Transformer Fault Diagnosis Based on BP‐Adaboost and PNN Series Connection

Chun, Youngsub; Li, Meixuan; Liu, Wei

doi:10.1155/2019/1019845

Cited by 26 publications

(12 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As one of the main pillars of the current economy, electric energy is gradually accelerating the pace of its intelligent construction, and the scale is also expanding. The oil-immersed transformer, as the key hub of a power system, undertakes the task of power transmission and transformation of the whole power grid, and its operation condition will directly affect the safety of the power network and users [1][2][3][4]. However, insulation faults like partial discharge and partial overheating inevitably exist during oil-immersed transformer long running process [5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

The Adsorption of H2 and C2H2 on Ge-Doped and Cr-Doped Graphene Structures: A DFT Study

Liao

Peng

et al. 2021

Nanomaterials

View full text Add to dashboard Cite

In order to find an excellent sensing material for dissolved gases in transformer oil, the adsorption structures of intrinsic graphene (IG), Ge-doped graphene (GeG), and Cr-doped graphene (CrG) to H2 and C2H2 gas molecules were built. It was found that the doping site right above C atom (T) was the most stable structure by studying three potential doping positions of the Ge and Cr atom on the graphene surface. Then, the structural parameters, density of states, and difference state density of these adsorption systems were calculated and analyzed based on the density functional calculations. The results show that the adsorption properties of GeG and CrG systems for H2 and C2H2 are obviously better than the IG system. Furthermore, by comparing the two doping systems, CrG system exhibits more outstanding adsorption performances to H2 and C2H2, especially for C2H2 gas. Finally, the highest adsorption energy (−1.436 eV) and the shortest adsorption distance (1.981 Å) indicate that Cr-doped graphene is promising in the field of C2H2 gas-sensing detection.

show abstract

Section: Introductionmentioning

confidence: 99%

The Adsorption of H2 and C2H2 on Ge-Doped and Cr-Doped Graphene Structures: A DFT Study

Liao

Peng

et al. 2021

Nanomaterials

View full text Add to dashboard Cite

show abstract

“…Even if the DT is prepruned, it will often overfit. The Bayesian network needs a large number of sample data 13 . When the SVM processes large data, it occupies a large amount of memory and the operation time is slow.…”

Section: Introductionmentioning

confidence: 99%

An early warning model for customer churn prediction in telecommunication sector based on improved bat algorithm to optimize ELM

Chun

Liu

et al. 2021

Int J Intell Syst

Self Cite

View full text Add to dashboard Cite

The competition in the telecommunications industry is mainly reflected in the competition for the number of key customers. Therefore, how to effectively prevent the loss of large customers is a problem that many telecommunications companies are very concerned about. This paper establishes a customer churn prediction model based on the improved bat algorithm (IBA) optimized extreme learning machine (ELM), with the purpose of discovering potential churn customers in time and taking measures to retain them in advance. This paper uses the IBA to optimize the initial random weights of the ELM, so as to improve the prediction accuracy of the ELM. To overcome the shortcomings of the bat algorithm (BA) that the convergence speed is too slow in the early stage and difficult to converge in the later stage, this paper introduces the inertia weight into the speed update formula. To improve the population diversity and local search ability of the BA, this paper adds a chaotic local search method to balance the global search ability of the BA in the early stage. To control the search range of the BAs in the later stage, the lane flight formula is introduced into the position update formula to speed up the convergence speed of the algorithm. Then according to the result of function optimization, it can be seen that IBA has a significant improvement in convergence speed and accuracy. Finally, IBA was used to optimize ELM, and a customer churn prediction model was established. The empirical results show that the predictive model proposed in this paper can effectively identify lost customers and lay a foundation for improving the competitiveness of the telecommunications industry in the future.

show abstract

“…With the rise of machine learning, machine learningrelated algorithms have been applied to transformer fault diagnosis. In the early stage, neural networks [18][19][20], support vector machines (SVMs) [14,21,22], and other algorithms [23][24][25] have improved the accuracy of transformer fault diagnosis. Jia et al [19] proposed a wavelet neural network diagnosis model based on the improved artificial fish-swarm algorithm, and gas content is used as the input of the diagnosis model.…”

Section: Introductionmentioning

confidence: 99%

Transformer Fault Identification with an IF-1DCNN Based on Informative Integration of Heterogeneous Sources

Wang

2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Only using single feature information as input feature cannot fully reflect the transformer fault classification and improve the accuracy of transformer fault diagnosis. To address the above problem, the convolution neural networks’ model is applied for transformer fault assessment designed to implement an end-to-end “different space feature extraction + transformer state diagnosis classification” to enable information from possibly heterogeneous sources to be integrated. This method integrates various feature information of the power transformer operation state to form the isomeric feature, and the model can be used to automatically extract different feature spaces’ information from isomeric feature quantity using its unique one-dimensional convolution and pooling operations. The performance of the proposed approach is compared with that of other models, such as a support vector machine (SVM), backpropagation neural network (BPNN), deep belief network (DBNs), and others. The experimental results show that the proposed one-dimensional convolution neural networks based on an isomeric feature (IF-1DCNN) can accurately classify the fault state of transformer and reduce the adverse interaction between different feature space information in the mixed feature, which has a good engineering application prospect.

show abstract

Transformer Fault Diagnosis Based on BP‐Adaboost and PNN Series Connection

Cited by 26 publications

References 15 publications

The Adsorption of H2 and C2H2 on Ge-Doped and Cr-Doped Graphene Structures: A DFT Study

The Adsorption of H2 and C2H2 on Ge-Doped and Cr-Doped Graphene Structures: A DFT Study

An early warning model for customer churn prediction in telecommunication sector based on improved bat algorithm to optimize ELM

Transformer Fault Identification with an IF-1DCNN Based on Informative Integration of Heterogeneous Sources

Contact Info

Product

Resources

About