Rotor speed identification on DTC system based on neural network of new chaos optimizer algorithms

To solve the disadvantage that BP neural network is liable to get into the local minimum, a novel learning algorithm that new chaos optimizer BP neural network is proposed. By the use of the properties of ergodicity and randomness of chaos algorithms, and combining global rough search and local elaborate search of chaotic variable, get the global optimization weight values of neural network. By the simulation of direct torque control (DTC) system based on new chaos neural network, the simulation results show that the rotor speed identification has high approximation precision and good generalization capability, and provides a new plan for the speed-sensorless DTC system.