Research on Real-Time Overload Prediction Method of in-Service Structures

被引：0
|
作者：
Yang B.-W. [1 ]
Huo J.-Z. [1 ]
Zhang W. [1 ]
Zhang Z.-G. [1 ]
机构：
[1] School of Mechanical Engineering, Dalian University of Technology, Dalian
来源：
Dongbei Daxue Xuebao/Journal of Northeastern University | 2022年 / 43卷 / 04期
关键词：
Advanced load prediction; BP neural network; Kernel density estimation; Monte Carlo method; Real-time prediction;
D O I：
10.12068/j.issn.1005-3026.2022.04.012
中图分类号：
学科分类号：
摘要：
In order to ensure the real-time monitoring of the fatigue life of key structures, the dynamic random load is used as the monitoring condition to accurately predict the importance of the advanced load spectrum for actual engineering analysis.Aiming at the difficulty of real-time monitoring of in-service equipment and accurately responding to the real laws of load, a probability density prediction method based on numerical analysis is proposed, combined with machine learning BP neural network intelligent algorithm to establish a prediction model. The random load is collected by the strain sensor for preprocessing to obtain random load spectra, and the Monte Carlo method is used to analyze the model load waveform trend and the prediction accuracy of the fluctuation range. The results show that the nuclear density fitting curve of the advanced prediction load spectrum has a high similarity to the real value, which provides theoretical support and practical engineering application for the advanced load monitoring of large and complex in-service structures. © 2022, Editorial Department of Journal of Northeastern University. All right reserved.
引用
收藏
页码：541 / 550
页数：9
相关论文
共 21 条
  • [1] Lewandowski M, Placzek B., An event-aware cluster-head rotation algorithm for extending lifetime of wireless sensor network with smart nodes[J], Sensors, 19, 19, pp. 4060-4071, (2019)
  • [2] Ma X, Wang B, Li L, Et al., A communication method between high-speed uuv and distributed intelligent nodes[J], Mobile Networks and Applications, 25, 4, pp. 1528-1536, (2019)
  • [3] Vahabi S, Eslaminejad M, Dashti S E., Integration of geographic and hierarchical routing protocols for energy saving in wireless sensor networks with mobile sink[J], Wireless Networks, 25, 5, pp. 2953-2961, (2019)
  • [4] Wang Y, Liu J, Hu J, Et al., Fatigue strength of EH36 steel welded joints and base material at low-temperature[J], International Journal of Fatigue, 122, pp. 105-117, (2020)
  • [5] Zhao X, Su S, Wang W, Et al., Metal magnetic memory inspection of q345b steel beam in four point bending fatigue test [J], Journal of Magnetism and Magnetic Materials, 514, pp. 155-167, (2020)
  • [6] Costilla-Reyes A, Erbay C, Carreon-Bautista S, Et al., A time-interleave-based power management system with maximum power extraction and health protection algorithm for multiple microbial fuel cells for Internet of things smart nodes[J], Applied Sciences, 8, 12, pp. 113-125, (2018)
  • [7] Shi Song-fang, High-reliability fiber Bragg grating sensor network transmission risk prediction, Laser Magazine, 41, 5, pp. 167-171, (2020)
  • [8] Li F., Compilation method of fatigue test load spectrum for underfloor equipment bearing structure[J], Journal of Mechanical Engineering, 52, 24, pp. 99-110, (2016)
  • [9] Zheng He-yan, Load spectrum compilation and fatigue life prediction simulation of accelerated life test of high-speed train body, (2019)
  • [10] Zhai Xin-ting, Research on the compilation method of construction machinery load spectrum based on extrapolation improvement, (2018)
123