caa a22 4500 606159835 CHVBK 20210128100626.0 cr unu---uuuuu 210128e20150501xx s 000 0 eng 10.1007/s00521-014-1759-x doi (NATIONALLICENCE)springer-10.1007/s00521-014-1759-x Squirrel-cage induction generator system using hybrid wavelet fuzzy neural network control for wind power applications [Elektronische Daten] [Faa-Jeng Lin, Kuang-Hsiung Tan, Dun-Yi Fang] 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. The Natural Computing Applications Forum, 2014 Intelligent hybrid control nationallicence Wavelet fuzzy neural network nationallicence Indirect field-oriented mechanism nationallicence Squirrel-cage induction generator nationallicence Projection algorithm nationallicence $$T_{e}$$ T e : Electromagnetic torque nationallicence $$P_{M}$$ P M : Pole number nationallicence $$L_{m}$$ L m : Mutual inductance nationallicence $$L_{r}$$ L r : Rotor inductance nationallicence $$i_{qs}$$ i q s : q-axis stator current nationallicence $$\theta_{m}$$ θ m : Mechanical angular position of rotor nationallicence $$\omega_{m}$$ ω m : Mechanical angular speed of rotor nationallicence $$\theta_{r}$$ θ r : Angular position of rotor nationallicence $$\omega_{r}$$ ω r : Angular speed of rotor nationallicence $$\theta_{e}$$ θ e : Electric angular angle nationallicence $$\theta_{e}^{{\prime }}$$ θ e ′ : Synchronous angle nationallicence $$i_{qs}^{*}$$ i q s ∗ : Torque control current nationallicence $$i_{ds}^{*}$$ i d s ∗ : Flux control current nationallicence $$\omega_{sl}$$ ω s l : Slip speed nationallicence $$T_{r}$$ T r : Time-constant of the rotor nationallicence $$i_{a}^{*} , \, i_{b}^{*} , \, i_{c}^{*}$$ i a ∗ , i b ∗ , i c ∗ : Three-phase current commands nationallicence $$T_{a}^{{}} , \, T_{b}^{{}} \, ,T_{c}^{{}}$$ T a , T b , T c : PWM signals of converter nationallicence $$i_{a}^{{}} , \, i_{b}^{{}} , \, i_{c}^{{}}$$ i a , i b , i c : Three-phase currents of SCIG nationallicence $$i_{dc}$$ i d c : DC-link current nationallicence $$V_{dc}^{*2}$$ V d c ∗ 2 : Square of DC-link voltage command nationallicence $$V_{dc}^{2}$$ V d c 2 : Square of DC-link voltage nationallicence $$i_{ds}^{{{\prime }*}}$$ i d s ′ ∗ : Active power control current nationallicence $$i_{qs}^{{{\prime }*}}$$ i q s ′ ∗ : Reactive power control current nationallicence $$i_{u}^{*} , \, i_{v}^{*} , \, i_{w}^{*}$$ i u ∗ , i v ∗ , i w ∗ : Three-phase current commands of DC/AC power inverter nationallicence $$T_{a}^{{\prime }} , \, T_{b}^{{\prime }} ,T_{c}^{{\prime }}$$ T a ′ , T b ′ , T c ′ : PWM signals of inverter nationallicence $$i_{u}^{{\prime }} , \, i_{v}^{{\prime }} , \, i_{w}^{{\prime }}$$ i u ′ , i v ′ , i w ′ : Three-phase currents of inverter nationallicence $$i_{u}^{{}} , \, i_{v}^{{}} , \, i_{w}$$ i u , i v , i w : Three-phase currents nationallicence $$V_{u}^{{}} , \, V_{v}^{{}} , \, V_{w}$$ V u , V v , V w : Three-phase voltages nationallicence $$P_{{}}^{*}$$ P ∗ : Active power command of inverter nationallicence $$Q_{{}}^{*}$$ Q ∗ : Reactive power command of inverter nationallicence $$P$$ P : Active power of inverter nationallicence $$Q$$ Q : Reactive power of inverter nationallicence $$R_{m}$$ R m : Turbine rotor radius nationallicence $$\lambda$$ λ : Tip ratio nationallicence ρ : Density nationallicence A : Exposed area nationallicence $$\eta_{m}$$ η m : Mechanical transmission efficiency nationallicence $$\eta_{g}$$ η g : Power efficiency of SCIG system nationallicence $$T_{m}$$ T m : Mechanical torque of the prime mover nationallicence J : Inertia of