Abstract
An intelligent controlled three-phase squirrel-cage induction generator (SCIG) system for grid-connected wind power applications using hybrid wavelet fuzzy neural network (WFNN) is proposed in this study. First, the indirect field-oriented mechanism is implemented for the control of the SCIG system. Then, an AC/DC power converter and a DC/AC power inverter are developed to convert the electric power generated by a three-phase SCIG to power grid. Moreover, the dynamic model of the SCIG system and an ideal computed torque controller are developed for the control of the square of DC-link voltage. Furthermore, an intelligent hybrid WFNN controller and two WFNN controllers, which are computation intensive approaches, are proposed for the AC/DC power converter and the DC/AC power inverter, respectively, to improve the transient and steady-state responses of the SCIG system at different operating conditions. In the intelligent hybrid WFNN controller, to relax the requirement of the lumped uncertainty in the design of the ideal computed torque controller, a WFNN is designed as an uncertainty observer to adapt the lumped uncertainty online. Finally, the feasibility and effectiveness of the SCIG system for grid-connected wind power applications are verified with experimental results.
Similar content being viewed by others
Abbreviations
- \(T_{e}\) :
-
Electromagnetic torque
- \(P_{M}\) :
-
Pole number
- \(L_{m}\) :
-
Mutual inductance
- \(L_{r}\) :
-
Rotor inductance
- \(i_{qs}\) :
-
q-axis stator current
- \(\theta_{m}\) :
-
Mechanical angular position of rotor
- \(\omega_{m}\) :
-
Mechanical angular speed of rotor
- \(\theta_{r}\) :
-
Angular position of rotor
- \(\omega_{r}\) :
-
Angular speed of rotor
- \(\theta_{e}\) :
-
Electric angular angle
- \(\theta_{e}^{{\prime }}\) :
-
Synchronous angle
- \(i_{qs}^{*}\) :
-
Torque control current
- \(i_{ds}^{*}\) :
-
Flux control current
- \(\omega_{sl}\) :
-
Slip speed
- \(T_{r}\) :
-
Time-constant of the rotor
- \(i_{a}^{*} , \, i_{b}^{*} , \, i_{c}^{*}\) :
-
Three-phase current commands
- \(T_{a}^{{}} , \, T_{b}^{{}} \, ,T_{c}^{{}}\) :
-
PWM signals of converter
- \(i_{a}^{{}} , \, i_{b}^{{}} , \, i_{c}^{{}}\) :
-
Three-phase currents of SCIG
- \(i_{dc}\) :
-
DC-link current
- \(V_{dc}^{*2}\) :
-
Square of DC-link voltage command
- \(V_{dc}^{2}\) :
-
Square of DC-link voltage
- \(i_{ds}^{{{\prime }*}}\) :
-
Active power control current
- \(i_{qs}^{{{\prime }*}}\) :
-
Reactive power control current
- \(i_{u}^{*} , \, i_{v}^{*} , \, i_{w}^{*}\) :
-
Three-phase current commands of DC/AC power inverter
- \(T_{a}^{{\prime }} , \, T_{b}^{{\prime }} ,T_{c}^{{\prime }}\) :
-
PWM signals of inverter
- \(i_{u}^{{\prime }} , \, i_{v}^{{\prime }} , \, i_{w}^{{\prime }}\) :
-
Three-phase currents of inverter
- \(i_{u}^{{}} , \, i_{v}^{{}} , \, i_{w}\) :
-
Three-phase currents
- \(V_{u}^{{}} , \, V_{v}^{{}} , \, V_{w}\) :
-
Three-phase voltages
- \(P_{{}}^{*}\) :
-
Active power command of inverter
- \(Q_{{}}^{*}\) :
-
Reactive power command of inverter
- \(P\) :
-
Active power of inverter
- \(Q\) :
-
Reactive power of inverter
- \(R_{m}\) :
-
Turbine rotor radius
- \(\lambda\) :
-
Tip ratio
- ρ :
-
Density
- A :
-
Exposed area
- \(\eta_{m}\) :
-
Mechanical transmission efficiency
- \(\eta_{g}\) :
-
Power efficiency of SCIG system
- \(T_{m}\) :
-
Mechanical torque of the prime mover
- J :
-
Inertia of prime mover and SCIG
- B :
-
Damping coefficient of prime mover and SCIG
- C :
-
Capacitor and the voltage of DC-link
- \(V_{dc} (t)\) :
