Abstract
FCSMPC is a classical converter predictive control algorithm whose control performance is affected by the prediction error of the prediction model. In classical predictive control theory, the feedback correction mechanism is used to compensate for such prediction error. However, when this strategy is directly applied to the FCSMPC algorithm, the prediction error cannot be easily calculated. To address the prediction error compensation problem of FCSMPC, this paper proposes a prediction error compensation method based on neural network. A neural network prediction model is also constructed based on the timing characteristics of prediction error signals. The prediction error of this prediction model at the next moment is calculated by the designed neural network model, and then the output of the prediction model is compensated at the current moment. To improve the anti-interference performance of FCSMPC, the MRSVD algorithm is used to filter the prediction error sample data and the neural networks are trained by these sample data. The adaptability of the prediction error calculation is further improved by combining offline training with the online calculation of the neural network. A simulation model of the proposed method is then constructed using MATLAB, and simulation results show that the control performance of the FCSMPC algorithm is improved and that the effectiveness and feasibility of the proposed method are verified.
Similar content being viewed by others
Data availability
The data supporting this study’s findings are available from the corresponding author upon reasonable request.
Abbreviations
- X :
-
Controlled quantity
- S :
-
Switching function combination
- f p :
-
Prediction model of three-phase inverter
- x p :
-
Prediction value of controlled quantity
- f g :
-
Cost function of system
- x*:
-
Reference value of controlled quantity
- A :
-
System matrix
- B :
-
Input matrix
- B d :
-
Disturbance input matrix
- T S :
-
Sampling cycle
- L :
-
Filter inductor
- C :
-
Filter capacitor
- r :
-
Filter equivalent resistance
- v s :
-
Output voltage of the IGBT bridge
- i s :
-
Inductor current of three-phase inverter
- v o :
-
Output voltage of three-phase inverter
- i o :
-
Load current of three-phase inverter
- v op :
-
Predicted value of vo
- λ c :
-
Prediction error correction factor for factor first-step prediction calculation
- v o * :
-
Reference value of output voltage
- v copi :
-
Second-step prediction value corresponding to the ith switching function combination
- v cop :
-
Prediction value after correction
- Δvop :
-
Value of prediction error
- A :
-
Hankel matrix
- D :
-
Diagonal matrix
- FCSMPC:
-
Finite control set model predictive control
- BP:
-
Back propagation
- 2L-VSI:
-
Two-level three-phase voltage source inverter
- MRSVD:
-
Multi-resolution singular value decomposition
- RMSE:
-
Root mean square error
- THD:
-
Total harmonic distortion
References
Yang, Y., Wen, H., Fan, M.D., Zhang, X.N., He, L.Q., Chen, R., **e, M.X., Norambuena, M., Rodriguez, J.: Low complexity finite-control-set MPC based on discrete space vector modulation for T-type three-phase three-level converters. IEEE Trans. Power Electron. 37(1), 392–403 (2022)
Wang, L., Wang, X.: Finite-control-set model predictive control for eight-switch three-phase NPC converters. IEEJ Trans. Electr. Electron. Eng. 14(1), 105–115 (2019)
HanJ, LiuL., YaoG, TangT.: Finite-control-set model predictive control for asymmetrical cascaded H-bridge multilevel grid-connected inverter with flying capacitor. IEEJ Trans. Electr. Electron. Eng. 16(10), 1328–1335 (2021)
Wang, H., Zhang, H.: Study on an improve finite-control-set-model predictive control (FCS-MPC) strategy for a T-type rectifier with direct power control strategy. IEEJ Trans. Electr. Electron. Eng. 18(3), 442–450 (2023)
