Abstract
This paper concerns the application of a neuro-fuzzy learning method based on data streams for high impedance fault (HIF) detection in medium-voltage power lines. A wavelet-packet-transform-based feature extraction method combined with a variation of evolving neuro-fuzzy network with fluctuating thresholds is considered for recognition of spatial–temporal patterns in the data. Wavelet families such as Haar, Symlet, Daubechie, Coiflet and Biorthogonal were investigated as a way to provide the most discriminative features for fault detection. The proposed evolving neuro-fuzzy classification model has shown to be particularly suitable for the problem because the HIF environment is subject to concept changes. Different from other statistical and intelligent approaches to the problem, the developed neuro-fuzzy model for HIF classification is not only parametrically, but also structurally adaptive to cope with nonstationarities and novelties. New neurons and connections are incrementally added to the neuro-fuzzy network when necessary for the identification of new patterns, such as faults and usual transients including sag, swell and spikes due to the switching of 3-phase capacitors and energization of transformers. Experimental evaluations compare the proposed classifier with other well-established computational intelligence methods, viz. multilayer perceptron neural network, learning vector quantization neural network and a support vector machine model. Results have shown that the evolving neuro-fuzzy system is effective and robust to changes. The system is able to maintain its detection and classification accuracy even in situations in which other classifiers exhibit a significant drop in accuracy due to gradual and abrupt changes of the fault patterns. Fuzzy rules are useful for interpretability purposes and help to enhance model credibility for decision making.
Similar content being viewed by others
Abbreviations
- ATP:
-
Alternative transients program
- DWT:
-
Discrete wavelet transform
- ECoS:
-
Evolving connectionist system
- EFuNN:
-
Evolving fuzzy neural network
- HIF:
-
High impedance fault
- HP:
-
High-pass filter
- MF:
-
Membership function
- LP:
-
Low-pass filter
- LVQ:
-
Learning vector quantization
- MLP:
-
Multilayer perceptron
- SVM:
-
Support vector machine
- WPT:
-
Wavelet packet transform
- \(D_i\) :
-
i-th diode
- \(L_i\) :
-
i-th inductance
- \(R_i\) :
-
i-th resistance
- V :
-
Voltage
- N :
-
Number of samples
- x :
-
Input vector
- y :
-
Output vector
- H(x):
-
Entropy of x
- W :
-
Weight vector
- \(S_{\mathrm{thr}}\) :
-
Sensitivity threshold
- \(E_{\mathrm{thr}}\) :
-
Error threshold
- \(A_j\) :
-
Activation degree of the j-th neuron
- \(D_j\) :
-
j-th normalized fuzzy distance
- \(\eta\) :
-
Learning rate
References
Sedighizadeh M, Rezazadeh A, Elkalashy NI (2010) Approaches in high impedance fault detection: a chronological review. Adv Electr Comput Eng 10(3):114–128
Ghaderi A, Ginn H, Mohammadpour H (2017) High impedance fault detection: a review. Electr Power Syst Res 143:376–388
Santos WC, Lopes FV, Brito N, Souza B (2017) High impedance fault identification on distribution networks. IEEE Trans Power Deliv 32(1):23–32
Silva S, Costa P, Gouvea M, Lacerda A, Alves F, Leite D (2018) High impedance fault detection in power distribution systems using wavelet transform and evolving neural network. Electr Power Syst Res 154:474–483
Samantaray SR, Panigrahi BK, Dash PK (2008) High impedance fault detection in power distribution networks using time–frequency transform and probabilistic neural network. IET Gener Transm Distrib 2(2):261–270
Etemadi AH, Pasand MS (2008) High impedance fault detection using multi-resolution signal decomposition and adaptive neural fuzzy inference system. IET Gener Transm Distrib 2(1):110–118
Baqui I, Zamora I, Mazon J, Buigues G (2011) High impedance fault detection methodology using wavelet transform and artificial neural networks. Electr Power Syst Res 81:1325–1333
