摘要
针对以永磁直线同步电机为执行机构的驱动系统易受到推力波动等周期性扰动影响的问题,采用了基于PID神经元网络的跟踪微分器控制方法。该方法通过定义具有比例、积分、微分功能的神经元,将PID控制规律融合进神经元网络中,有效抑制端部效应、纹波推力、齿槽力以及摩擦力对系统的干扰,同时具有快速的跟踪性能。仿真试验表明,与传统的PID控制相比,该控制方法提高了系统的鲁棒性和跟踪性,更加实用有效。
For permanent magnet linear synchronous motor as the actuator of the drive system being vulnerable to the influence of the periodic disturbance such as the end effect of the problem, the PIDNN control methodis based on PID Neural Network with tracking differentiator was proposed. PIDNN which has the function of proportion, integral and differential neurons, incorporate PID control law into the neural network. PIDNN effective inhibition of end effect, thrust ripple, the cogging force and the friction disturbance to the system. Simulation experiments showed that compared with the traditional PID control, the PIDNN control to improve the robustness and traceability of the system, the more practical and effective.
出处
《电机与控制应用》
北大核心
2017年第2期18-22,共5页
Electric machines & control application
基金
国家自然科学基金项目(20577038)
河北省科技计划项目(10213944)
关键词
永磁直线同步电机
PID神经元网络
干扰抑制
跟踪微分器
permanent magnet linear synchronous motor （PMLSM）
PID neural network （PIDNN）
disturbance rejection
tracking differentiator
