Font Size: a A A

Control Strategy Research Of Pmsm Based On An Improved T-S Fuzzy Neural Network

Posted on:2018-03-27Degree:MasterType:Thesis
Country:ChinaCandidate:Z L YanFull Text:PDF
GTID:2348330542484979Subject:Control theory and control engineering
Abstract/Summary:PDF Full Text Request
Compared with conventional motors,permanent-magnet synchronous motor(PMSM)has been widely used in many fields because of its simple structure,small torque ripple and high efficiency.It is difficult to establish a dynamic mathematical model for the motor control process with a nonlinear system,parameter variation and dynamic performance difference.With the development of fuzzy neural networks(FNN),which do not depend on the system model,have strong ability of nonlinear mapping,self-learning and fault-tolerance,which makes the FNN widely studied in the present control field.At present,the development of PMSM control strategy makes the PMSM control has the same as the DC motor control system of static and dynamic control performance.FNN has strong robustness and self-adaptability because of its own attributes.Therefore,this paper studies a vector control strategy of PMSM based on FNN.By studying the FNN model deeply,the T-S FNN model proposed by our predecessors is not suitable for the automatic optimization of network model parameters,the parameter stability domain is difficult to be determined,and the selection of hidden layer nodes is more limited.Parameter stability domain,and then the PSO algorithm is introduced to find the optimal parameters and the optimal number of nodes in the hidden layer automatically,which speeds up the network convergence and improves the network approximation accuracy.In addition,since the traditional speed control loop and current control loop are used in the traditional vector control module,the PID controller is widely used.However,the difference between the dynamic and static control performance and the artificial intelligence control strategy makes the vector control strategy of networked control has been studied extensively.In this paper,the T-S FNN model is introduced into the vector control as a speed loop to improve the dynamic and static performance of the PMSM control system through the deep study of this control strategy.Finally,a vector control simulation model of PMSM is established on MATLAB / SIMULINK.The simulation results show that the control effect of PMSM vector control system based on improved T-S FNN is better than that of the previous model.
Keywords/Search Tags:Permanent Magnet Synchronous Motor, Fuzzy Neural Network, Vector Control, PID
PDF Full Text Request
Related items