-
Voltage of DC-link
- K 1, K 2 :
-
Constants
- A n :
-
Nominal value of A
- \(B_{n} (t)\) :
-
Nominal value of B(t)
- \(C_{n} (t)\) :
-
Nominal value of C(t)
- \(D_{n} (t)\) :
-
Nominal value of D(t)
- ∆A(t):
-
Uncertainty
- ∆B(t):
-
Uncertainty
- ∆C(t):
-
Uncertainty
- ∆D(t):
-
Uncertainty
- W(t):
-
Lumped uncertainty
- \(U_{A} (t)\) :
-
Computed torque controller
- \(U_{C} (t)\) :
-
Compensated controller
- k 1, k 2 :
-
Nonzero positive constants
- Γ :
-
Collections of adjustable parameters of WFNN
- N :
-
Nth iteration
- n :
-
Total number of linguistic variables
- σ j :
-
Standard deviation of Gaussian function
- m j :
-
Mean of Gaussian function
- \(w_{jk}^{3}\) :
-
Connective weight between rule layer and membership layer
- \(\,y_{j}^{2}\) :
-
jth input to node of layer 3
- \(\phi_{ik}\) :
-
ith in kth term wavelet output
- \(w_{ik}^{4}\) :
-
Wavelet weight in WF k layer
- \(\psi_{k}\) :
-
kth term WF k output to node of wavelet layer
- \(y_{l}^{4}\) :
-
lth input to node of layer 5
- \(w_{l}^{5}\) :
-
Connective weight between output layer and wavelet layer
- \(\varGamma^{*}\) :
-
Optimal weight vector
- \(\eta_{{{w}1}} ,\eta_{{{w}2}}\) :
-
Learning rates of connective weights
- \(\eta_{\sigma } ,\eta_{m}\) :
-
Learning rates of standard deviations and means
- \(\it M_{{b}}\) :
-
Upper bound of \({\mathbf{w}}^{{\mathbf{5}}}\)
- \({\kern 1pt} \left\| \cdot \right\|\) :
-
Two-norm of vector
- \(\text{sgn} ( \cdot )\) :
-
Sign function
- η :
-
Positive constant
- P :
-
Symmetric positive definite matrix
References
Xu Z, Hu Q, Ehsani M (2012) Estimation of effective wind speed for fixed-speed wind turbines based on frequency domain data fusion. IEEE Trans Sustain Energy 3(1):57–64
Global Wind Energy Council (2012) Global wind report 2011. http://www.gwec.net/publications/global-wind-report-2/global-wind-report-2010-2/. Accessed March 2012
Pao LY, Johnson KE (2011) Control of wind turbines. IEEE Power Control Syst Mag 31(2):44–62
Al-Bahadly I (2011) Wind turbine. InTech, Croatia
Tazil M, Kumar V, Bansal RC, Kong S, Dong ZY (2010) Three-phase doubly fed induction generators: an overview. IET Electr Power Appl 4(2):75–89
Muller S, Deicke M, De Doncker RW (2002) Doubly fed induction generator systems for wind turbines. IEEE Ind Appl Mag 8(3):26–33
Cheng Z, Guerrero JM, Blaabjerg F (2009) A review of the state of the art of power electronics for wind turbines. IEEE Trans Power Electron 24(8):1859–1875
Yang Y, Chen Y, Jia Z, Liqiao W, Wu W (2010) Development of 22 kW experimental platform for wind power generation system using SCIG. In: Proceedings of 2010 IEEE international symposium on power electronics for distributed generation systems, Hefei, 16–18 June 2010, pp 593–596
Goel PK, Singh B, Murthy SS, Kishore N (2011) Isolated wind–hydro hybrid system using cage generators and battery storage. IEEE Trans Ind Electron 58(4):1141–1153
Ahmed T, Nishida K, Nakaoka M (2007) A novel stand-alone induction generator system for AC and DC power applications. IEEE Trans Ind Appl 43(6):1465–1474
Yazdani A, Dash PP (2009) A control methodology and characterization of dynamics for a photovoltaic (PV) system interfaced with a distribution network. IEEE Trans Power Deliv 24(3):1538–1551
Lin FJ, Huang MS, Yeh PY, Tsai HC, Kuan CH (2012) DSP-based probabilistic fuzzy neural network control for Li-Ion battery charger. IEEE Trans Power Electron 27(8):3782–3794
Lin FJ, Shieh HJ, Huang PK, Teng LT (2006) Adaptive control with hysteresis estimation and compensation using RFNN for piezo-actuator. IEEE Trans Ultrason Ferroelectr Freq Control 53(9):1649–1661
