基于模糊神经网络的输液监控系统设计

A Transfusion Monitor Based on Fuzzy Neural Network

以MSP430MCU为控制核心,结合输液传感器、电动执行器、液晶显示、键盘等,实现了对输液过程的自动监控。由于输液系统是一个非线性、时变、滞后的复杂控制对象,采用传统的控制策略难以取得良好的实时监控效果。本文介绍了一种基于模糊神经网络模型的控制方法,该方法结合了模糊逻辑控制和神经网络的优点,利用神经网络记忆模糊规则和实现模糊控制,并利用误差反向传播算法实现当控制对象参数变化时控制器的在线自学习。从而能快速、准确的对实测数据进行综合、分析和处理,达到智能实时控制的效果。经试验,其控制精确,运行可靠且系统体积小、成本低、操作简便,具有推广应用价值。

The monitor combines the transfusion sensor, the electric apparatus, the LCD screen, the keyboard and the MSP430 MCU as the core of control to realize automatic monitor for transfusion process. Because transfusion system is nonlinear and complex, which changes now and then and lags behind hour, conventional control method can hardly obtain benign real time monitor effect. This article introduced a control method based on fuzzy neural network, which integrates the excellences of fuzzy logical control and neural network. The method uses neural network to remember fuzzy rule and achieve fuzzy control and uses error back propagation to realize online self-learning when the control object parameter has changed. So it can colligate, analysis and dispose data quickly and exactly to achieve intelligent control. Through examination, this monitor manages accurately, runs credibility, and its small bulk, low cost and convenient manipulation makes it worth popularizing and applying.