伺服电机驱动的液压动力系统及其神经网络自适应优化控制

针对传统液压系统存在的高能耗、低响应特点,采用节能型液压动力源-永磁伺服电机直接驱动定量泵,以取代原有的异步电机驱动液压动力源,从而形成一种新型的节能、响应快速、易实现闭环控制的液压动力系统。由于实际液压系统随机干扰严重,具有多变量、非线性、强耦合的特征,难以建立较准确的数学模型,常规的PID控制算法很难满足液压系统高精度控制的要求,因此提出基于PSO与BP混合优化前向神经网络 PID自适应控制方法,实现液压系统在典型工况下流量的精确控制。PID控制器的参数采用神经网络进行自适应整定,神经网络的权值采用混合优化算法进行调整,通过神经网络的自学习能力寻找最佳的P、I、D非线性组合控制律,以增强液压系统对工况变化的适应能力。仿真和实验结果表明,该控制方法跟踪速度快、超调小、鲁棒性强,从而为液压系统流量高精度控制提供了一种新方法。

Neural Network Adaptive Optimal Control Strategy of Servo Motor Driven Hydraulic System

In view of the high energy consumption and low response of the traditional hydraulic system, a permanent magnet synchronous motor driven constant pump hydraulic system was designed instead of common motor, which was easy to realize closed-loop feedback control. Because of the serious random interference, multi-variable, nonlinear, strong coupling, it was difficult to establish precise mathematical model of hydraulic system. General PID was difficult to meet high precision control requirements, in this respect a forward neural network PID controller based on PSO-BP hybrid optimization algorithms for adaptive control of hydraulic system was proposed to realize precise control of flow under complex conditions. The control parameters of PID controller were adjusted adaptively by neural network, the weights of neural network were optimized by the mixed learning methods. An optimized non-linear combined control rule of P, I, and D was built by the self-learning ability of neural network and to strengthen the ability of changes in working condition. Simulation and experimental results show that: the controller has fast tracking ability, small overshoot and strong robustness. A new method is provided for the high-precision flow control of hydraulic system.