In transmission line when current does not flow from the secondary side of the transformer after flowing from the primary side, due to this overcurrent occurs in the transformer. This fault is known as inrush current in the transformer. Inrush current is the maximum transient current absorbed by an electrical device when first turned on. The electric motor and AC transformer can absorb the inrush current several times. Its normal full load current energizes first for two cycles of the input waveform. Say no to plagiarism. Get a tailor-made essay on "Why Violent Video Games Shouldn't Be Banned"? Get an Original Essay There are several methods to solve this problem. The first method is differential transformation, in this method when the currents of the primary side and secondary side of the transformer are equal. In that case, the relay connected together will detect the fault and trip the circuit. Another method is the Fourier series transform. In this method, when a fault occurs, the transmission line frequency increases from the rated frequency. The disadvantage of this method is that it only detects the fault of the frequency of 50 Hz and a time period of 0-5 seconds, it does not provide the exact time of the fault. To overcome this drawback, the Short Time Fourier Transform (STFT) is introduced. Provides the exact time of the error by dividing the overall time with ?. STFT also has some limitations: once you choose a particular size for the time window, that window is the same for all frequencies. This work can be easily done by Wavelet with higher precision. The wavelet transform is used to detect inrush current conditions. Artificial neural network (ANN) is used to classify inrush current conditions. The simulation process is performed by MATLAB. Jazebi.et.al. [1] proposes an inrush current magnetization approach using Gaussian mixture models (GMM). The simulation is performed by PSCAD/EMTDC software for various faults and switching conditions on a power transformer. 500 MVA, 400/230 kV, three-phase power transformer is used in the simulation system. The mother wave type and decomposition level are used to detect and locate different types of fault transients. The sampling rate and base frequency of the system are 10 KHz and 50 Hz. The window size of the WT is 50 samples per window for the GMM. In the energy system, GMM has proven to be a simple identification criterion, best suited for protection, fast performance and also investment. In [2], the classification of transient phenomena in distribution systems is presented. The scheme based on the wavelet transform algorithm is used to classify many types of transients common in distribution systems. The simulation is performed on ATP-EMTP used for inrush current, load switching, capacitor switching and single-phase-to-earth fault in 20 kV radial distribution primary power supply. ARSedighi and M.R.Haghifam [3] present an efficient method for inrush current detection in distribution transformer based on wavelet transform. Electromagnetic Transient Program (EMTP) is used for simulation of inrush current and other events for feature extraction and discrimination. A 20 kV distribution power supply and 20 kHz sampling rate is used in a single phase towards ground fault and inrush current. Ashrafian.et.al [4] describes the application of protectiondiscrete differential with S transformation of the power transformer. The discrete S transform is used for inrush current and internal fault discrimination. In the simulation power system, a 13.5 MVA, 132/33 kv three-phase transformer is used, which has 980 and 424 turns of the primary and secondary windings. In the model the transmission line is divided into two identical p sections. MATLAB and EMTP programs are used for implementation. In [5], the method involves inrush current discrimination and the internal fault is proposed in the power transformer. The method is based on Empirical Wavelet Transform (EWT) and Support Vector Machine (SVM). Matlab/Simulink is used for simulation. By taking the ratio of second harmonics to the fundamental of the current waveform, he distinguishes both types of current. It consists of two classes of data for validating inrush and internal fault current waveforms. It has two transformers T1 and T2 connected via transmission line.Abnaki.et.al. [6] provides a method to identify the magnetizing inrush current resulting from internal fault in power transformer protection. In this technique, symmetrical components are used. The simulation is done in all cases i.e. normal condition, inrush condition, internal fault condition, external fault condition and over flow condition using PSCAD/EMTDC. The ratings of the simulated power transformer system used are 30 MVA at 33 kV/11 kV speed. With the proposed model, probably in all cases, the simulation result is obtained. Ozgonenel.et.al. [7] introduces a modern approach for the protection of power transformers. The WT is used for the extraction of inrush current and internal faults in the power transformer. In phase-to-ground and phase-to-phase faults, the WT helps to analyze current signals with their discontinuities. Coiflet 6 wavelet functions are used to study the discontinuity of current signals. Regarding fault conditions and inrush currents, Coif 6 is selected as it provides fewer errors in reconstructions and provides more accurate results. The provided model is simulated using ATP-EMTP with fundamental frequency of 50 Hz and sampling rate of 200 Hz. Omar AS Youssef presents an advanced scheme for discrimination of power system faults and inrush currents [8]. Using EMTP, a transformer is connected at 132/11 kv to the power system. 11/132kv transformer with star on both sides connected to the earthed neutral. The transmission line consists of two sections of 132 kv at 50 km. The data window required for the proposed algorithm is less than half of the frequency cycle. The results obtained for the technique are accurate, rapid and reliable. Distinguish between inrush current and internal faults in indirect symmetrical phase shift transformer (ISPST) demonstrated in Bhasekar.et.al. [9]. Using Parseval's theorem, wavelet energy is used for extracting different current signals from different operating conditions. The WT is used to convert the time domain into the frequency domain. The PSCAD/EMMTDC software is used from which the data is generated. Using the DB7 mother wave, WT decomposes from level 1 to level 7. D1 to D7 are used for internal fault discrimination from inrush current. Wavelet transform theory is explained in Introduction to Wavelets by Amara Grap [10] and ANN is explained in The Ann Book by RM Hristev [11]. This paper presents the results of inrush current detection using wavelet transform and artificial neural network. This helps.