摘要
永磁同步电机控制算法在运行时需要转子位置信息参与计算。一般的无传感器转子位置估计方法计算量大且实现复杂,同时精度低、易受干扰。因此提出一种基于遗传算法优化小波神经网络的永磁同步电机转子位置估计方法,采用训练后的小波神经网络对永磁同步电机转子位置进行估计。同时针对小波神经网络初始权值和阈值选取易导致陷入局部极值的问题,引入遗传算法对小波神经网络进行优化。仿真和实验表明,提出的小波神经网络能够有效对转子位置进行估计,估计结果精度较好并且系统拥有较强的鲁棒性。
Permanent magnet synchronous motor(PMSM)control algorithm requires rotor position information to participate in the calculation.Generally,the sensorless rotor position estimation method has many disadvantages,such as large computation,complex implementation,low accuracy and easy to be disturbed.In this paper,a rotor position estimation method of PMSM based on genetic algorithm optimized wavelet network was proposed.The trained wavelet network was used to estimate the rotor position of permanent magnet synchronous motor.At the same time,genetic algorithm was introduced to optimize the wavelet network in order to solve the problem that the initial weights and thresholds of the wavelet network were easy to fall into local extremum.The simulation and experiment results show that the proposed wavelet neural network can effectively predict the rotor while with good accuracy and strong robustness.
作者
权晓
余红英
韦啸成
QUAN Xiao;YU Hongying;WEI Xiaocheng(School of Electrical and Control Engineering, North University of China, Taiyuan 030051, China;Faculty of Science and Engineering, University of Nottingham Ningbo China, Ningbo Zhejiang 315100,China)
出处
《微电机》
北大核心
2020年第9期63-68,共6页
Micromotors
基金
山西省自然科学基金资助项目(201601D102029)。