Liu, J., Ge, Z.Y., Wu, X., Wu, G.P., **ao, S.P., Huang, K.Y.: Predictive current control of permanent magnet synchronous motor based on duty-cycle modulation. Proc. CSEE. 40(10), 3319–3327 (2020)
Vafaie, M.H., Dehkordi, B.M., Moallem, P., Kiyoumarsi, A.: improving the steady-state and transient-state performances of PMSM through an advanced deadbeat direct torque and flux control system. IEEE Trans. Power Electron. 32(4), 2964–2975 (2017)
Yan, N., Cao, X., Zhang, L., Deng, Z.Q.: Direct torque control-based model predictive control of switched reluctance motors. Proc. CSEE. 37(18), 5446–5453 (2017)
Vazquez, S., Marino, D., Zafra, E., Peña, M.D.V., Rodriguez-Andina, J.J., Franquelo, L.G., Manic, M.: An artificial intelligence approach for real-time tuning of weighting factors in FCS-MPC for power converters. IEEE Trans. Ind. Electron. 69(12), 11987–11998 (2022)
Babaie, M., Mehrasa, M., Sharifzadeh, M., Al-Haddad, K.: Floating weighting factors ANN-MPC based on lyapunov stability for seven-level modified PUC active rectifier. IEEE Trans. Ind. Electron. 69(1), 387–398 (2021)
Novak, M., **e, H.T., Dragicevic, T., Wang, F.X., Rodriguez, J., Blaabjerg, F.: Optimal cost function parameter design in predictive torque control (PTC) using artificial neural networks (ANN). IEEE Trans. Ind. Electron. 68(8), 7309–7319 (2020)
Dragicevic, T., Novak, M.: Weighting factor design in model predictive control of power electronic converters: an artificial neural network approach. IEEE Trans. Ind. Electron. 66(11), 8870–8880 (2018)
Karamanakos, P., Geyer, T., Aguilera, R.P.: Long-horizon direct model predictive control: modified sphere decoding for transient operation. IEEE Trans. Ind. Appl. 54(6), 6060–6070 (2018)
**e, H.T., Wang, F.X., Xun, Q., He, Y.J., Rodriguez, J., Kennel, R.M.: A low-complexity gradient descent solution with backtracking iteration approach for finite control set predictive current control. IEEE Trans. Ind. Electron. 69(5), 4522–4533 (2022)
Dorfling, T., Mouton, H., Geyer, T., Karamanakos, P.: Long-Horizon finite-control-set model predictive control with nonrecursive sphere decoding on an FPGA. IEEE Trans. Power Electron. 35(7), 7520–7531 (2020)
Shen, K., Feng, J.H., Zhang, J.: Finite control set model predictive control with feedback correction for power converters. CES Trans. Electr. Mach. Syst. 2(3), 312–319 (2018)
Qiang, Y.Z., Yan, Y., Chen, W., Geng, Q.: Three-vector model predictive current control strategy for permanent magnet synchronous motor drives with parameter error compensation. Trans. China Electrotech. Soc. 35(2), 255–265 (2020)
Yao, X.L., Ma, C.W., Wang, J.F., Huang, S.Q.: Robust model predictive current control for PMSM based on prediction error compensation. Proc. CSEE. 41(17), 6071–6080 (2021)
Hong, J.F., Zhang, X., Cao, R.X., Xu, C.J.: Improved finite control set model predictive control of three-level grid-connected inverter. Acta Energiae Solaris Sinica. 43(8), 67–74 (2022)
Heydari, R., Young, H., Rafiee, Z., Flores-Bahamonde, F., Savaghebi, M., Rodriguez, J.: Model-free predictive current control of a voltage source inverter based on identification algorithm. IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society, IEEE, pp. 3065–3070 (2020)
Shen, K., Zhang, J.: Model predictive control scheme with modeling error compensation for three-phase inverter. Electr. Power Autom. Equip. 33(7), 86–91 (2013)
Zhao, S., Blaabjerg, F., Wang, H.: An overview of artificial intelligence applications for power electronics. IEEE Trans. Power Electron. 36(4), 4633–4658 (2020)
Alquennah, A.N, Trabelsi, M., Krama, A., Vahedi, H., Mohamed-Seghir, M.: ANN based auto-tuned optimized FCS-MPC for grid-connected CSC inverter. 2022 3rd International Conference on Smart Grid and Renewable Energy (SGRE), IEEE, pp. 1–6. (2020)
Acknowledgements
This work is supported by the Scientific Research Fund of the Hunan Provincial Education Department of China, No.23B0098.
