Fault detection and classification in electrical power transmission system using artificial neural network
 Majid Jamil^{1},
 Sanjeev Kumar Sharma^{1}Email author and
 Rajveer Singh^{1}
Received: 30 December 2014
Accepted: 3 June 2015
Published: 9 July 2015
Abstract
This paper focuses on the detection and classification of the faults on electrical power transmission line using artificial neural networks. The three phase currents and voltages of one end are taken as inputs in the proposed scheme. The feed forward neural network along with back propagation algorithm has been employed for detection and classification of the fault for analysis of each of the three phases involved in the process. A detailed analysis with varying number of hidden layers has been performed to validate the choice of the neural network. The simulation results concluded that the present method based on the neural network is efficient in detecting and classifying the faults on transmission lines with satisfactory performances. The different faults are simulated with different parameters to check the versatility of the method. The proposed method can be extended to the Distribution network of the Power System. The various simulations and analysis of signals is done in the MATLAB^{®} environment.
Keywords
Background
The electrical power system consists of so many different complex dynamic and interacting elements, which are always prone to disturbance or an electrical fault. The use of high capacity electrical generating power plants and concept of grid, i.e. synchronized electrical power plants and geographical displaced grids, required fault detection and operation of protection equipment in minimum possible time so that the power system can remain in stable condition. The faults on electrical power system transmission lines are supposed to be first detected and then be classified correctly and should be cleared in least fast as possible time. The protection system used for a transmission line can also be used to initiate the other relays to protect the power system from outages. A good fault detection system provides an effective, reliable, fast and secure way of a relaying operation.
The application of a pattern recognition technique could be useful in discriminating the faulty and healthy electrical power system. It also enables us to differentiate among three phases which phase of a three phase power system is experiencing a fault. The artificial neural networks (ANNs) are very powerful in identifying the faulty pattern and classification of fault by pattern recognition. There are lot of algorithms based upon ANN have been developed, tested and implemented practically in electrical power systems (Dalstein and Kulicke 1995; Bouthiba 2004; Venkatesan and Balamurugan 2007; Lin et al. 2001). WheiMin Lin et al. (2001) presents the method based on pattern recognition, but the method is very complex. Angel L. Orille Fernandez et al. (2002) presented the finite impulse response (FIRANN) method to detect and classify the fault. The author uses the impulse response of voltages and currents, which limits its applications. M. S. Abdel Aziz et al. (2012), presents adaptive neurofuzzy inference system (ANFIS) in power distribution system. The Fourier transform is used with ANFIS, which has its inherent disadvantages. Jayabharta Reddy and Mohanta (2007) proposes and wavelet transform and fuzzy logic based algorithm for fault classification, but the fuzzy logic gives poor performance at boundary line cases. Alanzi et al. (2014) proposed the fault detection by unconventional a synchronized method, but decision making is left untouched. An efficient and reliable protection method should capable to perform more than satisfactory under various system operating conditions and different electrical network parameters. As far as ANNs are considered they exhibit excellent qualities such as normalization and generalization capability, immunity to noise, robustness and fault tolerance. Therefore, the declaration of fault made by ANNbased fault detection method should not be affected seriously by variations in various power system parameters. Therefore so many ANNbased techniques have been developed and employed in power system. The results obtained from these methods are encouraging (Kezunovic et al. 1996; Rizwan et al. 2013). Some algorithms based upon ANN for location of faults and relay architecture for protection of transmission line are also suggested by the researchers (SanayePasand and KharashadiZadeh 2006; Lahiri et al. 2005). In this paper, a new algorithm based upon ANN is proposed for fast and reliable fault detection and classification. The various electrical transient system faults are modelled, simulated and an ANN based algorithm is developed for recognition of these faulty patterns. The performance of the proposed algorithm is evaluated by simulating the various types of fault and the results obtained are encouraging. It is observed that the algorithm developed is capable to perform fast and correct classification for different combinations of faulty conditions, e.g. fault type, fault resistance, fault location and short circuit MVA of the system.
The paper is divided into four categories. The section one is background, which discusses the vital points of fault detection. Second section gives over view of the artificial neural network and its training methods adopted. Third section gives the details of transmission line model and its simulation, the last fourth section is conclusion.
Artificial neural network

Number of transmission line configuration are possible as there can be any possibility from short length, long length, single circuit transmission line to doublecircuit transmission lines, etc.

