On-line diagnosis of incipient faults and cellulose degradation based on artificial intelligence methods

Izzularab, Mohamed A.; Aly, G. E. M.; Mansour, Diaa‐Eldin A.

doi:10.1109/icsd.2004.1350545

Cited by 21 publications

(10 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In one-component detection, palladium grid FET and catalytic oxidation inductor as well as electrochemistry H 2 inductor are mostly used [10] , while the main product is made by Canadian SYPROTEC company, HYDRAN; in multi-component detection, the mainly useful means are thermal conductance sensor, hydrogen flame ionization sensor and semiconductor sensor, etc. [11] . The TRUE Gas on-line monitoring device made by American company AVO can detect gases as many as 8, and it is the most effective instrument so far.…”

Section: The Technique Of Oil Dissolved Gas Analysismentioning

confidence: 99%

Review of Comprehensive Assessment of Power Transformer

Zhang¹,

Ning²,

Ya-he³

2018

Proceedings of the 2018 International Conference on Mathematics, Modelling, Simulation and Algorithms (MMSA 2018)

View full text Add to dashboard Cite

Since the power transformer is an important kind of electric power equipment in power system, in this paper, comprehensive evaluation of power transformer are divided into three parts: power transformer operation status, fault diagnosis and repair strategies. Furthermore, the evaluation methods of comprehensive evaluation analysis are proposed, which means, on-line monitoring, the method of fault diagnosis and condition-based maintenance strategy decision-making method. Summarizing the research thought, the application conditions and the research progress of these methods. Finally, some open problems for comprehensive evaluation of power transformer in this area are introduced.

show abstract

Section: The Technique Of Oil Dissolved Gas Analysismentioning

confidence: 99%

Review of Comprehensive Assessment of Power Transformer

Zhang¹,

Ning²,

Ya-he³

2018

Proceedings of the 2018 International Conference on Mathematics, Modelling, Simulation and Algorithms (MMSA 2018)

View full text Add to dashboard Cite

show abstract

“…Artificial intelligent methods were widely used to develop DGA based diagnosis with high accuracy. The first example of these methods is an artificial neural network (ANN), in which much training data were used to adapt the network for DGA diagnosis [13]- [16]. The input for ANN can be fuzzified gas concentrations [13], certain gas ratios [14]- [16], or others [16], [17].…”

Section: Introductionmentioning

confidence: 99%

“…The first example of these methods is an artificial neural network (ANN), in which much training data were used to adapt the network for DGA diagnosis [13]- [16]. The input for ANN can be fuzzified gas concentrations [13], certain gas ratios [14]- [16], or others [16], [17]. The second example of artificial intelligent and methods is a fuzzy logic system, in which several If-Then rules were implemented to correlate DGA with the proper diagnosis [18]- [20].…”

Section: Introductionmentioning

confidence: 99%

Hybrid Grey Wolf Optimizer for Transformer Fault Diagnosis Using Dissolved Gases Considering Uncertainty in Measurements

2020

View full text Add to dashboard Cite

The transformer fault diagnosis based on dissolved gas analysis is greatly affected by the uncertainties existing in measured data during oil sampling, handling and storage. This work aims to develop an efficient code matrix based on dissolved gas percentages for accurate fault diagnosis considering measurement uncertainties. Fuzzy system is utilized to produce the rules that map the limits of gas ratios for different fault types. Each gas percentage range is divided into three regions represented by three fuzzy memberships. The fuzzy system is then developed to relate the gas percentages to the fault type. The membership limits are then optimized by using heuristic algorithms in order to maximize the accuracy. Hybrid Grey Wolf Optimization (HGWO) algorithm is utilized to produce the diagnostic code matrix. The proposed code limits the impact of measurement uncertainties on the output fault diagnosis. Different levels of measurement uncertainties up to 20% are considered to validate the effectiveness of the new code in improving the diagnostic accuracy. The accuracies during the training and testing processes attained 97.45% and 95.45%, respectively, with the maximum uncertainty level of 20%. Moreover, randomly selected case studies representing various fault types are investigated using the proposed method. For each case study, various levels of uncertainties are imposed on the original data. The proposed method proved its easiness towards diagnosing transformer faults and robustness against measurement uncertainties.

show abstract

“…Toward improving the diagnostic accuracy of DGA interpretation, several methods have been proposed based on an artificial intelligence (AI) and computational techniques. Examples of these techniques are artificial neural network (ANN) [6–9], fuzzy logic and expert system [10–13], support vector machine (SVM) [14, 15], and hybrid methods [16–21].…”

Section: Introductionmentioning

confidence: 99%

“…Hybrid methods were proposed to enhance the diagnosis accuracy, such as neural network or SVM with fuzzy input layer [16, 19], SVM with Bayesian classifier [18], neuro fuzzy inference system [21], and so on. However, with using such methods, the complication of the system increases.…”

Section: Introductionmentioning

confidence: 99%