基于模糊神经网络的枸杞滴灌系统设计  

Design of Goji Drip Irrigation System Based on Fuzzy Neural Network

作　　者：张硕 王福平 胡永乐 李振翔 ZHANG Shuo;WANG Fu-ping;HU Yong-le;LI Zhen-xiang(School of computer science and engineering,North Minzu University,Yinchuan 750021,China;School of Innovation and Entrepreneurship,North Minzu University,Ningxia 750021,China)

机构地区：[1]北方民族大学计算机科学与工程学院,银川750021 [2]北方民族大学创新创业学院,银川750021

出　　处：《节水灌溉》2020年第6期87-90,96,共5页Water Saving Irrigation

基　　金：国家自然科学基金项目(61261045);中央引导地方科技发展专项项目基金(YDZX20176400003121);北方民族大学重点科技服务项目(2015KJ01)。

摘　　要：枸杞作为宁夏地区重要的经济作物,其种植过程中的自动化水平低下,宁夏地处西北,全年降水量偏少,土壤以沙土为主,水分易流失,因此枸杞滴灌十分重要。常规的PID算法难以满足枸杞滴灌的自动控制,因此设计了基于模糊神经网络的控制系统,该系统整合了模糊控制和神经网络,将土壤含水率的偏差和偏差变化率作为输入值,经过模糊神经网络运算后,得到PID控制器的3个输入参数,然后通过PID闭环控制系统实现枸杞滴灌的控制,通过Simulink仿真实验得出,模糊神经网络PID控制比传统的PID控制,超调量小,响应速度快。Goji is an important economic crop in Ningxia,while the automation level in its cultivation process is low.Ningxia is located in the northwest of China,its annual precipitation is relatively small,the soil is mainly sandy,water is easy to lose,so Goji drip irrigation is very important.Conventional PID algorithm is difficult to meet the automatic control of Goji drip irrigation.Therefore,a control system based on fuzzy neural network was designed.This system integrated fuzzy control and neural network,and took the deviation of soil moisture content and the variation rate of deviation as input values.After the fuzzy neural network operation,the three input parameters of the PID controller were obtained,and then the Goji drip irrigation control was realized through this PID closed-loop control system.Through the simulation experiments of Simulink,it was verified that the fuzzy neural network PID control had less overshoot and faster response than the traditional PID control.

关 键 词：枸杞滴灌的自动控制 枸杞滴灌系统的设计 超调量 响应速度 模糊神经网络 

分 类 号：S275[农业科学—农业水土工程]