基于rbfnn的无刷直流电机直接电流控制与转矩分析-电机与电器专业论文.docxVIP

中文摘要本文研究了无刷直流电机的无位置传感器控制技术、转矩波动抑制理论及 中文摘要 本文研究了无刷直流电机的无位置传感器控制技术、转矩波动抑制理论及 其DSP控制。首先，构造一个隐层节点初始个数为零的RBF网络，在训练过程 中不断地按照自适应算法添加和删除隐层单元，形成一个结构简单、紧凑的 RBF网络以实现电机电压、电流与功率开关导通信号之间的非线性映射，完成 无位置传感器的直接电流控制。利用来自实验数据的训练样本按给出的自适应 算法对网络进行离线训练，确定RBF网络隐层节点的个数及位置；再按递推最 小二乘法(RLS)在线修正隐层与输出层之间的连接权。这样，在保证网络结 构简单、紧凑的同时，在线训练算法简单。提高了系统的动态响应速度。其 次，提出了基于RBF神经网络的无刷直流电机无位置传感器控制下转矩波动抑 秘策略。通过对两个RBF神经网络按照本文提出的自适应算法进行离线训练， 实现了电机电压、电流与转予位置之间以及转矩、转予位置与参考电流之间的 非线性映射。将训练完的网络分别用于转子位置与参考电流的在线估计，并按 参考电流调节电枢绕组的电流，在实现无位置传感器控制的同时，达到了抑制 转矩波动的目的。最后，本文介绍了无刷直漉电机无位置传感器控制的DSP实 现技术，给出了无刷直流电机无位置传感器控制硬件系统与软件结构图，以及 相应的实验结果。 关键词：无刷直流电机；自适应RBF神经网络；宣接电流控制；转矩波动 DSP ABSTRACTThis ABSTRACT This research focuses on the technique of position-sensorless control，the methods of torque ripple minimization and the DSP control for the bmshless DC motor(BLDCM)．the In this paper,a novel approach based on all adaptive Radial Basis Function{RBF)neural network is proposed，and through this approach，the direct control of the currents for a brnshless DC motor without position sensors is realized．In the proposed KBF network，there is nO hidden units at the beginning．and during the process of learning，they are increased or decreased according to all adaptive algorithm SO that a RBF network is built with a much simpler and tighter structure to form an efficient nonlinear map from terminal voltages and phase currents of the motor to the states of the power switches，facilitating the elimination of the position sensors．The RBF network iS tminexl both offiine and online．．In the off／ine ways with the training data collected from experiments，the number and locations of the hidden units of the RBFNN fll-e obtained；while online．1earning,the weights between the hidden layer and the output layer are updated according to the recursive least squares(RLS)algorithm．Therefore,the simpleness and tightness is ensured，at the same time，the online algorithm is very simple SO that the dynamic responsible speed is improved．Secondly,to deal with the issues of roto