On-line Observation About Parameters Of DTC Based On Wavelet Fuzzy Neural Network Adjusted By Ant Colony Optimization

Great developments have taken place since Direct Torque Control system (DTC) was brought forward. It has been a focus among domestic and foreign scholars because it has character with simple structure, novelty thought and wonderful property. DTC system is different from vector control in that it is located in stator coordinate. As a result, few parameters have effect on DTC systems and it has littler calculation. This paper makes research on stator resistance detector and speed estimator adjusted by ant colony optimization (ACO), the whole DTC system has been emulated and the performance has been checked. At the same time, hardware circuit and software chart, which is based on wavelet fuzzy neural network adjusted by ant colony optimization, have been designed.In the high-speed area, the error brought by stator resistance variety can be ignored, so stator flux can be hold on the track well. However, in the low-speed area, error can't be ignored, thus system performance is seriously affected by stator resistance. How to enhance resistance detector precision is the key to improve the low-speed performance of DTC system.The stator resistance is affected by many factors, such as the driver's runtime, current magnitude, frequency, and cool conditions etc. It is difficult to find the relationship through the tradition methods because of complicated variety of resistance. The main point of this paper is to apply ACO to the detection of stator resistance; to combine several factors into two parameters: temperature and temperature changing-rate. This paper adopts the wavelet neural network (WNN) as the detector of the stator resistance. The network can be used on-line while being trained on-line.This paper designs a wavelet fuzzy neural network (WFNN) speed estimator, which combines the sensor-less technology with ACO. In the emulation, MATLAB language will be used to emulate the DTC system, resistance detector and speed estimator. The results validate that the resistance detector greatly improves the system low-speed performance and speedestimator follows the tracks of the motor speed rapidly; So the system acquire better static and dynamic features. The DTC system has good prospect in application. The enhancement of low-speed performance may accelerate the extending and application of sensor-less DTC system.