There are several methods to simulate the network with different power system conditions in a fast and reliable manner;

The conditions of the electrical power system change after each and every disturbance. Hence a neural network is capable to incorporate the dynamic changes in the power systems.

The ANN output is very fast, reliable and accurate depending on the training, because its working depends upon a series of very simple operations.
The algorithm which employed ANNs programming offers many advantages, but it also suffers with many disadvantages, which are very complex in nature. Some of the important factors are the selection of type of network, architecture of the network (which includes the selection of number of layers, number of neurons in each layer, selection of activation functions, learning algorithms parameters etc.), termination criteria etc. There are various parameters like values of the pre fault and post fault voltages and currents of the respective three phases in steady state required for precise fault detection and classification.
The values of the pre fault and post fault voltage and current of respective three phases are very different and are governed by the type of fault. Thus, the fault classification method required a neural network that allows it to determine the type of fault from the patterns of pre fault and post fault voltages and currents, which are generated from the values measured from a three phase transmission line of an electrical power system at one terminal. The neural network is based upon the total six number of inputs, i.e. the voltages and currents of respective three phases. The neural network is trained by using these six inputs. The total number of outputs of the neural network is four in numbers, i.e. three phases A, B, C and fourth is ground of three phase transmission line.
Back propagation neural network (BPNN)
In the Back propagation neural network (BPNN) the output is feedback to the input to calculate the change in the values of weights. One of the major reasons for taking the back propagation algorithm is to eliminate the one of the constraints on two layers ANNs, i.e. similar inputs lead to the similar output. The error for each iteration and for each point is calculated by initiating from the last step and by sending calculated the error backwards. The weights of the backerrorpropagation algorithm for the neural network are chosen randomly, feeds back in an input pair and then obtain the result. After each step, the weights are updated with the new ones and the process is repeated for entire set of inputsoutputs combinations available in the training data set provided by developer. This process is repeated until the network converges for the given values of the targets for a pre defined value of error tolerance. The entire process of back propagation can be understood by Figure 1. The backerrorpropagation algorithm is effectively used for several purposes including its application to error functions (other than the sum of squared errors) and for the calculation of Jacobian and Hessian matrices. This entire process is adopted by each and every layer in the entire the network in the backward direction (Haykin 1994). The proposed algorithm uses the Mean Square Error (MSE) technique for calculating the error in each iteration.
 1.Forward propagation$$a_{j} = \sum\limits_{i}^{m} {w_{ji}^{(1)} } x_{i}$$$$z_{j} = f(a_{j} )$$$$y_{j} = \sum\limits_{i}^{M} {w_{kj}^{(2)} } z_{j}$$
 2.Output difference$$\delta_{k} = y_{k}  t_{k}$$
 3.Back propagation for hidden layers$$\delta_{j} = (1  z_{j}^{2} )\sum\limits_{k = 1}^{K} {w_{kj}^{{}} } \delta_{k}$$
 4.
The gradient of error with respect to first layer weights and second layer weights are calculated.
 5.
In this step the previous weights are updated.

The structure of the neural network

The size of the neural network (number of layers, etc.)

The complexity of the problem under investigation

The method of learning adopted (training function)

