An Evaluation of Linear Time Frequency Distribution Analysis for VSI Switch Faults Identification

Abstract

This paper present an evaluation of linear time frequency distribution analysis for voltage source inverter system (VSI). Power electronic now are highly demand in industrial such as manufacturing, industrial process and semiconductor because of the reliability and sustainability. However, the phenomenon that happened in switch fault has become a critical issue in the development of advanced. This causes problems that occur study on fault switch at voltage source inverter (VSI) must be identified more closely so that problems like this can be prevented. The TFD which is STFT and S-transform method are analyzed the switch fault of VSI. To identify the VSI switches fault, the parameter of fault signal such as instantaneous of average current, RMS current, RMS fundamental current, total waveform distortion, total harmonic distortion and total non-harmonic distortion can be estimated from TFD. The analysis information are useful especially for industrial application in the process for identify the switch fault detection. Then the accuracy of both method, which mean STFT and S-transform are identified by the lowest value of mean absolute percentage error (MAPE). In addition, the S-transform gives a better accuracy compare with STFT and it can be implement for fault detection system.

An accurate pattern classification for empty fruit bunch based on the age profile of oil palm tree using neural network

“…Since it is suitable to deal with a complex parameters where the operation can be implemented in supervised technique or unsupervised. By using the supervised technique, this method can reduce the number of misclassified since the variables will be reclustered according to class specification [22][23][24]. Figure 4 shows the network architecture for LVQ.…”

“…In the algorithms setting, training is set to random weight/bias rule and performance is set to mean squared error (mse) [22]. The number of iterations is set to 1000 [21,23,25]. The code used for the neural network for this project is shown in (1).…”

An improved smooth-windowed Wigner-Ville distribution analysis for voltage variation signal

“…Its main disadvantage is the compromise between frequency and time resolution [20,21]. The bilinear TFD displays a better distribution compare to linear TFD as it offers a high resolution in both frequency and time domains [22,23]. However, the existence of cross-terms make this technique difficult to interpret the true signal characteristics.…”

Fault Detection & Classification in UPFC Integrated Transmission Line Using DWT

“…One of the approach in the field of protection is Kalman filtering discussed in [10], the problem in this is the requirement of a number of dissimilar filters. Another promising hybrid approach of machine intelligence and support vector machine (SVM) also discussed in [12] for fault identification and classification, but it is more prone to noise and interferences. In addition to this it provides result with higher inaccuracy when signal-to-noise ratio is considered for 30 db [11].…”

“…In addition to this it provides result with higher inaccuracy when signal-to-noise ratio is considered for 30 db [11]. Fault identification using linear time-frequency distribution for VSI switch is discussed in [12], however it fails to explain fault detection time of different fault considered and its relay response time. In detection and classification of faults in matrix converter [13] also explains open circuit and short circuit fault of switching component but unable to detect and classify shunt fault occurred in transmission line propoerly.…”