Browse > Article
http://dx.doi.org/10.1007/s43236-022-00434-w

Efficient learning approach using new combined fuzzy-M5P model tree: experimental investigation of active power filters  

Bouhouta, Ahmed (Research Laboratory of Electrical Engineering and Automatic (LREA), Department of Electrical Engineering, University of Medea)
Moulahoum, Samir (Research Laboratory of Electrical Engineering and Automatic (LREA), Department of Electrical Engineering, University of Medea)
Kabache, Nadir (Research Laboratory of Electrical Engineering and Automatic (LREA), Department of Electrical Engineering, University of Medea)
Publication Information
Journal of Power Electronics / v.22, no.6, 2022 , pp. 981-990 More about this Journal
Abstract
This paper deals with the complete design and real-time implementation of a novel mixed control based on the pruned model tree (M5P) and collected datasets of a fuzzy logic controller. This combination aims to benefit from both the decision tree rapidity and the fuzzy logic advantages. In harmonic mitigation systems with an active power filter, a strategy for identifying harmonic currents has a considerable influence on the quality and capacity of compensation. The proposed fuzzy-M5P model tree is assessed in the indirect current control identification algorithm along with an effective comparison using the artificial neural network approach. The two learning methods are described and contrasted in an organized manner to evaluate their respective advantages in both steady state and dynamic state operating conditions. In compliance with IEEE std 519-1992 harmonic limits, an experimental setup was realized using dSPACE 1103 hardware to verify the excellent behavior of the system and to confirm the effectiveness of the proposed M5P based control in terms of an almost unity power factor of 0.99, a low total harmonic distortion value of 3.07%, and satisfactory dynamic performances characterized by a fast response time of 100 ms.
Keywords
M5P decision tree; ANN; FLC; Total harmonic distortion; Transient state;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 Bekakra, Y., Zellouma, L., Malik, O.: Improved predictive direct power control of shunt active power filter using GWO and ALO-simulation and experimental study. Ain Shams Eng J 12(4), 3859-3877 (2021)   DOI
2 Hoon, Y., Mohd Radzi, M.A., Khair Hassan, M., Mailah, N.F.: DC-link capacitor voltage regulation for three-phase three-level inverter-based shunt active power filter with inverted error deviation control. Energies MDPI 9, 533 (2016)   DOI
3 Musa, S., Radzi, M.A.M., Hizam, H., Wahab, N.I.A., Hoon, Y., Ammirrul, M.: Modified synchronous reference frame based shunt active power filter with fuzzy logic control pulse with modulation inverter. Energies MDPI 10, 758 (2017)   DOI
4 Y. Wang, I. H. Witten: Induction of model trees for predicting continuous classes (1996)
5 Benyamina, A., Moulahoum, S., Colak, I., Bayindir, R.: Design and real time implementation of adaptive neural-fuzzy inference system controller based unity single phase power factor converter. Electr Power Syst Res 152, 357-366 (2017)   DOI
6 Singh, B., Verma, V.: An indirect current control of hybrid power filter for varying loads. IEEE Trans Power Del 21(1), 178-184 (2006)   DOI
7 Adel, M., Zaid, S., Mahgoub, O.: Improved active power filter performance based on an indirect current control technique. J Power Electr 11(6), 19 (2011)
8 Wang, Y., Xie, Y.-X.: Adaptive DC-link voltage control for shunt active power filter. J Power Electr 14(4), 764777 (2014)
9 Jayachandran, J., Sachithanandam, R.M.: ANN based controller for three phase four leg shunt active filter for power quality improvement. Ain Shams Eng J 7(1), 275-292 (2016)   DOI