The size of the input and output data set (training/learning patterns).
The efficiency and best performance of a developed ANN and the optimum learning method can be estimated by using the final trained network by testing with testing dataset. This testing data set is supposed to be provided by the developer and is a part of network development.
Modelling the three phase transmission line system
A typical 400 × 10^{3} V three phase transmission line system having generators at two ends has been used for simulating, developing and implementing the developed method based upon ANNs. The system consists of two generators of 400 × 10^{3} V, each located each ends of the transmission line to simulate and study the various faults at different various locations on the transmission line.
Measurement voltage and current and preprocessing of data
The three phase Voltage and current waveforms have been generated and sampled at a frequency of 1,000 Hertz. Hence, there are 20 samples per each cycle. A reduction in the overall size of the neural network improves the time performance of the neural network and this can be achieved by optimizing the feature extraction. By doing this, all of the important and relevant information present in the waveforms of the voltage and current signals can be used effectively.
Training and testing
For the task of training the neural networks for different stages, sequential feeding of input and output pair has been adopted. In order to obtain a large training set for efficient performance, each of the ten kinds of faults has been simulated at different locations along the considered transmission line. In view of all these issues, about 100 different fault cases for each of the 10 kinds of faults have been simulated. Apart from the type of fault, the phases that are faulted and the distance of the fault along the transmission line, the fault resistance also has been varied to include several possible realtime fault scenarios.
The fault resistance has been varied as follows: 0.25, 0.5, 0.75, 1, 5, 10, 25, 50 Ω. Also, the fault distance has been varied at an incremental factor of every 3 km on a 300 km transmission line.
Fault detection
The correlation coefficient (r) is a measure of how well the neural network’s targets can track the variations in the outputs (0 being no correlation at all and 1 being complete correlation). The correlation coefficient in this case has been found to be 0.99982 which indicates excellent correlation.
The correlation coefficient (r) is a measure of how well the neural network’s targets can track the variations in the outputs (0 being no correlation at all and 1 being complete correlation). The correlation coefficient in this case has been found to be 0.99982 which indicates excellent correlation.
Fault classification
Fault classifier ANN outputs for various faults
Type of fault  Phase A  Phase B  Phase C  Ground 