Chen J, Phung B, Zhang D, Blackburn T, Ambikairajah E (2013) Study on high impedance fault arcing current characteristics. In: Australasian universities power engineering conference, pp 1–6
Torres V, Guardado JL, Ruiz HF, Maximov S (2014) Modelling and detection of high impedance faults. Electr Power Energy Syst 61:163–172
Leite D, Ballini R, Costa P, Gomide F (2012) Evolving fuzzy granular modeling from nonstationary fuzzy data streams. Evolv Syst 3(2):65–79
Angelov P, Filev D, Kasabov N (2010) Evolving intelligent systems: methodology and applications, 1st edn. Wiley, Hoboken
Mohamad S, Sayed-Mouchaweh M, Bouchachia A (2018) Active learning for classifying data streams with unknown number of classes. Neural Netw 98:1–15
Andonovski G, Music G, Blazic S, Skrjanc I (2018) Evolving model identification for process monitoring and prediction of non-linear systems. Eng Appl Artif Intell 68:214–221
Hyde R, Angelov P, Mackenzie A (2017) Fully online clustering of evolving data streams into arbitrarily shaped clusters. Inf Sci 382:96–114
Pratama M, Lughofer E, Lim C, Rahayu W, Dillon T, Budiyono A (2017) A novel evolving semi-supervised classifier. Int J Fuzzy Syst 19:863–880
Kasabov N (2007) Evolving connectionist systems: the knowledge engineering approach. Springer, London
Pratama M, Anavatti SG, Angelov P, Lughofer E (2014) PANFIS: a novel incremental learning machine. IEEE Trans Neural Netw Learn Syst 25(1):55–68
Leite D, Costa P, Gomide F (2013) Evolving granular neural networks from fuzzy data streams. Neural Netw 38(1):1–16
Leite D, Costa P, Gomide F (2010) Evolving granular neural network for semi-supervised data stream classification. In: IEEE international joint conference on neural networks, pp 1–8
Rubio JJ (2014) Evolving intelligent algorithms for the modelling of brain and eye signals. Appl Soft Comput 14(B):259–268
Rubio JJ (2018) Error convergence analysis of the SUFIN and CSUFIN. Appl Soft Comput. https://doi.org/10.1016/j.asoc.2018.04.003
Lughofer E, Pratama M, Skrjanc I (2018) Incremental rule splitting in generalized evolving fuzzy systems for autonomous drift compensation. IEEE Trans Fuzzy Syst 26(4):1854–1865
Leite D, Palhares R, Campos V, Gomide F (2015) Evolving granular fuzzy model-based control of nonlinear dynamic systems. IEEE Trans Fuzzy Syst 23(4):923–938
Zamanan N, Sykulski J (2014) The evolution of high impedance fault modeling. In: IEEE 16th international conference on harmonics and quality of power, pp 77–81
Kersting WH (2001) Radial distribution test feeders. In: Power Engineering Society Winter Meeting, Columbus, pp 908–912
Ghaffarzadehand N, Vahidi B (2010) A new protection scheme for high impedance fault detection using wavelet packet transform. Adv Electr Comput Eng 81(3):17–20
Barros J, Diego RI (2008) Analysis of harmonics in power systems using the wavelet-packet transform. IEEE Trans Instrum Meas 57(1):63–69
Costa F, Souza B, Brito N, Silva J, Santos W (2015) Real-time detection of transients induced by high impedance faults based on the boundary wavelet transform. IEEE Trans Ind Appl 51(6):5313–5323
Haykin S (2009) Neural networks and learning machines, 3rd edn. Pearson, London
Rubio J, Lughofer E, Meda-Campana J, Paramo LA, Novoa J, Pacheco J (2018) Neural network updating via argument Kalman filter for modeling of Takagi–Sugeno fuzzy models. J Intell Fuzzy Syst 35(2):2585–2596
Lughofer E (2012) Single-pass active learning with conflict and ignorance. Evolv Syst 3(4):251–271
Rubio J, Lughofer E, Angelov P, Novoa J, Meda-Campana J (2018) A novel algorithm for the modeling of complex processes. Kybernetika 54(1):79–95
Abe S (2010) Support vector machines for pattern classification. Advances in pattern recognition, 2nd edn. Springer, London
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Silva, S., Costa, P., Santana, M. et al. Evolving neuro-fuzzy network for real-time high impedance fault detection and classification. Neural Comput & Applic 32, 7597–7610 (2020). https://doi.org/10.1007/s00521-018-3789-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-018-3789-2