异步电机单神经元自适应智能控制系统

针对传统抽油电机控制器自适应性能较弱的特点,提出一种单神经元模型参考自适应控制方法,此法在模型参考自适应控制基础上,采用单神经元代替复杂神经网络,选择线性函数作为参考模型,并将速度变化考虑进误差函数,采取磁链开环、转速闭环的控制结构建立控制系统,建立基于此控制方法的异步电机控制系统仿真模型,并基于DSP构建实验控制系统,仿真及实验结果表明所述控制器输出平稳,具有参数及负载时变的自适应能力,应用前景广泛。

Control System of Induction Motors for Pumping Units with Ability Self-adaptive Based on Single Neuron

A method of one single neuron model reference adaptive control（MRAC） method that adopted on single neuron instead of the neural networks based on model reference adaptive control was brought forwards.The control system that adopted on the structure of opening loop of magnetism chain and closed loop of rate was established with the induction motor was taken as a research object.Linearity function was selected as reference model in the system,and rate variety was taken into account when calculated error functions.The simulation and the experimental system of induction motor were proposed.The results demonstrate that the scheme can ensure the motor speed tracking the reference speed quickly and precisely,and reduce its sensitivity to load disturbances.Furthermore,the algorithm is also robust for induction motor parameters variation.The designed controller prospect of application is becoming more and more widespread.