10 Eskandarian, N., et al.: Improvement of dynamic behaviour of shunt active power filter using fuzzy instantaneous power theory. J Power Electr 14(6), 1303-1313 (2014)   DOI
11 S. R. Shahu, N. A.Wanjari.: Performance analysis of shunt active power filter with various switching signal generation techniques. Int. J. Eng. Dev. Res. 5(2) (2017)
12 Fallah, M., Modarresi, J., Kojabadi, H.M., Chang, L., Guerrero, J.M.: A modified indirect extraction method for a single-phase shunt active power filter with smaller DC-link capacitor size. Sustain Energy Technol Assess 45, 101039 (2021)
13 Ouchen, S., Steinhart, H., Benbouzid, M., Blaabjerg, F.: Robust DPC-SVM control strategy for shunt active power filter based on H∞ regulators. Electr Power Energy Syst 117, 105699 (2020)   DOI
14 Bhattacharya, B., Solomatine, D.P.: Neural networks and M5P model trees in modelling water level-discharge relationship. Neurocomputing 63, 381-396 (2005)   DOI
15 Du, X., Zhou, L., Lu, H., Tai, H.-M.: DC link active power filter for three-phase diode rectifier. IEEE Trans Ind Electron 59(3), 1430-1442 (2012)   DOI
16 Balasubramanian, R., Parkavikathirvelu, K., Sankaran, R., Amirtharajan, R.: Design, simulation and hardware implementation of shunt hybrid compensator using synchronous rotating reference frame (SRRF)-based control technique. Electr MDPI 8, 42 (2019)
17 Kazmierkowski, M.P.: Power quality problems and mitigation techniques. IEEE Ind Electr Mag 9(2), 62-62 (2015)   DOI
18 Andriy, S., Fu, C., Kayacan, E.: Intuit before tuning: Type-1 and type-2 fuzzy logic controllers. Appl Soft Comput 81, 105495 (2019)   DOI
19 Blaif, S., Moulahoum, S., Benkercha, R., Taghezouit, B., Saim, A.: M5P model tree based fast fuzzy maximum power point tracker. Sol. Energy 163, 405-424 (2018)   DOI
20 Buyuk, M., Inci, M., Tan, A., Tumay, M.: Improved instantaneous power theory based current harmonic extraction for unbalanced electrical grid conditions. Electr Power Syst Res 177, 106014 (2019)   DOI
21 Tamer, A., Zellouma, L., Benchouia, M.T., Krama, A.: Adaptive linear neuron control of three-phase shunt active power filter with anti-windup PI controller optimized by particle swarm optimization. Comput Electr Eng 96, 107471 (2021)   DOI
22 J.R. Quilan.: Learning with continous classes. In: Proc 5th of the Australian joint conference on artificial intelligence, Singapore, pp.343-348 (1999)
23 A Mohammed, S Rafq, P Sihag, R Kurda, W Mahmood, Kawan Ghafor, Warzer Sarwar (2020) ANN, M5P-tree and nonlinear regression approaches with statistical evaluations to predict the compressive strength of cement-based mortar modified with fly ash. Journal of Materials Research and Technology, Volume 9, Issue 6:12416-12427   DOI
24 Chan, P.P.K., Zheng, J., Liu, H., Tsang, E.C.C., Yeung, D.S.: Robustness analysis of classical and fuzzy decision trees under adversarial evasion attack. Appl Soft Comput 107, 107311 (2021)   DOI
25 M. Fiedler.: Performance analytics by means of the M5P machine learning algorithm. In: 31st International Teletrafc Congress (ITC 31), pp. 104-105 (2019)
26 Li, D., Wang, T., Pan, W., Ding, X., Gong, J.: A comprehensive review of improving power quality using active power filters. Electr Power Syst Res 199, 107389 (2021)   DOI
27 Benchouia, M.T., Ghadbane, I., Golea, A., Srairi, K., Benbouzid, M.E.H.: Implementation of adaptive fuzzy logic and PI controllers to regulate the DC bus voltage of shunt active power filter. Appl Soft Comput 28, 125-131 (2015)   DOI
28 Balouchi, B.: Mohammad Reza Nikoo, Jan Adamowski: Development of expert systems for the prediction of scour depth under live-bed conditions at river confluences: Application of different types of ANNs and the M5P model tree. Appl Soft Comput 34, 51-59 (2015)   DOI