AG  1  0  0  1 
BG  0  1  0  1 
CG  0  0  1  1 
AB  1  1  0  0 
BC  0  1  1  0 
CA  1  0  1  0 
ABG  1  1  0  1 
BCG  0  1  1  1 
CAG  1  0  1  1 
ABC  1  1  1  0 
The training set contains total 7,920 inputs and output pattern (792 for each type of fault out of ten faults) with six inputs and one output in each input–output combination. Backpropagation networks with a variety of combinations of hidden layers and the different number of neurons in each hidden layer were analyzed. Of those, the one that achieved satisfactory performance was the neural network 6384, i.e. 6 neurons in the input layer, 1 hidden layer with 38 neurons in it and four neurons in the output layer.
Conclusion
In this paper we have studied the application of artificial neural networks for the detection and classification of faults on a three phase transmission lines system. The method developed utilizes the three phase voltages and three phase currents as inputs to the neural networks. The inputs were normalized with respect to their prefault values respectively. The results shown in the paper is for line to ground fault only. The other types of faults, e.g. linetoline, double linetoground and symmetrical three phase faults can be studied and ANNs can be developed for each of these faults.
All the artificial neural networks studied here adopted the backpropagation neural network architecture. The simulation results obtained prove that the satisfactory performance has been achieved by all of the proposed neural networks and are practically implementable. The importance of choosing the most appropriate ANN configuration, in order to get the best performance from the network, has been stressed upon in this work. The sampling frequency adopted for sampling the voltage and current waveforms in this research work is 1,000 Hz.
 1.
Artificial neural networks are a reliable and effective method for an electrical power system transmission line fault classification and detection especially in view of the increasing dynamic connectivity of the modern electrical power transmission systems.
 2.
The performance of an artificial neural network should be analyzed properly and particular neural network structure and learning algorithm before choosing it for a practical application.
 3.
Back propagation neural networks delivers good performance, when they are trained with large training data set, which is easily available in power systems and hence back propagation networks have been chosen for proposed method.
The scope of ANN is wide enough and can be explored more. The fault detection and classification can be made intelligent by nature by developing suitable intelligent techniques. This can be achieved if we have the computers which can handle large amount of data and take least amount time for calculations.
Declarations
Authors’ contributions
MJ provide the basic idea of the research and supervise. SKS developed the Simulink/MATLAB model of the transmission line, ANN algorithm related work and compile results. RS provided the background literature, organized and drafting of the manuscript. All authors read and approved the final manuscript.
Compliance with ethical guidelines
Competing interests The authors declare that they have no competing interests.
Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
Authors’ Affiliations
References
 Alanzi EA, Younis MA, Ariffin AM (2014) Detection of faulted phase type in distribution systems based on one end voltage measurement. Electr Power Energy Syst 54:288–292View ArticleGoogle Scholar
 Aziz MS, Abdel MA, Hassan M, Zahab EA (2012) Highimpedance faults analysis in distribution networks using an adaptive neuro fuzzy inference system. Electr Power Compon Syst 40(11):1300–1318View ArticleGoogle Scholar
 Bouthiba T (2004) Fault location in EHV transmission lines using artificial neural networks. Int J Appl Math Comput Sci 14(1):69–78Google Scholar
 Chaturvedi DK (2008) Soft computing techniques and its applications in electrical engineering. Springer, Berlin, HeidelbergGoogle Scholar
 Chaturvedi DK, Mohan M, Kalra PK (2004) Improved generalized neuron model for shortterm load forecasting. Soft Comput 8:370–379View ArticleGoogle Scholar
 Dalstein T, Kulicke B (1995) Neural network approach to fault classification for highspeed protective relaying. IEEE Trans Power Deliv 4:1002–1009View ArticleGoogle Scholar
 Demuth H, Beale M, Hagan M (2014) Neural networks toolbox 6: the math works user’s guide for MATLAB and Simulink. The MathWork, USAGoogle Scholar
 ElSharkawi M, Niebur D (1996) A tutorial course on artificial neural networks with applications to Power systems. IEEE Publ. No. 96TP 1120Google Scholar
 Fernandez ALO, Ghonaim NKI (2002) A novel approach using a FIRANN for fault detection and direction estimation for highvoltage transmission lines. IEEE Trans Power Del 17(4):894–900View ArticleGoogle Scholar
 Haykin S (1994) Neural networks. A comprehensive foundation. Macmillan Collage Publishing Company, New YorkGoogle Scholar
 Jayabharta Reddy M, Mohanta DK (2007) A wavelet fuzzy combined approach for classification and location of transmission line faults. Electr Power Energy Syst 29:669–678View ArticleGoogle Scholar
 Kezunovic M, Rikalo I, Sobajic DJ (1996) Realtime and offline transmission line fault classification using neural networks. Eng Intell Syst 10:57–63Google Scholar
 Lahiri U, Pradhan AK, Mukhopadhyaya S (2005) Modular neuralnetwork based directional relay for transmission line protection. IEEE Trans Power Deliv 20(4):2154–2155View ArticleGoogle Scholar
 Li Y, Tang Z, Zhan Y (2014) Twodimensional bilinear preserving projections for image feature extraction and classification. Neural Comput Appl 24(3–4):901–999View ArticleGoogle Scholar
 Lin WM, Yang CD, Lin JH, Tsay MT (2001) A fault classification method by RBF neural network with OLS learning procedure. IEEE Trans Power Del 16(4):473–477View ArticleGoogle Scholar
 Reducindo I, Santana ERA, Delgado DUC, Alba A (2014) Registration of multimodal medical images by particle filter: evaluation and new results. IEEE Latin Am Trans 12(2):129–137View ArticleGoogle Scholar
 Rizwan M, Kalam MA, Jamil M, Ansari AQ (2013) WaveletFFNN based fault location estimation of a transmission line. Electr Eng Res EER Int Ref J USA 1(3):77–82. ISSN: 23277254 (print)Google Scholar
 Rubio JJ (2014) Evolving intelligent algorithms for the modelling of brain and eye signals. Appl Soft Comput 14(Part B):259–268View ArticleGoogle Scholar
 Rubio JJ, Ortiz F, Mariaca CR, Tovar JC (2013) A method for online pattern recognition for abnormal eye movements. Neural Comput Appl 22(3–4):597–605View ArticleGoogle Scholar
 SanayePasand M, KharashadiZadeh H (2006) An extended ANNbased high speed accurate distance protection algorithm. Electr Power Energy Syst 28(6):387–395View ArticleGoogle Scholar
 Venkatesan R, Balamurugan B (2007) A realtime hardware fault detector using an artificial neural network for distance protection. IEEE Trans Power Deliv 16(1):75–82View ArticleGoogle Scholar
 Ye J (2014) Compound control of a compound cosine function neural network and PD for manipulators. Int J Control 87(10):2118–2129Google Scholar