Lin WM, Hong CM (2011) A new Elman neural network-based control algorithm for adjustable-pitch variable-speed wind-energy conversion systems. IEEE Trans Power Electron 26(2):473–481
Lin WM, Hong CM, Chen CH (2011) Neural-network-based MPPT control of a stand-alone hybrid power generation system. IEEE Trans Power Electron 26(12):3571–3581
Song Y, Gao L (2011) Incremental battery model using wavelet-based neural networks. IEEE Trans Compon Pack Manuf Technol 1(7):1075–1081
Pan H, Xia LZ (2008) Efficient object recognition using boundary representation and wavelet neural network. IEEE Trans Neural Netw 19(12):2132–2149
Teng LT, Lin FJ, Chiang HC, Lin JW (2009) Recurrent wavelet neural network controller with improved particle swarm optimisation for induction generator system. IET Electr Power Appl 3(2):147–159
Lin FJ, Tan KH, Chiu JH (2012) Active islanding detection method using wavelet fuzzy neural network. In: Proceedings of 2012 IEEE international conference on fuzzy systems, Brisbane, 10–15 June 2012, pp 1–8
Bhaskar K, Singh SN (2012) AWNN-assisted wind power forecasting using feed-forward neural network. IEEE Trans Sustain Energy 3(2):306–315
Yilmaz AS, Özer Z (2009) Pitch angle control in wind turbines above the rated wind speed by multi-layer perceptron and radial basis function neural networks. Expert Syst Appl 36(6):9767–9775
Duong MQ, Grimaccia F, Leva S, Mussetta M, Ogliari E (2014) Pitch angle control using hybrid controller for all operating regions of SCIG wind turbine system. Renew Energy 70:197–203
Timbus A, Teodorescu R, Blaabjerg F, Liserre M (2005) Synchronization methods for three phase distributed power generation systems - an overview and evaluation. In: Proceedings of IEEE 36th power electronics specialists conference, Recife, 16 June 2005, pp 2474–2481
Blaabjerg F, Teodorescu R, Liserre M, Timbus AV (2006) Overview of control and grid synchronization for distributed power generation systems. IEEE Trans Ind Electron 53(5):1398–1409
Lin FJ, Hung YC, Tsai MT (2013) Fault-tolerant control for six-phase PMSM drive system via intelligent complementary sliding-mode control using TSKFNN-AMF. IEEE Trans Ind Electron 60(12):2157–2169
Lin FJ, Teng LT, Shieh PH, Li YF (2006) Intelligent controlled wind turbine emulator and induction generator system using RBFN. IET Electr Power Appl 153(4):608–618
Lin FJ, Teng LT, Yu MH (2008) Radial basis function network control with improved particle swarm optimization for induction generator system. IEEE Trans Power Electron 23(4):2157–2169
Teodorescu R, Blaabjerg F (2004) Flexible control of small wind turbines with grid failure detection operating in stand-alone and grid-connected mode. IEEE Trans Power Electron 19(5):1323–1332
Lin FJ, Wai RJ, Hong CM (2001) Hybrid supervisory control using recurrent fuzzy neural network for tracking periodic inputs. IEEE Trans Neural Netw 12(1):68–90
Acknowledgments
The author would like to acknowledge the financial support of Institute of Nuclear Energy Research of Taiwan, R.O.C. through its Grant 1012001INER046.
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
Theorem 1
Considering the SCIG system represented by (16), if the hybrid WFNN control law is designed in (20), in which the computed torque control law is designed in (24), the adaptation law of the WFNN is designed in (43), and the compensated control is designed in (44), then the asymptotical stability of the control system is guaranteed.
