Improvement of Chromatographic Peaks Qualitative Analysis for Power Transformer Base on Decision Tree

2020 ◽  
pp. 429-436
Author(s):  
Jie Shan ◽  
Cheng-Kuo Chang ◽  
Hao-Min Chen ◽  
Jeng-Shyang Pan
Keyword(s):  
Decision Tree ◽  
Qualitative Analysis ◽  
Power Transformer ◽  
Chromatographic Peaks

On multivariate method of qualitative analysis of Hodgkin-Huxley model with decision tree induction

2016 ◽  
Author(s):  
Vasyl Martsenyuk ◽  
Kornel Warwas ◽  
Krzysztof Augustynek ◽  
Aleksandra Klos-Witkowska ◽  
Volodymyr Karpinskyi ◽  
...  
Keyword(s):  
Decision Tree ◽  
Qualitative Analysis ◽  
Multivariate Method ◽  
Decision Tree Induction

scholarly journals Decision Tree Based UV/VIS Response To Access the age of Transformer Oil

2011 ◽  
pp. 113-118
Author(s):  
U. Mohan Rao ◽  
A. Pramoda ◽  
D.Vijay Kumar
Keyword(s):  
Decision Tree ◽  
Power Transformer ◽  
Transformer Oil ◽  
Insulation System ◽  
Vis Spectroscopy ◽  
System Information ◽  
Decision Tree Method ◽  
Operational Criteria ◽  
Dielectric Insulation ◽  
Tree Method

Diagnostics and proper monitoring of power transformer plays a key role in the life expectancy of proper transformer. Mineral oil in transformer is the inseparable component of the dielectric insulation system. Information about the health of the power transformer that can be use to plan cost, maintenance, renovation and operational criteria can be accurately interpreted using UVSpectrophotometer. As UV scan can only show the pictorial information of the age of the oil hence it is not advantageous in all aspects. In the present paper a decision tree method to determine the age of the transformer oil is introduced. The decision tree uses the UV/VIS spectroscopy absorbance values of the transformer oil which are in service at several locations. The decision tree method is designed so that the results of transformer oil can be examined quickly and automatically. The results obtained are compared with the UV/VIS spectroscopy for testing the accuracy of the decision tree and found that it is 100% accurate.

Study on Housing Performance Evaluation Model Based on Hierarchical Potential Support Vector Machine

2011 ◽  
Vol 90-93 ◽  
pp. 894-898
Author(s):  
Bo Jing Tian
Keyword(s):  
Support Vector Machine ◽  
Feature Selection ◽  
Performance Evaluation ◽  
Decision Tree ◽  
Qualitative Analysis ◽  
Supplier Selection ◽  
Evaluation Model ◽  
Support Vector ◽  
Performance Evaluation Model ◽  
Multi Class Classification

Housing performance is an important and widely studied topic since it has significant impact on architecture design and programming. In terms of problems existing in the field, a new support vector machine technology, potential support vector machine, is introduced and then combined with decision tree to address issues on supplier selection including feature selection, multi-class classification and so on. And the methodology proposed in the paper, which is proved to the strengthens of integrating knowledge and experiences from experts in the paper, can be applied in housing performance evaluation which is one of complex issues combined with processes including not only quantitative, but also qualitative analysis.

A Qualitative Analysis and Statistics of Educational Evaluation Results Based on Decision Tree Algorithm

2012 ◽  
Vol 433-440 ◽  
pp. 319-323 ◽  
Author(s):  
Yang Liu ◽  
Jun Le Yu
Keyword(s):  
Decision Tree ◽  
Qualitative Analysis ◽  
Evaluation Method ◽  
Educational Evaluation ◽  
Evaluation Index System ◽  
Education Evaluation ◽  
Decision Tree Algorithm ◽  
Tree Algorithm ◽  
Internal Education ◽  
Development Prospects

This paper has surveyed on education evaluation method and technology at home and abroad, and also researched on the statistics and analysis of internal education evaluation information processing technology. In view of the evaluation index system of secondary vocational education, it has established educational evaluation and analysis of statistical models based on decision tree algorithm, and also made a qualitative analysis and statistics of educational evaluation results, thereby providing the basis so as to obtain a qualitative analysis of educational evaluation in school, meanwhile, it provides a broad development prospects for the qualitative analysis quantitative analysis of educational evaluation results.

Power Transformer Fault Diagnosis using DGA and Artificial Intelligence

2020 ◽  
Vol 13 (4) ◽  
pp. 579-587
Author(s):  
Seyed Javad Tabatabaei Shahrabad ◽  
Vahid Ghods ◽  
Mohammad Tolou Askari
Keyword(s):  
Artificial Intelligence ◽  
Decision Tree ◽  
Power Transformer ◽  
Gas Analysis ◽  
Power Transformers ◽  
Detection Methods ◽  
Support Vector ◽  
Dissolved Gas ◽  
Dissolved Gas Analysis ◽  
Internal Faults

Background: Power transformers are one of the most applicable electricity network devices which transmit output power of the generator to the network through increasing voltage and decreasing current. Due to high cost of such devices and cost of disconnecting device upon failure, disconnection and failure of the transformer should be avoided as much as possible. Objective: In addition, in order to increase reliability and reduce maintenance costs, such devices should be monitored constantly. Internal faults ionize and warm up oil and as a result, gases like carbon dioxide, methane, ethane, ethylene and acetylene are produced. Various methods have been proposed for diagnosing fault in power transformers where one of the most well-known methods is dissolved gas analysis (DGA). DGA in oil is one of the effective tools for diagnosing initial faults in transformers. Methods: Common fault detection methods using oil-dissolved gas analysis include Dornemburge, Duval’s triangle, IEC/IEEE standard, key gases and Rogers. In recent years, artificial intelligence like genetic algorithm, fuzzy logic and neural networks have been used to detect faults using DGA. In this paper, support vector machine (SVM) and decision tree are used to detect internal faults in power transformers. Results: By evaluation of the proposed methods, total accuracies of classifiers using SVM and decision tree were 90% and 97.5%, respectively. Conclusion: Decision tree shows better performance and it is suggested as a proper method for obtaining promising results.

Sign in / Sign up

Export Citation Format

Share Document