Design And Implementation Of A Communication Network Status Prediction System For Intelligent Production Line

In recent years,with concept of "Industry 4.0",the intelligent production line with the basic characteristics of production intelligence and communication platform network has been developed rapidly,and China is also speeding up the intelligent construction of production lines.Therefore,network status monitoring and prediction for intelligent production line communication platform network has become particularly important.In intelligent production line network system,network traffic is a complex and time-changing data with high degree of uncertainty.The congestion or crash of a device node network in the intelligent production line network will cause the intelligent production line equipment to fail to communicate normally,and even cause the entire production line network system to crash,cause serious consequences such as the loss of production line data,and greatly reduce the work efficiency of the production line.Therefore,it is very important to predict the network status of the intelligent production line in advance,so that the network managers can repair the network problems in time and improve the efficiency of the intelligent production line.Aiming at the problems that need to be solved urgently in the network communication technology in the intelligent production line environment,this paper combines the existing intelligent production line network platform in the laboratory to carry out the research of the intelligent production line network status prediction system based on LSTM?BP neural network,and designs a network prediction system.It can prejudge the operation status of the intelligent production line network,and reduce the influence of the fluctuation of the network status on the production efficiency of the intelligent production line.The specific research content of this paper is as follows:1.The collection and preprocessing of network data.First,study and compare the characteristics of various data collection methods,choose a method suitable for production line network data collection,then analyze the specific parameters affecting the state of network nodes,determine the type of network data collected,and finally pre-process the data.2.Based on the idea of hybrid model,a status prediction model of intelligent production line network based on the hybrid of LSTM and BP neural network is proposed.The data flow in the equipment communication network has the characteristics of nonlinearity and suddenness,and the long and short-term memory network has many advantages in solving the problem of multiple input and output variables,which makes it able to solve the problem of time series well.BP neural network model has strong nonlinear fitting and generalization ability,so this paper proposes a network status prediction model based on the hybrid of deep neural network LSTM and BP neural network.Aiming at the time sequence of the operating status of each node in the intelligent production line network,first,the long-short-term memory network is used to predict the network operation data of the monitoring node at the next moment,and then the prediction results are input into the BP neural network model,and finally the network operation status of the monitoring node is predicted.The experimental results show that the hybrid prediction model proposed in this paper has high prediction accuracy,which proves the effectiveness of the hybrid model proposed in this paper and meets the expected requirements of the production line network status prediction.3.Following the idea of software engineering,design and implementation of a communication network status prediction system for intelligent production line.In order to monitor the operation status of each node in the intelligent production line network more intuitively,based on the B/S architecture,this paper designs and develops a communication network status prediction system for the intelligent production line using the Java language.The system includes data management module,network equipment status monitoring module,network status prediction module and user management module.Finally,a comprehensive functional test and performance test are performed on the system.The test results show that the system can meet the expected requirements and has a certain value in practical application.