Neural Network Based Fractional Order PID Controller for Harmonic Mitigation of Induction Motor Drive System

Year : 2023 | Volume : 01 | Issue : 01 | Page : 23-41
By

    Workagegn Tatek Asfu

  1. Solomon Feleke Aklilu

  2. Daniel Abebe Beyene

  1. Research Scholar, Department of Electrical and Computer Engineering, Debre Berhan University Debre, Berhan, Ethiopia
  2. Associate Professor, Department of Electrical and Computer Engineering, Debre Berhan University Debre, Berhan, Ethiopia
  3. Associate Professor, Department of Electrical and Computer Engineering, Debre Berhan University Debre, Berhan, Ethiopia

Abstract

Torque produced in IM (induction Motor) is collected fundamental torque, however, due to core saturation, air gap irregularity, and winding distribution; stator and rotor slotting harmonics torque are produced. This reduces the quality of the power system, life span, and performance of the motor and the controller device. In this paper, a neural network, based fractional order proportional integral derivative (NNFOPID) controller is designed to compensate the harmonics of the induction motor driving system. FOPID controller parameters have been tuned automatically based on the delta-learning rule with sigmoid activation function. The active shunt capacitor is directly connected to a five-level three-phase inverter directly controlled by sinusoidal pulse width modulation (SPWM). Based on the reference and measured harmonics error, the controller parameter of FOPID is tuned using NN (neural network) delta learning algorithm. The design of discrete type PI speed and current vector controller followed by space vector pulse width modulation (SVPWM) is designed to track the actual speed of IM to the reference speed. The IM modeling and power electronics driving the system within its harmonics effect was analyzed and discussed. In addition, the effect of current and voltage harmonics with different conditions is illustrated. For this NNFOPID controller parameter a tuning was designed, and MATLAB simulations check the system performance. The result shows that the current harmonic and voltage harmonic were reduced to 2.79%, 12.12%, respectively.

Keywords: Neural network, Fractional order PID, Vector control, five level three phase inverters, Harmonic mitigation

[This article belongs to International Journal of Electrical Power and Machine Systems(ijepms)]

How to cite this article: Workagegn Tatek Asfu, Solomon Feleke Aklilu, Daniel Abebe Beyene Neural Network Based Fractional Order PID Controller for Harmonic Mitigation of Induction Motor Drive System ijepms 2023; 01:23-41
How to cite this URL: Workagegn Tatek Asfu, Solomon Feleke Aklilu, Daniel Abebe Beyene Neural Network Based Fractional Order PID Controller for Harmonic Mitigation of Induction Motor Drive System ijepms 2023 {cited 2023 Oct 25};01:23-41. Available from: https://journals.stmjournals.com/ijepms/article=2023/view=130950

