基于高速开关阀控的叶片泵变量控制研究

发布时间：2018-05-22 11:44

本文选题：叶片泵 + 变量机构　；参考：《昆明理工大学》2017年硕士论文

【摘要】：随着流体传动控制与计算机技术的迅速发展及广泛应用,使液压系统自动化控制在液压元件、系统控制以及理论应用等方面都日趋完善和成熟,电液数字控制技术已成为机电一体化中一个重要技术手段。变量泵作为液压传动与控制系统中的核心元件,其性能好坏影响整个液压系统的控制性能。本文提出了一种基于RBF神经网络与PID控制相结合的变量叶片泵控制系统,主要由RBF神经网络控制器、压力和位移传感器、高速开关阀、变量叶片泵等元件组成。该系统通过智能控制器输出PWM信号,改善高速开关阀的动静态特性,同时根据工作要求对控制系统的各个环节进行智能优化,实现液压数字泵控制系统的智能化、自动化。本文针对现有数字泵控制系统的缺陷和不足,设计一种基于RBF神经网络算法的控制器,通过控制高速开关阀PWM信号的占空比,改变活塞缸两腔间的压力差,使液压泵内变量机构随活塞缸位置的调整而改变,实现变量叶片泵工作口输出流量与压力的控制;运用MATLAB/SIMULINK软件对控制系统进行仿真,结果表明该控制系统的控制效果和稳定性都能满足工作要求;针对复杂非线性,外界干扰的控制问题,设计了一种单神经元自适应PID控制系统,用RBF神经网络辨识获得对象的模型信息,使权值系数根据被控对象运动状态的变化而调整,从而提高控制系统的鲁棒性和抗干扰性,优化了系统的控制性能。
[Abstract]:With the rapid development and wide application of fluid transmission control and computer technology, the automatic control of hydraulic system has become more and more perfect and mature in the aspects of hydraulic components, system control and theoretical application. Electro-hydraulic digital control technology has become an important technical means in electromechanical integration. Variable pump is the core component of hydraulic transmission and control system, and its performance affects the control performance of the whole hydraulic system. In this paper, a variable vane pump control system based on RBF neural network and PID control is proposed. It is composed of RBF neural network controller, pressure and displacement sensor, high speed switch valve, variable vane pump and so on. The system outputs the PWM signal through the intelligent controller, improves the dynamic and static characteristics of the high speed switch valve, at the same time carries on the intelligent optimization according to the work request to the control system each link, realizes the hydraulic digital pump control system intellectualization, the automation. Aiming at the defects and shortcomings of the existing digital pump control system, a controller based on the RBF neural network algorithm is designed in this paper. By controlling the duty cycle of the PWM signal of the high speed switch valve, the pressure difference between the two cavities of the piston cylinder can be changed. The variable mechanism of hydraulic pump is changed with the adjustment of piston cylinder position, the output flow and pressure of variable vane pump are controlled, and the control system is simulated by MATLAB/SIMULINK software. The results show that the control effect and stability of the control system can meet the operational requirements, and a single neuron adaptive PID control system is designed for complex nonlinear and external disturbance control problems. The model information of the object is identified by RBF neural network, and the weight coefficient is adjusted according to the change of the moving state of the controlled object, thus the robustness and anti-interference of the control system are improved, and the control performance of the system is optimized.
【学位授予单位】：昆明理工大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TH137.51;TP273

【参考文献】