A Fractional Order Sliding Mode Neural Networks Compensation Method For Friction Torque In The Servo Systems Towards Energy Efficency

Compared with the traditional direct current(DC)motor,the permanent magnet synchronous motor(PMSM)has simple structure,low cost and high control performance,and is widely used in high precision servo control systems.Friction torque disturbancce is one of the major factors affecting the accuracy and robustness of the PMSM servo system.It is of great significance to design a nonlinear friction disturbance compensation controller,compensate for the nonlinear friction torque,and improve the position and velocity tracking accuracy of the servo systems.Focusing on the friction torque disturbance in PMSM position servo systems,a fractional order-sliding mode control-neural network(FO-SMC-NN)friction torque compensation control algorithm is proposed by combining fractional order control(FOC),sliding mode control(SMC)and radial basis function neural network(RBFNN)to estimate the friction torque disturbance and eliminate the effect of friction torque disturbance on the system performance.The main contributions of this paper are as follows:Firstly,based on some characteristics of the PMSM,a typical position servo system model with LuGre friction torque disturbance is established.Using the particle swarm optimization-simulated annealing(PSO-SA)optimization algorithm,four static parameters in the LuGre friction model are identified.Moreover,the unmeasured state variable in the model is estimated via the RBF neural network.Secondly,based on the PMSM position servo system model and the LuGre friction model,a fractional order adaptive neural network(FOANN)compensation control algorithm is designed,and its stability is analyzed through the Lyapunov stability theory.Some simulation comparisons with the model reference adaptive control(MRAC)algorithm and the proportional derivative(PD)control algorithm demonstrate that the proposed FOANN control algorithm can accurately estimate the friction torque disturbance and improve the control accuracy of the system.Thirdly,a FO-SMC-NN friction torque compensator is proposed to further improve the robustness of the PMSM positon servo system.Considering the performance and the energy consumption of the control system,a tuning method towards energy efficiency is proposed to determine the equivalent control gain.The simulation results show that the proposed FO-SMC-NN friction torque compensation control algorithm and the parameter tuning method not only improve the control performance of the servo system,but also reduce energy consumption.Finally,using a PMSM position servo system testbed,some comparison experiments of MRAC,PD and FO-SMC-NN controllers are conducted to further verify the effectiveness and superiority of the proposed friction compensation control algorithm.