scholarly journals A Multinomial DGA Classifier for Incipient Fault Detection in Oil-Impregnated Power Transformers

Algorithms ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 128
Author(s):  
George Odongo ◽  
Richard Musabe ◽  
Damien Hanyurwimfura

This study investigates the use of machine-learning approaches to interpret Dissolved Gas Analysis (DGA) data to find incipient faults early in oil-impregnated transformers. Transformers are critical pieces of equipment in transmitting and distributing electrical energy. The failure of a single unit disturbs a huge number of consumers and suppresses economic activities in the vicinity. Because of this, it is important that power utility companies accord high priority to condition monitoring of critical assets. The analysis of dissolved gases is a technique popularly used for monitoring the condition of transformers dipped in oil. The interpretation of DGA data is however inconclusive as far as the determination of incipient faults is concerned and depends largely on the expertise of technical personnel. To have a coherent, accurate, and clear interpretation of DGA, this study proposes a novel multinomial classification model christened KosaNet that is based on decision trees. Actual DGA data with 2912 entries was used to compute the performance of KosaNet against other algorithms with multiclass classification ability namely the decision tree, k-NN, Random Forest, Naïve Bayes, and Gradient Boost. Investigative results show that KosaNet demonstrated an improved DGA classification ability particularly when classifying multinomial data.

2020 ◽  
Vol 4 (2) ◽  
pp. 329-335
Author(s):  
Rusydi Umar ◽  
Imam Riadi ◽  
Purwono

The failure of most startups in Indonesia is caused by team performance that is not solid and competent. Programmers are an integral profession in a startup team. The development of social media can be used as a strategic tool for recruiting the best programmer candidates in a company. This strategic tool is in the form of an automatic classification system of social media posting from prospective programmers. The classification results are expected to be able to predict the performance patterns of each candidate with a predicate of good or bad performance. The classification method with the best accuracy needs to be chosen in order to get an effective strategic tool so that a comparison of several methods is needed. This study compares classification methods including the Support Vector Machines (SVM) algorithm, Random Forest (RF) and Stochastic Gradient Descent (SGD). The classification results show the percentage of accuracy with k = 10 cross validation for the SVM algorithm reaches 81.3%, RF at 74.4%, and SGD at 80.1% so that the SVM method is chosen as a model of programmer performance classification on social media activities.


2017 ◽  
Vol 31 (2) ◽  
pp. 156-162 ◽  
Author(s):  
O. V. Schneider

The article summarizes the main approaches in the definition of business valuation the economic entity. In the process of business valuation, taking into account the risks of financial and economic activities necessary to obtain information on what stage the owner implements the business will receive income. The most difficult task is the impossibility of accurate prediction in determining the level of income and the determination of a discount rate capitalization of future incomes due to the instability of the economy, both in the country and around the world.


2021 ◽  
Vol 11 (11) ◽  
pp. 4754
Author(s):  
Assia Aboubakar Mahamat ◽  
Moussa Mahamat Boukar ◽  
Nurudeen Mahmud Ibrahim ◽  
Tido Tiwa Stanislas ◽  
Numfor Linda Bih ◽  
...  

Earth-based materials have shown promise in the development of ecofriendly and sustainable construction materials. However, their unconventional usage in the construction field makes the estimation of their properties difficult and inaccurate. Often, the determination of their properties is conducted based on a conventional materials procedure. Hence, there is inaccuracy in understanding the properties of the unconventional materials. To obtain more accurate properties, a support vector machine (SVM), artificial neural network (ANN) and linear regression (LR) were used to predict the compressive strength of the alkali-activated termite soil. In this study, factors such as activator concentration, Si/Al, initial curing temperature, water absorption, weight and curing regime were used as input parameters due to their significant effect in the compressive strength. The experimental results depict that SVM outperforms ANN and LR in terms of R2 score and root mean square error (RMSE).


1980 ◽  
Vol 53 (3) ◽  
pp. 437-511 ◽  
Author(s):  
D. W. Brazier

Abstract An attempt has been made to review the development of thermoanalytical procedures as they have been applied to elastomers and elastomer systems over the past 10 years. For all rubber industry products, temperature and its effects, either alone or in conjunction with the chemical environment, play an important role from the production stage through to the final failure of the product in the field. It is thus not surprising that thermal analysis, in which temperature is the prime variable, has found such diverse applications in elastomer studies. The identification and quantitative analysis of rubber formulations have received most attention. Such formulations produce characteristic “fingerprints” when studied in DTA, DSC, TG, or TMA. In DSC, the determination of the glass transition characteristics, the observation and determination of crystallinity, the detection of cyclization reactions, and the monitoring of thermal and oxidative degradation characteristics can all be observed in a single experiment covering the temperature range from −150 to +600°C. At normal heating rates, e.g., 20°C/min, such information is available in 40 min. TG/DTG analysis can yield the elastomer or elastomers content, oil and plasticizer, carbon black (level and often type), and inorganic ash in less than 60 min. Processing and curing can also be studied. Blend compatibility can be assessed on the basis of both Tg and crystallinity measurements and the data used to determine optimum mixing times. Sulfur vulcanization and peroxide curing of elastomers is readily monitored by DSC and can be used for confirmation analysis of the presence of curatives. Limitations in such analysis exist, but as understanding and ability to interpret cure exotherms increase, valuable information about the mechanism and the nature of the cured network will be obtained. The testing of rubber compounds involves many hours of labor by current procedures. The rapidity of thermal analysis promises to offer some relief. In addition to DSC and TG, TMA, a relatively new technique, offers a rapid approach to low-temperature testing. Dynamic mechanical analysis (DMA) offers a rapid route to determining dynamic properties, but as yet, relatively little has been published on the application of this new technique to elastomers. As environmental concern increases, techniques such as evolved gas analysis (EGA) and combined techniques such as TG/gas chromatography are predicted to play an important role. As for the future, it is readily apparent that the principles of the methods have been established and, in several cases, it now remains to reduce them to a practical level. In some areas, such as vulcanization studies, much remains to be undertaken to improve our interpretive skills. Although there is some indication that certain industries have produced “in-house” standards for the analysis of rubber compounds by DSC and TG/DTG, it will only be when national and international standards organizations study and produce standard procedures, that the techniques will be generally adopted. Maurer's prediction in 1969 of increased applications of DTA and TG in elastomer studies has undoubtedly proved correct, and with the proliferation of reliable commercial instrumentation, significant developments can be anticipated in the next decade.


2013 ◽  
Vol 2013 ◽  
pp. 1-7 ◽  
Author(s):  
Nitin K. Dhote ◽  
Jagdish B. Helonde

Dissolved gas analysis (DGA) of transformer oil has been one of the most reliable techniques to detect the incipient faults. Many conventional DGA methods have been developed to interpret DGA results obtained from gas chromatography. Although these methods are widely used in the world, they sometimes fail to diagnose, especially when DGA results fall outside conventional methods codes or when more than one fault exist in the transformer. To overcome these limitations, the fuzzy inference system (FIS) is proposed. Two hundred different cases are used to test the accuracy of various DGA methods in interpreting the transformer condition.


Sign in / Sign up

Export Citation Format

Share Document