Abstract— In this paper, wavelet transform and artificial neural network (ANN) is used for processing current waveforms and distinguish between inrush current, fault and normal situation. Wavelet transform is used to analyze and detect various frequency components present in the signal. ANN is a tool which is utilized for classification of data based on specific properties. Different types of power system combinations are used in simulation. Fault detection is an important part for safety of electric power system. For the synthesis of signals and the classification of current conditions, WT and ANN are used in collectively.Index Terms— Inrush current, Wavelet Transform, Artificial Neural Network.I. INTRODUCTIONIn transmission line when current does not flow from transformer’s secondary side after flowing from its primary side, due to this over current in transformer occurs. This fault is known as an inrush current in transformer. Inrush current is the transient maximum, current drawn by an electrical device when first turned on. Alternating current electric motor and transformer may draw inrush current several times. Its normal full load current first energizes for a two cycles of the input waveform.There are different methods to solve this fault. First method is Differential Transformation, in this method when currents of primary side and secondary side of transformer are equal. In such case, relay connected between them will detect the fault and trip the circuit. Another method is Fourier series transform. In this method when fault occurs then frequency of transmission line increases than the rated frequency. The drawback of this method is, it only detects the fault of frequency 50Hz and 0-5sec time period, it does not give the exact time of fault. To overcome this drawback Short Time Fourier Transform (STFT) is introduced. It gives accurate time of fault by dividing the overall time with ½. STFT also has some limitations that once you choose a particular size for the time window, that window is same for all frequencies. Thiswork is easily done by Wavelet with more precision. Wavelet Transform is used to detect the inrush current conditions. Artificial Neural Network (ANN) is used to classify the inrush current conditions. The simulation process is done by MATLAB.In 1, presents the discrimination of inrush current from internal fault currents in power transformer. The method is based on wavelet and neural network (WNN). A 3 phase, 750 MVA, 27/420 kv, ?/Y transformer connected to an infinite bus-bar is used for simulation. Discrete wavelet transform (DWT) coefficients are calculated from PSCAD simulation data and given to the MATLAB. Db6 wavelet is used as mother wavelet. ANN is used for discrimination of internal fault and magnetizing inrush currents.Jazebi.et.al. 2 proposes an approach of magnetizing inrush current using Gaussian Mixture Models (GMM). The simulation is done 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 simulation system. Mother wavelet type and decomposition level are used in detecting and localizing different kinds of fault transients. The sampling frequency and system basic frequency is 10 KHz and 50 Hz. The window size of WT is 50 samples per window for GMM. In power system, GMM is proved as simple identification criteria, best suited for protection, fast performance and further more investments.A.R.Sedighi and M.R.Haghifam 3 presents an efficient method for detection of inrush current in distribution transformer based on wavelet transform. Electro Magnetic Transient Program (EMTP) is used for the simulation of Inrush current and other events for feature extraction and discrimination. 20kv distribution feeder is used and 20kHz sampling frequency in single phase to ground fault and inrush current.In 4 describes protection schemes based on wavelet transform for power transformer. Wavelet coefficients are calculated by different operating conditions such as load normal, inrush, internal and external current. Energy and standard deviation features are obtained from parsevals theorem. These features are given as input to Probabilistic Neural Network (PNN) for fault classification. A 450MVA,INRUSH CURRENT DETECTION USING WAVELET TRANSFORM AND ARTIFICIAL NEURAL NETWORKPrachi R. Gondane1, Rukhsar M. Sheikh1, Kajol A. Chawre1, Vivian V. Wasnik1, Dr. Altaf Badar2, M.T.Hasan2Scholar, Dept. of EE, Anjuman College of Engineering and Technology, Sadar, Nagpur, Maharashtra, India1Assistant Professor, Dept. of EE, Anjuman College of Engineering and Technology, Sadar, Nagpur, Maharashtra, India2500 / 3230 kv Y/ ? transformer connected to neutral grounded is used for simulation. Db9 is used as mother wavelet.In 5, the method is for discrimination of inrush current and internal fault is proposed in 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 current waveform, it distinguishes both type of current. It consist of two classes of data for validation such inrush and internal fault current waveforms. It has two transformers T1 and T2 which is connected through transmission line.A. Tahasildar.et.al. 6 gives a combine technique of wavelet transform and neural network for the detection of internal fault and inrush current. A 750MVA, 27/450kv, 3 phase power transformer is used. In power transformer, the decomposition of current signals into series wavelet component is done by WT. Then the detailed spectral coefficient is calculated. And those signals are given to the trained neural network for discrimination of internal and magnetizing inrush current fault. Total 220 cases have been simulated in MATLAB software.L. Sonwani and D. Singh 7 introduces an identification of inrush current using WT. As internal fault and inrush current are non-stationary. WT has the ability to track the signal dynamic property. A 3-phase, 450MVA, 500kV/230kV/ 60kV are used of Y/Y/Delta connections. The simulation time is 0.5sec and sampling rate is 3.2 kHz. The samples are simulated at MATLAB.Omar A.S. Youssef presents an advance scheme for the discrimination of faults in power system and inrush currents 8. Using EMTP, a transformer is connected 132/11kv to power system. 