CAJ | 학술논문

针对永磁直线同步电机混沌系统参数不确定的控制问题，基于具有很强非线性映射能力的 RBF 神经网络，研究一种基于径向基神经网络(RBFNN)的反馈控制方法。该方法以永磁直线同步电机的定子交轴电流、直轴电流以及转速作为控制变量，首先采用 RBFNN 学习这3个变量所体现出来的混沌动力学特性，然后用训练好的径向基函数神经网络模型反馈控制混沌系统。数值模拟结果表明，提出的算法具有很强的鲁棒性，抗干扰能力强、响应速度快、控制精度高。
침대영자직선동보전궤혼돈계통삼수불학정적공제문제，기우구유흔강비선성영사능력적 RBF 신경망락，연구일충기우경향기신경망락(RBFNN)적반궤공제방법。해방법이영자직선동보전궤적정자교축전류、직축전류이급전속작위공제변량，수선채용 RBFNN 학습저3개변량소체현출래적혼돈동역학특성，연후용훈련호적경향기함수신경망락모형반궤공제혼돈계통。수치모의결과표명，제출적산법구유흔강적로봉성，항간우능력강、향응속도쾌、공제정도고。
In terms of the control problem with uncertain parameters for the chaotic system of per-manent magnet linear synchronous motor (PMLSM),based on the RBF neural network with a strong nonlinear mapping ability,a feedback control method with radial basis function neural net-work (RBFNN)is proposed in this paper.This method uses the stator quadrature axis current, direct axis current and speed of the PMLSM as the control variables.Firstly,chaotic dynamics characteristics of the three variables were studied by RBFNN,and then feedback control chaotic systems based on RBFNN model was well trained.The simulation results showed that the pro-posed method is with strong robustness,strong anti-jamming capability,fast responsibility and high control precision.