论文部分内容阅读
提出了针对永磁同步电机速度控制的神经网络模型参考自适应控制器。将模型参考自适应状态观测器和单神经元PID应用于永磁同步电机无速度传感器矢量控制中,选取永磁同步电机本体作为参考模型,电流模型为可调模型。以波波夫稳定性理论为基础确定自适应律并分析其稳定性。系统同时采用了将神经网络理论与传统PID控制理论相结合,通过结合无监督Hebb学习规则和有监督Delta学习规则提高控制器参数在线学习和优化,形成了神经网络PID控制器单取代传统PID,改善了传统PID的控制效果和鲁棒性。同时,采取了Matlab进行仿真验证可行性和有效性。
A neural network model reference adaptive controller for the speed control of permanent magnet synchronous motor was proposed. The model reference adaptive observer and single neuron PID are used in the sensorless vector control of permanent magnet synchronous motor. The main body of the PMSM is selected as the reference model, and the current model is an adjustable model. Based on Popov’s stability theory, the adaptive law is determined and its stability is analyzed. At the same time, the system combines neural network theory with traditional PID control theory to improve on-line learning and optimization of controller parameters by combining unsupervised Hebb learning rules and supervised Delta learning rules. Neural network PID controller is formed to replace traditional PID, Improve the traditional PID control effect and robustness. At the same time, the feasibility and effectiveness of Matlab simulation are verified.