An intelligent approach using SVM to enhance turn-to-turn fault detection in power transformers

2012 ◽  
Author(s):  
M. Elsamahy ◽  
M. Babiy
Keyword(s):  
Fault Detection ◽  
Power Transformers ◽  
Intelligent Approach

Support vector machine and K-nearest neighbour for unbalanced fault detection

2014 ◽  
Vol 20 (1) ◽  
pp. 65-75 ◽  
Author(s):  
Ashkan Moosavian ◽  
Hojat Ahmadi ◽  
Babak Sakhaei ◽  
Reza Labbafi
Keyword(s):  
Fault Diagnosis ◽  
Fault Detection ◽  
Experimental System ◽  
Performance Comparison ◽  
Fault Classification ◽  
Support Vector ◽  
Rotating Machines ◽  
Vibration Signals ◽  
Content Type ◽  
Intelligent Approach

Purpose – The purpose of this paper is to develop an appropriate approach for detecting unbalanced fault in rotating machines using KNN and SVM classifiers. Design/methodology/approach – To fulfil this goal, a fault diagnosis approach based on signal processing, feature extraction and fault classification, was used. Vibration signals were acquired from a designed experimental system with three conditions, namely, no load, balanced load and unbalanced load. FFT technique was applied to transform the vibration signals from time-domain into frequency-domain. In total, 29 feature parameters were extracted from FFT amplitude of the signals. SVM and KNN were employed to classify the three different conditions. The performances of the two classifiers were obtained under different values of their parameter. Findings – The experimental results show the potential application of SVM for machine fault diagnosis. Practical implications – The results demonstrate that the proposed approach can be used effectively for detecting unbalanced condition in rotating machines. Originality/value – In this paper, an intelligent approach for unbalanced fault detection was proposed based on supervised learning method. Also, a performance comparison was made between KNN and SVM in fault classification. In addition, this approach gave a high level of classification accuracy. The proposed intelligent approach can be used for other mechanical faults.

scholarly journals Effective Automatic Fault Detection in Transmission Lines by Hybrid Model of Authorization and Distance Calculation through Impedance Variation

2021 ◽  
Vol 3 (1) ◽  
pp. 36-48
Author(s):  
Bindhu V ◽  
Ranganathan G
Keyword(s):  
Fault Detection ◽  
Transmission Line ◽  
Transmission Lines ◽  
Power Distribution ◽  
Power Transmission ◽  
Control Unit ◽  
Labor Costs ◽  
Impedance Variation ◽  
Distribution Line ◽  
Intelligent Approach

Fault detection in the transmission is a challenging task when examining the accuracy of the system. This fault can be caused by a man-made force or by using concurrent overvoltage in the power distribution line. This research focuses on two sections to handle the power transmission line problem and can be rectified as previously stated. An intelligent approach is utilized for monitoring and controlling line faults in order to improve the accuracy of the equipment in transmission line fault detection. After several iterations of the procedure, the combination of line and master unit improves the system's accuracy and reliability. The master unit identifies faulty poles in the network based on the variation of current and voltage of each node and calculates the distance between the station and the faulty node to reduce manual effort. In the proposed work, many sensors are used to detect the line fault in a network by placing the appropriate point. The pure information can be transferred to an authorized person or unit after many iterations due to knowledgeable devices. The faulty status of the pole information is displayed in the control unit by a display unit comprised of an alarm unit to alert the corresponding section using ZigBee techniques. The GSM unit provides the faulty status of an authorized person to rectify the problems immediately which further improve the reliability of the system. When compared to existing methods, our hybrid proposed method achieves a higher accuracy of 90%. This method aids to reduce the labor costs gradually to visit all-pole points instead of faulty pole points and thereby increasing the reliability of the electrical consumers.

scholarly journals IOT Based Fault Detection and Protection of Power Transformer in the Smart Grid

2021 ◽  
Vol 12 (1) ◽  
pp. 7
Author(s):  
Muhammad Kashif Sattar ◽  
Muhammad Waseem ◽  
Saqib Fayyaz ◽  
Riffat Kalsoom ◽  
Hafiz Ashiq Hussain ◽  
...  
Keyword(s):  
Fault Detection ◽  
Smart Grid ◽  
Power System ◽  
Power Transformer ◽  
Optimal Operation ◽  
Protection System ◽  
Power Transformers ◽  
Practical Implementation ◽  
Operating Condition ◽  
Current Voltage

This paper presents a novel Arduino-based fault detection and protection system for power transformers. Power transformers are an integral component of the power system infrastructure. Power transformers are present in such a significant number in the power architecture that any alteration in its operation effects the whole power system. The optimal operation of the transformer depends upon its operating condition; for this reason, its monitoring and protection are very important. Currently, power transformers employ differential relays to ensure optimal operation, but differential relays are unable to ascertain conditions such as overloading and intra turn faults. In this paper, Arduino was used to monitor transformer operation instead of differential relays and generate tripping or alert signals based on sensed values. Arduino autonomously sensed the current, voltage, and temperature values of the power transformer round the clock and handled any fault by comparing preset values of these parameters. In addition, the differential relay functionality of fault detection was implemented in the Arduino environment. Whenever a fault occurred, Arduino sent the fault signal to a Wi-Fi module, which was then displayed in the Blynk app. The practical implementation of this proposed system was tested, and its operation was found to be effective in fault detection.

Sign in / Sign up

Export Citation Format

Share Document