Digital Exchange Of Intelligent Motor Control Systems

This paper investigates the induction motor full digital AC frequency conversion system, and develops an AC motor experiment platform based on DSP TMS320F240, the software and hardware implementation of the system is discussed in detail. The industry computer controls the DSP to output the space vector pulse width modulation voltage wave (SVPWM) onto the induction motor. Using this software we can view the state variable waveform on the PC and modify the variable in the DSP memory. In the meanwhile, we can put the varied advanced motor control method into practice on this platform. In this paper, we have finished the vector control experiments on this platform.Then, the paper discusses the implementation of a new kind of rotor flux and speed observer based on a model reference adaptive system (MRAS), and a speed sensor-less field-oriented control (FOC) system using PI controller for induction motor is presented. The math model of the induction motor is nonlinear, time varying and coupled, from the simulation results, we will find the performance of the system using PI controller is not ideal because it is influenced by parameter variations and external disturbance or uncertainty. So the paper combined the fuzzy logic control and recurrent neural network, and the Recurrent fuzzy neural network (RFNN) controller is introduced into the speedsensorless vector control system. Moreover, an online parameter training methodology, which is derived from the Lyapunov stability theorem and gradient descent method is proposed to increase the learning capability of the RFNN. The RFNN controller has a better performance than the PI controller system; the effectiveness of the proposed control scheme is verified by simulation results.