Funding
This article is supported by Scientific Research Fund of Hunan Provincial Education Department of China, 23B0098, Kun Shen.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Appendices
Appendix A
Figure 1 shows a three-phase inverter with an output LC filter. The converter and filter models are presented in this section, and the load is assumed to be unknown.
The switching states of the converter are determined by the gating signals Sa, Sb, and Sc as follows:
The switching function combination S can be expressed in vectorial form as
where the operator is α = exp(2πj/3).
The output–voltage space vectors generated by the inverter are defined as
where va, vb, and vc are the phase voltages of the inverter with respect to the negative terminal of the DC-link. The voltage vector vi can be related to the switching state vector S by
where Vdc is the DC-link voltage.
By considering all possible combinations of the gating signals Sa, Sb, and Sc, eight switching states and eight voltage vectors vi(i = 0, 1, …, 7) are obtained. Note that v0 = v7, thereby resulting in only seven voltage vectors.
The inverter can be modeled as a continuous system by using modulation techniques, such as pulse-width modulation. Nevertheless, in this article, the inverter is considered a non-linear discrete system with only seven voltage vectors as possible outputs.
By using vectorial notation, the filter current is, output voltage vc, and output current io can be expressed as space vectors and defined as
The LC filter can be described by using two equations, with the first equation describing the inductance dynamics and the second equation describing the capacitor dynamics.
The filter inductance expressed in vectorial form is
where L is the filter inductance.
The dynamic behavior of the output voltage can be expressed as
where C is the filter capacitance.
The above equations can be rewritten as the following state-space system:
where \(x(k) = \left[ \begin{gathered} i_{s} (k) \hfill \\ v_{o} (k) \hfill \\ \end{gathered} \right]\) represents the state quantities, \(A = \left[ {\begin{array}{*{20}c} { - r/L} & { - 1/L} \\ {1/C} & 0 \\ \end{array} } \right]\) is the system matrix, B = [1/L 0]T is the input matrix, and Bd = [0 − 1/C]T is the disturbance input matrix.
Variables is and vc are measured, vi can be calculated using Eq. (14), and io is considered an unknown disturbance. The value of Vdc is assumed to be fixed and known.
The output of the system is the output voltage vc, which is written as the following state equation:
A discrete-time model of the filter is obtained from Eq. (20) for a sampling time Ts and is expressed as
where \(A_{{\text{q}}} = e^{{{\text{AT}}_{{\text{s}}} }} ,B_{q} = \int\limits_{0}^{{T_{{\text{s}}} }} {e^{A\tau } Bd\tau }\), \(B_{{{\text{dq}}}} = \int\limits_{0}^{{{\text{T}}_{{\text{s}}} }} {e^{A\tau } B_{{\text{d}}} d\tau }\),
The above equations are used as predictive models in the proposed predictive controller.
Appendix B
Parameters of inverter: vdc = 520 V; Lf = 2.4 mH; rf = 0.05 Ω; Cf = 40 μF; and Ts = 40 us.
Parameters of load: three-phase resistive-inductive load with active power P = 15 kW and reactive power Q = 2 kvar.
Parameters of inverter: Ts = 40 us; λc = 0.7; and vo* is the three-phase AC voltage with a frequency of 50 Hz and amplitude of 200 V.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Shen, K., Chen, H., Zhang, M. et al. Prediction error compensation method of FCSMPC for converter based on neural network. J. Power Electron. (2024). https://doi.org/10.1007/s43236-024-00862-w
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s43236-024-00862-w