Hoang THI THOM, Cho MING YUAN, Vu TUAN QUOC

A novel perturbed particle swarm optimization-based support vector machine for fault diagnosis in power distribution systems

In this paper, a novel perturbed particle swarm optimization (PPSO) algorithm is investigated to improve the performance of a support vector machine (SVM) for short-circuit fault diagnosis in power distribution systems. In the proposed PPSO algorithm, the velocity of each particle is perturbed whenever the particles strike into a local optimum, in order to achieve a higher quality solution to optimization problems. Furthermore, the concept of proposed perturbation is applied to three variants of PSO, and improved corresponding algorithms are named perturbed C-PSO (PC-PSO), perturbed T-PSO (PT-PSO), and perturbed K-PSO (PK-PSO). For the purpose of fault diagnosis, the time- domain re ectometry (TDR) method with pseudorandom binary sequence (PRBS) excitation is considered to generate the necessary fault simulation data set. The proposed approaches are tested on a typical two-lateral radial distribution network.

PDF

___

[1] Rstemli S, Ceng MS. Active lter solutions in energy systems. Turk J Elec Eng & Comp Sci 2015; 23: 1587-1607.
[2] Wattanasakpubal C, Bunyagul T. Algorithm for detecting, identifying, locating and experience to develop the automate faults location in radial distribution system. J Electr Eng Technol 2011; 5: 33-44.
[3] Mora-Florez J, Cormane-Angarita J, Carrillo-Caicedo G. Algorithm and mixture distributions for locating faults in power systems. Elec Power Sys Res 2009; 79: 714-721.
[4] Chen TH, Yang WC. Analysis of multi-grounded four-wire distribution systems considering the neutral grounding. IEEE T Power Deliver 2001; 16: 710-717.
[5] Liao Y. Algorithms for power system fault location and line parameter estimation. IEEE 2007 Southeastern Symposium on System Theory; 4{6 March 2007; Macon, GA, USA. New York, NY, USA: IEEE, pp. 189-193.
[6] Magnago FH, Abur A. Fault location using wavelets. IEEE T Power Deliver 1998; 13: 1475-1480.
[7] Borgheti A, Corsi S, Nucci CA, Paolone M, Pereto L, Tinarelli R. On the use of continuous-wavelet transform for fault location in distribution power systems. Elec Power Energy Sys 2006; 28: 608-617.
[8] Shaher MA, Sabra MM, Saleh AS. Fault location in multi-ring distribution networks using arti cial neural network. Elec Power Sys Res 2003; 64: 87-92.
[9] Pourahmadi-Nakhli M, Safavi AA. Path characteristic frequency-based fault locating in radial distribution systems using wavelets and neuron networks. IEEE T Power Deliver 2011; 60: 1654-1663.
[10] Hashmi GM, Papazyan R, Lehtonen M. Determining wave propagation characteristics of MV XLPE power cable using time domain re ectometry technique. Turk J Elec Eng & Comp Sci 2011; 19: 207-219.
[11] Komoda M, Aihara M. Development of a current detection type cable fault locator. IEEE T Power Deliver 1991; 6: 541-545.
[12] Navaneethan S, Soraghan JJ, Siew WH, McPherson F, Gale PF. Automatic fault location for underground low voltage distribution networks. IEEE T Power Deliver 2001; 16: 346-351.
[13] Mirzaei M, Hizam H, AbKadir MZA. Review of fault location methods for distribution power system. Austr J Basic Appl Sci 2009; 3: 2670-2676.
[14] Ozdemir AT, Dansman K. Fully parallel ANN-based arrhythmia classi er on a single-chip FPGA: FPAAC. Turk J Elec Eng & Comp Sci 2011; 19: 667-687.
[15] Magnago F, Vakula D, Sarma NVSN. Using neural networks for fault detection in planar antenna arrays. Prog Electromagn Res 2010; 14: 21-30.
[16] Ortac R, Kabaoglu. A fault detection, diagnosis, and recon guration method via support vector machines. Turk J Elec Eng & Comp Sci 2015; 23: 589-601.
[17] Deng X, Yuan R, Xiao Z, Li T, Wanga KLL. Fault location in loop distribution network using SVM technology. Elec Power Energy Sys 2015; 65: 254-261.
[18] Ye L, You D, Yin X, Wang K, Wu J. An improved fault-location method for distribution system using wavelets and support vector regression. Elec Power Energy Sys 2014; 55: 467-472.
[19] Vapnik VN. The Nature of Statistical Learning Theory. 2nd ed. New York, NY, USA: Springer-Verlag, 1995.
[20] Hsu C, Chang C, Lin C. A practical guide to support vector classi cation. Technical report, Department of Computer Science, National Taiwan University. July, 2003.
[21] Jack LB, Nandi AK. Fault detection using support vector machines and arti cial neural networks augmented by genetic algorithms. Mech Syst Signal Pr 2001; 16: 373-390.
[22] Samanta B, Al-Balushi KR, Al-Araimi SA. Arti cial neural networks and support vector machines with genetic algorithm for bearing fault detection. Eng Appl Artif Int 2003; 16: 657-665.
[23] Basgumus A, Namdar M, Yilmaz G, Altuncu A. Performance comparison of the differential evolution and particle swarm optimization algorithms in free-space optical communications systems. Adv Electr Comput Eng 2015; 15: 17-22.
[24] Yalcn N, Tezel G, Karakuru C. Epilepsy diagnosis using arti cial neural network learned by PSO. Turk J Elec Eng & Comp Sci 2015; 23: 421-432.
[25] Horan DM, Guinee RA. A novel pulse echo correlation tool for transmission path testing and fault diagnosis. J Comp 2006; 11: 31-39.
[26] Kennedy J, Eberhart R. Particle swarm optimization. In: IEEE 1995 International Conference on Neural Networks; 27 November{1 December 1995; Perth, WA, Australia. New York, NY, USA: IEEE. pp. 1942-1948.
[27] Eberhart R, Kennedy J. A new optimizer using particle swarm theory. In: IEEE 1995 International Symposium on Micro Machine and Human Science; 4{6 October 1995; Nagoya, Japan. New York, NY, USA: IEEE. pp. 39-43.
[28] Alam MN, Das B, Pant V. A comparative study of metaheuristic optimization approaches for directional overcurrent relays coordination. Elec Power Sys Res 2015; 128: 39-52.
[29] Abdullah MN, Bakar AHA, Rahim NA, Mokhlis H, Illias HA, Jamian JJ. Modi ed particle swarm optimization with time varying acceleration coefficients for economic load dispatch with generator constraints. J Electr Eng Technol 2014; 9: 15-26.
[30] Clerc M, Kennedy J. The particle swarm: explosion, stability, and convergence in a multidimensional complex space. IEEE T Evol Comp 2002; 6: 58-73.