Application of an artificial neural network in the use of physicochemical properties as a low cost proxy of power transformers DGA data

Barbosa, Fábio Rocha; Almeida, Otacílio M.; Braga, Arthur P. S.; Amora, Márcio André Baima; Cartaxo, S. J. M.

doi:10.1109/tdei.2012.6148524

Cited by 46 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Step 3: According to (14) and Table III, the diagnosis error ratio e 11 of PD by method z 1 is 0.4063 (26/64), because its number (C ) of misjudgment cases is 26 and the number (T ) of PD samples is 64,as mentioned above. Likewise, the diagnosis error ratio e 21 of PD by method z 2 is 0.3281 (21/64), because its number (C ) of misjudgment cases is 21 and the number (T ) of PD samples is 64.…”

Section: Diagnosis Examples and Analysismentioning

confidence: 99%

“…CDMOW is constructed according to the following steps. First, the diagnosis error ratio e ik is calculated according to (14) after the historical data samples stored in a database are diagnosed by m single diagnosis methods. The diagnosis error information matrix E can be also gained according to (15).…”

Section: Construction Process Of Cdmowmentioning

confidence: 99%

“…The diagnostic results are shown in Table III. In Table III, the diagnosis error ratio 0.4063 (26/64) is the result of dividing the misjudgment cases (26) by the number of PD cases (64) according to (14), where the number T of PD samples is 64 and the number C of misjudgment cases is 26. Likewise, 0.35 (42/120) is the result of dividing the misjudgment cases (42) by the number of D1 cases (120).…”

Section: Diagnosis Examples and Analysismentioning

confidence: 99%

“…Recently, at home and abroad, the primary method of transformer fault diagnosis is based on dissolved gas analysis (DGA) [9][10][11][12]. In addition, the use of backpropagation (BP) neural network, expert system diagnosis, fuzzy theory, grey system theory (GS) algorithm, Dempster-Shafer evidence (DS) theory, and genetic algorithms for transformer fault diagnosis has also achieved good results [13,14]. However, none of these methods has good application potential especially in diagnostic stability and accuracy in practice.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Application of a combined decision model based on optimal weights in incipient faults diagnosis for power transformer

Tingfang

Zhang

et al. 2016

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

A new method for the diagnosis of incipient transformer faults based on a combined decision model using IEC 60599 three-ratio method, grey system theory (GS) algorithm, Dempster-Shafer evidence (DS) theory, and backpropagation (BP) neural network diagnosis method is proposed in this paper. The new method will eliminate the influence of any one individual diagnosis method due to insufficient information or diagnostic prejudices. In order to minimize the sum-of-squared errors of the proposed method, the optimal weights of every individual method which comprises the combined decision model are calculated based on their own diagnosis error ratios. Thus a combined decision model based on optimal weights (CDMOW) is formed. Then the optimal diagnosis result is obtained based on CDMOW. Results of diagnosis instances show that the use of CDMOW not only gives a much higher diagnostic accuracy rate but also more stability in fault diagnosis than any single method composing it.

show abstract

Section: Diagnosis Examples and Analysismentioning

confidence: 99%

Section: Construction Process Of Cdmowmentioning

confidence: 99%

Section: Diagnosis Examples and Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Application of a combined decision model based on optimal weights in incipient faults diagnosis for power transformer

Tingfang

Zhang

et al. 2016

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

show abstract

“…It is essential to explore the principles, methods and means from various disciplines that are helpful in the fault diagnosis of transformers. With the rapid development of computer science and the rise of machine learning, multiple intelligent approaches such as artificial neural network [17][18][19], support vector machine (SVM) [20][21][22], fuzzy theory [23][24][25], extreme learning machine [26], and Bayesian network [27] have been applied in practice. A smart fault diagnostic approach based on integrating five interpretation methods using neural networks is proposed in [28].…”

mentioning

confidence: 99%

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

Wang

Zhang

et al. 2019

Energies

View full text Add to dashboard Cite

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.Energies 2019, 12, 995 2 of 16 commonly used fault diagnosis methods. However, these traditional methods have limitations. They may not be able to provide an interpretation to every possible combination of various ratios and may have excessively absolute coding boundary. Due to the objective uncertainty of transformer fault itself and the boundaries of the subjective judgment, it is difficult to meet the requirements of engineering application with the above ratio methods.Since the transformer faults are complex and concealed, simple and crude methods have difficulty performing effective diagnosis. It is essential to explore the principles, methods and means from various disciplines that are helpful in the fault diagnosis of transformers. With the rapid development of computer science and the rise of machine learning, multiple intelligent approaches such as artificial neural network [17][18][19], support vector machine (SVM) [20][21][22], fuzzy theory [23][24][25], extreme learning machine [26], and Bayesian network [27] have been applied in practice. A smart fault diagnostic approach based on integrating five interpretation methods using neural networks is proposed in [28]. Ma et al. [29] presented an intelligent framework for transformer condition monitoring and assessment. Within their framework, different intelligent algorithms can be effectively deployed. Peimankar et al. [30] first used multi-objective particle swarm optimization (PSO) algorithm to select the best subset of features corresponding to each fault class of power transformers. Then, they used ensemble learning systems to classify actual faults of transformers. Sherif et al. [31] utilized the thermodynamic theory to evaluate the severity based on the energy associated with each transformer fault type. These intelligent methods remedy the disadvantages of t...

show abstract

Reliability‐based fault analysis models with industrial applications: A systematic literature review

Ahmed

Raza

Al-Anazi

2020

Quality & Reliability Eng

View full text Add to dashboard Cite

Effective and early fault detection and diagnosis techniques have tremendously enhanced over the years to ensure continuous operations of contemporary complex systems, control cost, and enhance safety in assets‐intensive industries, including oil and gas, process, and power generation. The objective of this work is to understand the development of different fault detection and diagnosis methods, their applications, and benefits to the industry. This paper presents a contemporary state‐of‐the‐art systematic literature survey focusing on a comprehensive review of the models for fault detection and their industrial applications. This study uses advanced tools from bibliometric analysis to systematically analyze over 500 peer‐reviewed articles on focus areas published since 2010. We first present an exploratory analysis and identify the influential contributions to the field, authors, and countries, among other key indicators. A network analysis is presented to unveil and visualize the clusters of the distinguishable areas using a co‐citation network analysis. Later, a detailed content analysis of the top‐100 most‐cited papers is carried out to understand the progression of fault detection and artificial intelligence–based algorithms in different industrial applications. The findings of this paper allow us to comprehend the development of reliability‐based fault analysis techniques over time, and the use of smart algorithms and their success. This work helps to make a unique contribution toward revealing the future avenues and setting up a prospective research road map for asset‐intensive industry, researchers, and policymakers.

show abstract

Application of an artificial neural network in the use of physicochemical properties as a low cost proxy of power transformers DGA data

Cited by 46 publications

References 26 publications

Application of a combined decision model based on optimal weights in incipient faults diagnosis for power transformer

Application of a combined decision model based on optimal weights in incipient faults diagnosis for power transformer

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

Reliability‐based fault analysis models with industrial applications: A systematic literature review

Contact Info

Product

Resources

About