning algorithm provides the gas component analysis method a way to diagnose PD in an air-insulated switchgear.

show abstract

“…However, during higher training/testing data size, RVM-based method takes a longer computational time than usual. Another protective technique, hierarchical ensemble of extreme learning machine (HE-ELM) has been presented in [4]. Wang et al [5] and Dogaru et al [6] compared the ELM with SVM (i.e.…”

Section: Introductionmentioning

confidence: 99%

Efficient CNN‐XGBoost technique for classification of power transformer internal faults against various abnormal conditions

Raichura

Chothani

Patel³

2021

IET Generation Trans & Dist

Self Cite

View full text Add to dashboard Cite

To increase the classification accuracy of a protection scheme for power transformer, an effective convolution neural network (CNN) extreme gradient boosting (XGBoost) combination is proposed in this work. Data generated from various test cases are fed to one‐dimensional CNN for high‐level feature extraction. After that, an efficient classifier tool XGBoost is used to properly discriminate different transformer internal faults against outside abnormalities. A portion of an Indian power system is considered and simulated in PSCAD software using the multi‐run feature to collect a large number of data for various fault/abnormal situations. The generated data are used in MATLAB software where the proposed algorithm is programmed. A high‐performance CPU is used for training and testing purpose of the projected artificial intelligent technique. The obtained results for classification accuracy as well as discrimination time shows that the proposed scheme is competent enough to properly discriminate transformer operational conditions. Further, the combined CNN‐XGBoost technique is compared with existing relevance vector machine and hierarchical ensemble of extreme learning machine classifier techniques. Moreover, a hardware experiment is performed in a laboratory prototype of 50 kVA, 440/220 V transformer to verify the authenticity of the developed protective scheme. After analyzing a variety of experiments, the authors note that the presented method provides promising classification accuracy within a short time period.

show abstract

Identification of internal fault against external abnormalities in power transformer using hierarchical ensemble extreme learning machine technique

Cited by 32 publications

References 24 publications

Review of methodologies used for detection of magnetising inrush and fault conditions in power transformer

Review of methodologies used for detection of magnetising inrush and fault conditions in power transformer

Diagnosis of Partial Discharge Based on the Air Components for the 10 kV Air-Insulated Switchgear

Efficient CNN‐XGBoost technique for classification of power transformer internal faults against various abnormal conditions

Contact Info

Product

Resources

About