论文部分内容阅读
本文在神经网络误差回传算法基础上提出了一种三层BP神经网络算法,并和PID控制算法相融合,得出一种新的控制伺服交流电机的方法。整个伺服系统的控制电路以数字信号处理器为核心,它可以完成永磁同步电机数字控制中的传感器信号的采集与数据处理,实现基于神经网络的PID参数自整定的电机矢量控制算法,产生控制交流伺服电机的PWM信号。在算法方面,利用三层BP神经网络算法对PID的积分增益、微分增益和比例增益进行智能化调节,大大提高了系统的性能。
Based on neural network error feedback algorithm, a three-layer BP neural network algorithm is proposed in this paper, which is combined with PID control algorithm to get a new method to control servo AC motor. The entire servo system control circuit to digital signal processor as the core, it can complete the digital control of permanent magnet synchronous motor sensor signal acquisition and data processing, based on neural network PID parameter self-tuning motor vector control algorithm to produce control AC servo motor PWM signal. In the aspect of algorithm, the three-layer BP neural network algorithm is used to intelligently adjust integral gain, differential gain and proportional gain of PID, which greatly improves the performance of the system.