11/132kv transformer with both sides star connected with grounded neutral. The transmission line is two 132kv at 50km sections is used. The data window required for proposed algorithm is less than half frequency cycle. The results obtained for the technique is accurate, fast 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 the extraction of different current signals from different operating conditions. WT is used to convert time domain into frequency domain. The software PSCAD/ EMTDC is used from which the data is generated. Using DB7 mother wavelet, WT decomposes from level 1 to level 7. D1 to D7 is used for the discrimination of internal fault from inrush current. The theory of wavelet transform is explained in An Introduction to Wavelets by Amara Grap 10 and ANN is explained in The Ann Book by R.M. Hristev 11.This paper presents results detection of inrush current using wavelet transform and artificial neural network. This helps to distinguish inrush current and internal fault current. The data is generated from Db4 which is used as mother wavelet with level 5.II. INRUSH CURRENTInrush current is the maximum instantaneous input current given by an electrical device when it is switched on. This current arises due to high starting current. To charge the capacitor, inductor and transformer, high current is produced at the time of switch on. Its value depends on the core material, residual flux and instant of energization.In power transformer, inrush current other than energization also takes after the clearance of external fault until voltage recovery. Inrush current also contains even and odd harmonics. It also has DC offset.Inrush current can be high as 20 times the normal current value it can only last for about 10 ms. It requires about 30 to 40 cycles for the current to settle down to its normal current value.III. WAVELET TRANSFORM (WT)Wavelets are mathematical functions which break the data into various frequency components. Each component is then studied with a resolution matched to its scale. WT has advantages over Fourier methods in analyzing physical situations where the signal contains discontinuities and sharp spikes. A drawback in STFT is that once a particular size is selected for the time window, then time window remains same for all frequencies. To accurately analyze signals that have abrupt changes, a new class of functions that are well localized in time and frequency is used. Wavelets were evolved independently in different fields like quantum physics, mathematics, seismic geology and electrical engineering has discussed in 10.WT are classified as Continuous Wavelet Transform (CWT) and Discrete Wavelet Transform (DWT). WT breaks the signals into various frequencies which are used for the detection of inrush current, fault current and normal current. The detection of inrush current is implemented at DWT as you can see in the fig1.Fig 1. Analysis of inrush current using DWT in MATLABIV. ARTIFICIAL NEURAL NETWORK (ANN)The basic building block of Artificial Neural Network (ANN) is the neuron. A neuron is processing units which have some inputs and only one output. The ANN is built by putting the neurons in layers and connecting the output of the neuronsfrom one layer to the inputs of the neurons from the next layerhas discussed 11.An ANN is configured for a specific application, such aspattern recognition or data classification, through a learningprocess. Learning in biological systems is done by adjustmentsto the synaptic connections that exist between the neurons.WT breaks the signal into small contents, dependingupon the content of each frequency signal is classified byANN. The fig 2 shows the model of a trained ANN systemwhich differentiates between the inrush and fault current.Fig 2. Model obtained by consecutive training of ANN ModelAn example of the input values which are used for testingthe Simulink model is given in Fig 3. The input values are forinrush current, requiring 1 as output.Fig 3. Input given to ANN modelThe graph in Fig 4 shows a precise classification with outputas 1 signifying Inrush current. For fault condition the output is0 and for normal it is 2.Fig 4. Output waveform of ANN modelV.SIMULATION AND RESULTThe discrimination of inrush current and fault current isobtained by simulating various models. The generalized modelis as shown in the fig 5.Fig 5. Schematic model for analysisIt consists of a generator, transformer, transmission line andload having different combinations. Other equipment likecircuit breaker and different fault resistances were utilized asand where required. The simulation was done in MATLABusing Simulink. The data is generated from wavelet is throughdb4 with level 5.VI. CONCLUSIONAn efficient technique is used for the detection of inrushcurrent using wavelet transform and artificial neural network.The proposed technique is based on the decomposition ofcurrents using WT with db4 as mother wavelet. ANN is usedfor the discrimination of normal, inrush and fault current.REFERENCES1 A.Y.Abdelaziz, Amr. A. Ibrahim. (2009). Classification of transientphenomenon in power transformer based on a Wavelet-Ann approach.OJEEE. 3(4).2 S Jazebi, B Vahidi, S.H. Hosseinian, J.Faiz. (2009). Magnetizing inrushcurrent identification using wavelet based gaussian mixture models.ELSEVIER, Simulation Modeling Practice and Theory. 17, pp.991-1010.3 A.R.Sedighi, M.R.Haghifam. (2005). Detection of inrush current indistribution transformer using wavelet transform. ELSEVIER, ElectricalPower and Energy Systems. 27, pp.361-370.4 S. Sendilkumar, B.L.Mathur, and Joseph Henry. (2010). Differentialprotection for power transformer using wavelet transform and PNN.World academy of science, engineering and technology.5 Maya.P, S. Vidya shree, Roopasree.K and K.P.Soman. (2015).Discrimination of internal fault current and inrush current in a powertransformer using empirical wavelet transform. ELSEVIER, ProcediaTechnology. 21, pp.514-519.6 Mohommad Nayeem A TAhasildar, S.L.Shaikh. (2013). A noveltechnique for power transformer protection based on combined wavelettransform and neural network. IJAEEE.2(4).7 Lakshminarayan Sonwani, Dharmendra Kumar Singh. (2015). Identifyinrush current in power transformer using the wavelet transform.IJSETR. 4(13).8 Omar A. S. Youssef. (2002). Discrimination between faults andmagnetizing inrush currents in transformers based on wavelettransforms. ELSEVIER, Electric Power Systems Research. 63, pp.87-94.9 Shailendra Kumar Bhasker, Manoj Tripathy and Vishal Kumar. (2014).Wavelet transform based discrimination between inrush and internalfault of indirect symmetrical phase shift transformer. Application ofwavelets to model short-term power system disturbances. IEEE.10 Amara Graps. An introduction to wavelet.11 R.M.Hristev. (1998).The ANN Book. Edition (second)G Load1