摘要
为了提高远程无人测流实时性,提出一种远程实时控制方案。PLC将雷达测流仪采集的水面信号和流速信号进行过滤后,经Zigbee无线数传模块与测流控制软件进行处理与保存,定义通讯格式并开发客户端软件实现远程控制。结合测流平台本身的特点,基于改进小波神经网络PID算法对网络时延实时预测并进行预估补偿,最后的仿真和实验结果表明:小波神经网络-PID算法对时延的预测率较高,系统网络时延能够有效保持在200ms左右,较补偿前缩短20%,满足水文测流实时控制的要求。
In order to improve the real-time performance of remote unmanned flow measurement,a remote real-time control scheme is proposed.Afier the PLC filters the water surface signal and the flow rate signal collected by the radar flow meter,they are processed and stored by the Zigbee wireless data transmission module and flow measurement control sofiware,the communication format is defined and the client software is developed to realize remote control.Combined with the characteristics of the flow measurement platform itself,the improved wavelet neural network PID algorithm is used to predict and compensate the network delay in real time.The final simulation and experimental results show that the wavelet neural network-PID algorithm has a high prediction rate of time delay,and the system network delay can be effectively maintained at about 200ms,which is 20%shorter than before compensation,and meets the requirements of real-time control of hydrological flow measurement.
作者
吕健
武利生
张金柱
付晓艳
LYU Jian;WU Lisheng;ZHANG Jinzhu;FU Xiaoyan(College of Mechanical and Vehicle Engineering,Taiyuan University of Technology,Shanxi Taiyuan 030024,China;Tianjin Polytechnic College,Tianjin 300400,China)
出处
《机械设计与制造》
北大核心
2025年第9期1-4,共4页
Machinery Design & Manufacture
基金
国家自然科学基金青年项目(51905367)。
关键词
远程测流
实时控制
小波神经网络
网络时延
预测补偿
Remote Flow Measurement
Real-Time Control
Wavelet Neural Network
Network Delay
Predic-tiveCompensation
