Research and application of network status prediction based on BP neural network for intelligent production line

被引:23
作者
Ma, Yue [1 ,2 ]
Li, Le [1 ,2 ]
Yin, Zhenyu [1 ,2 ]
Chai, Anying [1 ,2 ]
Li, Mingshi [1 ,2 ]
Bi, Zhiying [1 ,2 ]
机构
[1] Chinese Acad Sci, Shenyang Inst Comp Technol, Shenyang 110168, Peoples R China
[2] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
来源
PROCEEDINGS OF THE 10TH INTERNATIONAL CONFERENCE OF INFORMATION AND COMMUNICATION TECHNOLOGY | 2021年 / 183卷
关键词
ARMA; BP neural network; Network status prediction system;
D O I
10.1016/j.procs.2021.02.049
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In the intelligent production line network communication process of the Industrial IoT, communication node congestion will cause the communication quality to decrease, thereby affecting the production efficiency. Therefore, accurately predicting the status of network and making adjustments to the network in real time is of great significance to improving the quality of network communication. Aiming at the urgent problem of the network communication quality of the intelligent production line, this paper proposes a network status prediction algorithm for the intelligent production line. The algorithm uses the ARMA prediction model to predict the network data, and calculates and predicts the entire network operation through the optimized BP neural network. At the same time, an intelligent production line network prediction system is designed based on the algorithm. The system can predict the network operation status in advance, reducing the impact of network status fluctuations on the production efficiency of the intelligent production line. The simulation results show that after a large number of network data prediction experiments, the optimal data prediction period is obtained. Under this period, the accuracy of network status prediction reaches 90%. (C) 2021 The Authors. Published by Elsevier B.V.
引用
收藏
页码:189 / 196
页数:8
相关论文
共 18 条
[1]  
Abed H, 2010, GLOBAL TELECOMMUNICA, P1
[2]   Efficient failure prediction in autonomic networks based on trend and frequency analysis of anomalous patterns [J].
Abed, Hesham J. ;
Al-Fuqaha, Ala ;
Khan, Bilal ;
Rayes, Ammar .
INTERNATIONAL JOURNAL OF NETWORK MANAGEMENT, 2013, 23 (03) :186-213
[3]  
Ali Liu Omidi, 2018, J DONGHUA U, P270
[4]  
Chen Ping, 2019, SHIP ELECT ENG, V39, P98
[5]  
Deng Li, 2012, Computer Engineering, V38, P251, DOI 10.3969/j.issn.1000-3428.2012.20.065
[6]  
Hou Xiaokai, 2014, J SHANDONG U TECHNOL, P29
[7]   A Study of Equipment Fault Forecast System Based on Virtual Setting [J].
Huang Jingde .
INFORMATION ENGINEERING FOR MECHANICS AND MATERIALS SCIENCE, PTS 1 AND 2, 2011, 80-81 :1244-1248
[8]  
Liu Jie, 2007, Journal of Computer Applications, V27, P1770
[9]  
Liu Liang, 2015, COMPUTER ENG DESIGN, P2021
[10]  
Liu X, 2015, PROCEEDINGS OF THE 2015 IFIP/IEEE INTERNATIONAL SYMPOSIUM ON INTEGRATED NETWORK MANAGEMENT (IM), P371, DOI 10.1109/INM.2015.7140313