油茶果采摘机阀控液压马达模糊神经网络PID控制

Fuzzy Neural Network PID Control of Valve-controlled Hydraulic Motor for Camellia Fruit Picking Machine

推摇式油茶果采摘机在作业机构作业时,需要保证振动液压马达恒定转速输出,以保证油茶果能够顺利通过推摇振动从树枝脱落,对此,推导了推摇式油茶果采摘机阀控振动液压马达系统的状态空间方程,并在传统增量式PID控制原理的基础上设计了模糊径向基函数(Radial Basis Function,RBF)神经网络PID控制方法。采用MATLAB/Simulink仿真软件对液压系统在空载和5 s带载工况进行仿真,并与传统PID控制和模糊PID控制方法进行比较和分析。仿真结果显示,传统PID控制和模糊PID控制响应速度较慢、鲁棒性较差;而采用模糊RBF神经网络PID控制方法响应速度快、鲁棒性强,能够很好地满足振动液压马达恒定转速输出的要求,并且能够灵活地在线调整PID的3个参数,控制精度较高。

The push-shaking camellia fruit picking machine needs to ensure the constant the hydraulic motor speed during the operation to ensure that the camellia fruit can smoothly fall from the branches through the shaking vibration.In this regard,this paper derives the state space model of the valve-controlled hydraulic motor system of the push-shaking camellia fruit picking machine,and designs a fuzzy RBF neural network PID control method based on the traditional incremental PID control principle.Finally,the hydraulic system is simulated with the MATLAB/Simulink software with the simulation under no-loading and 5 s-loading conditions.Then the simulation of the system is compared with traditional PID control and fuzzy PID control methods.The results show that the traditional PID control and the fuzzy PID control have slow response and poor robustness,while the fuzzy RBF neural network PID control method possesses the characteristics of fast response and strong robustness,which can well meet the constant the hydraulic motor speed,and flexibly adjust the three parameters of the PID controller online and has high control accuracy.