Performance improvement of direct torque control system based on dynamic parameter identification technology

In traditional direct torque control system, the torque and flux are directly controlled by means of optimum voltage vectors, where the stator resistance variation deteriorates the dynamic performance. It is necessary to improve estimation accuracy for stator flux and torque. Considering the effects of the stator resistance variation on direct torque control, a novel approach of stator resistance identification based on wavelet network is presented for dynamic performance in low speed status, optimizing the inverter control strategy. The wavelet transform decomposes the signal using dilated and translated wavelets in time-frequency domain into a series of correlation factors or wavelet coefficients. The wavelet network combines the mathematical feature of wavelet transform with learning scheme of conventional neural network into an organic unit, which has been applied to nonlinear function approximation and dynamical system modeling. The improved training algorithm is utilized to fulfill the network parameter initialization, increasing the network stabilization and convergence property. Therefore, the stator voltage vector can be obtained from the stator resistance identification result of wavelet network output, reducing the number of voltage sensors. The simulation results show that the steady state and dynamic performance was improved.