基于多尺度卷积的多PLC通信时延预测研究  

Time-Delay Prediction Study of Multi-PLC Communication Based on Multi-scale Convolution

作　　者：王梦欣 冯永康 WANG Mengxin;FENG Yongkang(School of Information and Electronic Engineering,Shangqiu Institute of Technology,Shangqiu 476000,China)

机构地区：[1]商丘工学院信息与电子工程学院,河南商丘476000

出　　处：《通信电源技术》2025年第3期195-197,共3页Telecom Power Technology

摘　　要：由于现有的预测方法数据解码均发生显著变化,导致时延结果均在350~500 ms,为此研究基于多尺度卷积的多可编程逻辑控制器(Programmable Logic Controller,PLC)通信时延预测。在多PLC的协同工作中,通过计算校正位并在接收端进行校正,完成多PLC通信数据采集。建立多尺度卷积神经网络模型提取数据中的不同特征。通过逻辑优化算法优化网络,使用训练好的模型预测通信时延数据,得到预测的通信时延。实验结果表明,实验组的时延保持在330 ms以内,能够更高效地处理通信任务。Because the data decoding of the existing prediction methods has changed significantly,the delay results are all in the range of 350~500 ms.Therefore,the communication delay prediction of Programmable Logic Controller(PLC)based on multi-scale convolution is studied.In the cooperative work of multiple PLC,the communication data acquisition of multiple PLC is completed by calculating the correction bits and correcting them at the receiving end.A multi-scale convolutional neural network model is established to extract different features from data.The network is optimized by logical optimization algorithm,and the communication delay data is predicted by using the trained model to get the predicted communication delay.The experimental results show that the delay of the experimental group is kept within 330 ms,and the communication task can be handled more efficiently.

关 键 词：多尺度卷积 可编程逻辑控制器(PLC) 通信时延预测 

分 类 号：TN929.5[电子电信—通信与信息系统]