Browse Figures

References

Nandagopal, H. K. Ravi, and L. N. Chokkalingam, “Harmonics study of five phase induction machine with different winding approaches for traction,” in 2019 IEEE Transportation Electrification Conference (ITEC-India), IEEE, 2019, pp. 1–4.
Ranga and M. Mittal, “Harmonic reduction in induction motor using harmonic injection method and passive filter: A comparison,” in 2020 First IEEE International Conference on Measurement, Instrumentation, Control and Automation (ICMICA), IEEE, 2020, pp. 1–5.
A. K. A. Biabani and S. M. Ali, “Control of induction motor drive using space vector pwm,” in 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT), IEEE, 2016, pp. 3344–3351.
-H. Hsu, “Fractional order pid control for reduction of vibration and noise on induction motor,” IEEE Transactions on Magnetics, vol. 55, no. 11, pp. 1–7, 2019.
Bacˇa, D. Kouˇril, P. Palacky`, and J. Strossa, “Induction motor drive with field-oriented control and speed estimation using feedforward neural network,” in 2020 21st International Scientific Conference on Electric Power Engineering (EPE), IEEE, 2020, pp. 1–6.
T. Asfu, “Stator current-based model reference adaptive control for sensorless speed control of the induction motor,” Journal of control science and Engineering, vol. 2020, pp. 1–17, 2020.
Sengamalai, G. Anbazhagan, T. Thamizh Thentral, P. Vishnuram, T. Khurshaid, and S. Kamel, “Three phase induction motor drive: A systematic review on dynamic modeling, parameter estimation, and control schemes,” Energies, vol. 15, no. 21, p. 8260, 2022.
R. Sudharshana, V Muralidhara, A Ramachandran, and R Srinivasan, “Analysis of total harmonic distortion in 5-level inverter fed induction motor,” in 2018 International Conference on Computing, Power and Communication Technologies (GUCON), IEEE, 2018, pp. 800–804.
M Sujith and S Padma, “Optimization of harmonics with active power filter based on adaline neural network,” Microprocessors and Microsystems, vol. 73, p. 102 976, 2020.
S. Abdel-Khalik, S. Ahmed, and A. M. Massoud, “Steady-state mathematical modeling of a five-phase induction machine with a combined star/pentagon stator winding connection,” IEEE Transactions on Industrial Electronics, vol. 63, no. 3, pp. 1331–1343, 2015.
Krenicky, Y. Nikitin, and P. Bozˇek, “Model-based design of induction motor control system in matlab,” Applied Sciences, vol. 12, no. 23, p. 11 957, 2022.
Surasmi and G Shiny, “Harmonic mitigation in induction-motor drives using active filtering approach,” in 2020 IEEE International Power and Renewable Energy Conference, IEEE, 2020, pp. 1–6.
Ye, B. Wu, and N Zargari, “Modeling and simulation of induction motor with mechanical fault based on winding function method,” in 2000 26th Annual Conference of the IEEE Industrial Electronics Soci-ety. IECON 2000. 2000 IEEE International Conference on Industrial Electronics, Control and Instrumenta-tion. 21st Century Technologies, IEEE, vol. 4, 2000, pp. 2334–2339.
Qin, M. Liu, J. Zou, and X. Xin, “Vector control algorithm for electric vehicle ac induction motor based on improved variable gain pid controller,” mathematical problems in engineering, vol. 2015, 2015.
Djagarov, H. Milushev, M. Bonev, Z. Grozdev, and J. Djagarova, “Adaptive vector control of induction motor drives by optimal adaptive observer,” in 2020 7th International Conference on Energy Efficiency and Agricultural Engineering (EE&AE), IEEE, 2020, pp. 1– 5.
Ferdiansyah, L. P. S. Raharja, D. S. Yanaratri, and E. Purwanto, “Design of PID controllers for speed control of three phase induction motor based on direct- axis current (id) coordinate using ifoc,” in 2019 4th International Conference on Information Technology, Information Systems and Electrical Engineering (ICI- TISEE), IEEE, 2019, pp. 369–372.
L. Saleh, B. A. Obaid, and A. A. Obed, “Motion control of linear induction motor based on optimal recurrent wavelet neural network-pid controller,” Inter- national Journal of Engineering & Technology, vol. 7, no. 4, pp. 2028–2034, 2018.
Ferdiansyah, M. R. Rusli, B. Praharsena, H. Toar, E. Purwanto, et al., “Speed control of three phase induction motor using indirect field oriented control based on real-time control system,” in 2018 10th International Conference on Information Technology and Electrical Engineering (ICITEE), IEEE, 2018, pp. 438–442.
Amarapur, “Neural network based speed control of induction motor,” in 2013 Nirma University Interna- tional Conference on Engineering (NUiCONE), IEEE, 2013, pp. 1–6.
Liceaga-Castro, L. Amezquita-Brooks, and E. Liceaga-Castro, “Induction motor current controller for field oriented control using individual channel design,” in 2008 34th Annual Conference of IEEE Industrial Electronics, IEEE, 2008, pp. 235–240.
E. Venghi, F. Aguilera, P. M. de la Barrera, and C. H. De Angelo, “Design of discrete-time current controllers for induction motor drives based on an individual chan- nel analysis approach,” in 2019 Argentine Conference on Electronics (CAE), IEEE, 2019, pp. 70–75.
Rodr´ıguez-Abreo, J. Rodr´ıguez-Rese´ndiz, C. Fuentes-Silva, R. Herna´ndez-Alvarado, and M. D. C. P. T. Falco´n, “Self-tuning neural network pid with dynamic response control,” IEEE Access, vol. 9, pp. 65 206–65 215, 2021.


Regular Issue Subscription Original Research
Volume 01
Issue 01
Received September 19, 2023
Accepted October 10, 2023
Published October 25, 2023