一种三电平NPC整流-逆变调速系统的无权重系数模型预测控制策略

Model predictive control strategy for three-level NPC rectifier–inverter drive system without weighting factor

针对异步电机三电平中点钳位(Neutral point clamped,NPC)整流–逆变驱动系统的高性能高效控制,搭建了三电平整流–逆变系统的预测与损耗模型,构建了包含中点电压平衡与损耗优化的代价函数,提出了一种基于序列并行结构的无权重系数模型预测控制.策略在传统的序列模型预测控制中引入了直流母线中点电压和变换器开关频率控制,构建了包含多个控制目标的统一代价函数.根据整流–逆变系统在运行中对各控制目标的实际需求,将代价函数中的多个控制目标分为主要和次要控制目标并归类为两个序列优化集,对不同的序列集进行顺序优化.在相同的序列集内部,采用自适应并行寻优来选择最优开关状态,保证了同级序列内各控制目标的同步优化,避免了权重系数的设计.仿真和实验结果验证了该方法具有良好的控制性能和参数鲁棒性,并能有效控制中点电压波动和降低系统损耗.

The three-level converter has become the mainstream converter topology because of its good output power quality and high power factor.The three-level dual pulse width modulation frequency speed control system with rectifier–inverter structure has become a research hotspot in academic circles because of its advantages of bidirectional energy flow,high power quality,and controllable intermediate direct current(DC)voltage.Aiming at the high-performance and high-efficiency control of the three-level neutral point clamped(NPC)rectifier–inverter drive system of an induction motor,this study builds a prediction and loss model of the three-level rectifier–inverter system,constructs a cost function including the midpoint voltage balance and loss optimization,and proposes a model predictive control without weighting factors based on a sequential parallel structure.With the development of the field of power electronics,the control performance and efficiency of the converter have gradually improved,and the model predictive control applied to the converter is no longer limited to the traditional control objectives.The proposed strategy introduces the DC bus midpoint voltage and converter switching frequency control to the traditional sequential model predictive control and constructs a unified cost function with multiple control objectives.According to the actual requirements of the multiple control objectives in the operation of the rectifier–inverter system,the control objectives in the cost function are divided into primary and secondary control objectives and classified into two sequence optimization sets,and different sequence sets are sequentially optimized.In the same sequence set,adaptive parallel optimization is used to select the optimal switching state,which ensures the synchronous optimization of each control object in the sequence,thus avoiding the need for weighting factors.The parallel structure can rank multiple control targets,reduce the number of sequences to increase the number of optional voltage vectors between each sequence and increase the control effect of nonprimary control targets.Moreover,synchronous optimization of control targets of the same importance is realized at the same level,which solves the problem that targets of similar importance must be sequentially optimized in conventional sequential model predictive control,solves the problem that the priority of different targets is difficult to adjust,and has stronger applicability for the complex topology structure with multiple control requirements.The simulation and experimental results showed that the proposed algorithm can improve the steady-state and dynamic performance of the system,reduce the midpoint voltage bias,reduce the switching frequency of the rectifier and inverter,reduce the total harmonic bias,and adjust the midpoint voltage unbalance.