prime mover and SCIG nationallicence B : Damping coefficient of prime mover and SCIG nationallicence C : Capacitor and the voltage of DC-link nationallicence $$V_{dc} (t)$$ V d c ( t ) : Voltage of DC-link nationallicence K 1, K 2 : Constants nationallicence A n : Nominal value of A nationallicence $$B_{n} (t)$$ B n ( t ) : Nominal value of B(t) nationallicence $$C_{n} (t)$$ C n ( t ) : Nominal value of C(t) nationallicence $$D_{n} (t)$$ D n ( t ) : Nominal value of D(t) nationallicence ∆ A ( t ) : Uncertainty nationallicence ∆ B ( t ) : Uncertainty nationallicence ∆ C ( t ) : Uncertainty nationallicence ∆ D ( t ) : Uncertainty nationallicence W ( t ) : Lumped uncertainty nationallicence $$U_{A} (t)$$ U A ( t ) : Computed torque controller nationallicence $$U_{C} (t)$$ U C ( t ) : Compensated controller nationallicence k 1, k 2 : Nonzero positive constants nationallicence Γ : Collections of adjustable parameters of WFNN nationallicence N : Nth iteration nationallicence n : Total number of linguistic variables nationallicence σ j : Standard deviation of Gaussian function nationallicence m j : Mean of Gaussian function nationallicence $$w_{jk}^{3}$$ w j k 3 : Connective weight between rule layer and membership layer nationallicence $$\,y_{j}^{2}$$ y j 2 : jth input to node of layer 3 nationallicence $$\phi_{ik}$$ ϕ i k : ith in kth term wavelet output nationallicence $$w_{ik}^{4}$$ w i k 4 : Wavelet weight in WF k layer nationallicence $$\psi_{k}$$ ψ k : kth term WF k output to node of wavelet layer nationallicence $$y_{l}^{4}$$ y l 4 : lth input to node of layer 5 nationallicence $$w_{l}^{5}$$ w l 5 : Connective weight between output layer and wavelet layer nationallicence $$\varGamma^{*}$$ Γ ∗ : Optimal weight vector nationallicence $$\eta_{{{w}1}} ,\eta_{{{w}2}}$$ η w 1 , η w 2 : Learning rates of connective weights nationallicence $$\eta_{\sigma } ,\eta_{m}$$ η σ , η m : Learning rates of standard deviations and means nationallicence $$\it M_{{b}}$$ M b : Upper bound of $${\mathbf{w}}^{{\mathbf{5}}}$$ w 5 nationallicence $${\kern 1pt} \left\| \cdot \right\|$$ · : Two-norm of vector nationallicence $$\text{sgn} ( \cdot )$$ sgn ( · ) : Sign function nationallicence η : Positive constant nationallicence P : Symmetric positive definite matrix nationallicence Lin Faa-Jeng Department of Electrical Engineering, National Central University, 320, Chungli, Taiwan aut Tan Kuang-Hsiung Department of Electrical and Electronic Engineering, Chung Cheng Institute of Technology, National Defense University, 335, Taoyuan, Taiwan aut Fang Dun-Yi Department of Electrical Engineering, National Central University, 320, Chungli, Taiwan aut Neural Computing and Applications Springer London 26/4(2015-05-01), 911-928 0941-0643 26:4<911 2015 26 521 https://doi.org/10.1007/s00521-014-1759-x text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00521-014-1759-x text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Lin Faa-Jeng Department of Electrical Engineering, National Central University, 320, Chungli, Taiwan aut NATIONALLICENCE 700 1- Tan Kuang-Hsiung Department of Electrical and Electronic Engineering, Chung Cheng Institute of Technology, National Defense University, 335, Taoyuan, Taiwan aut NATIONALLICENCE 700 1- Fang Dun-Yi Department of Electrical Engineering, National Central University, 320, Chungli, Taiwan aut NATIONALLICENCE 773 0- Neural Computing and Applications Springer London 26/4(2015-05-01), 911-928 0941-0643 26:4<911 2015 26 521