Proof
A Lyapunov function is defined as
where \({\mathbf{P}}\) satisfies the following Lyapunov equation:
and \({\mathbf{Q}} > 0\) is selected by the designer. Take the derivative of the Lyapunov function and use (31), (32) and (46), then
To satisfy \(V^{{\prime }} (t) \le 0\), the update law \(({\mathbf{w}}^{{\mathbf{5}}} )^{{\prime }}\) and the compensated controller \(U_{{C}} (t)\) are designed as (43) and (44). Substitute (43) into (47) and use (44), then
Since \(V^{{\prime }} (t) \le 0\), \(V^{{\prime }} (t)\) is negative semidefinite (i.e. \(V(t) \le V(0)\)), which implies \({\kern 1pt} {\mathbf{E}}\) and \({\mathbf{[w}}^{{{\mathbf{5}}*}} - {\mathbf{w}}^{{\mathbf{5}}} {\mathbf{]}}^{{\mathbf{T}}}\) are bounded. Define function \(\Theta (t) = \frac{1}{2}{\mathbf{E}}^{{\mathbf{T}}} {\mathbf{QE}} \le - V^{\prime}(t)\), and integrate function \(\Theta (t)\) with respect to time
Because \(V(0)\) is bounded, and \(V(t)\) is nonincreasing and bounded, then
Differentiate with respect to time
Since all the variables in the right-hand side of (32) are bounded, it implies \({\mathbf{E}}^{{\prime }}\) is also bounded. Then, \(\Theta^{{\prime }} (t)\) is uniformly continuous. By using the Barbalat’s lemma, it can be shown that \(\mathop {\lim }\limits_{t \to \infty } \Theta (t) = 0\). Thus, \({\kern 1pt} {\mathbf{E}} \to 0\) as \(t \to \infty\). As a result, the hybrid WFNN control system is asymptotically stable.
Theorem 2
Considering the SCIG system shown in (16 ), if the hybrid WFNN control law is designed in (20), in which the computed torque control law is designed in (24), the adaptation law of the WFNN is designed in (42), and the compensated control is designed in (44), then the asymptotical stability of the control system is guaranteed.
Proof
When the condition \(\left\| {{\mathbf{w}}^{{\mathbf{5}}} } \right\| \le M_{{b}}\) or \(\left( {\left\| {{\mathbf{w}}^{{\mathbf{5}}} } \right\| = M_{{b}} \,{\text{and}}\,{\kern 1pt} {\mathbf{E}}^{{\mathbf{T}}} {\mathbf{PB}}_{{\mathbf{P}}} {\mathbf{w}}^{{{\mathbf{5}}{\text{T}}}} {\mathbf{y}}^{{\mathbf{4}}} \le 0} \right)\) holds, the stability analysis is the same as Theorem 1. On the other hand, when \(\left\| {{\mathbf{w}}^{{\mathbf{5}}} } \right\| = M_{{b}} {\kern 1pt}\) and \({\mathbf{E}}^{{\mathbf{T}}} {\mathbf{PB}}_{{\mathbf{P}}} {\mathbf{w}}^{{{\mathbf{5T}}}} {\mathbf{y}}^{{\mathbf{4}}} > 0\), the derivative of the Lyapunov function shown in (47) can be redescribed as follows:
Using the characteristic \({\mathbf{[w}}^{{{\mathbf{5*}}}} - {\mathbf{w}}^{{\mathbf{5}}} {\mathbf{]}}^{{\mathbf{T}}} {\mathbf{w}}^{{\mathbf{5}}} = \frac{1}{2}\left( {\left\| {{\mathbf{w}}^{{{\mathbf{5*}}}} } \right\|^{2} - \left\| {{\mathbf{w}}^{{\mathbf{5}}} } \right\|^{2} - \left\| {{\mathbf{w}}^{{{\mathbf{5*}}}} - {\mathbf{w}}^{{\mathbf{5}}} } \right\|^{2} } \right) < 0\), which is based on \(\left\| {{\mathbf{w}}^{{\mathbf{5}}} } \right\| = M_{{b}} > {\kern 1pt} {\kern 1pt} \left\| {{\mathbf{w}}^{{{\mathbf{5}}*}} } \right\|\), then
By using Barbalat’s lemma as shown in Theorem 1, \({\kern 1pt} {\mathbf{E}} \to 0\) as \(t \to \infty\). Therefore, the stability property also can be guaranteed.
Rights and permissions
About this article
Cite this article
Lin, FJ., Tan, KH. & Fang, DY. Squirrel-cage induction generator system using hybrid wavelet fuzzy neural network control for wind power applications. Neural Comput & Applic 26, 911–928 (2015). https://doi.org/10.1007/s00521-014-1759-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-014-1759-x