Prediction of Structural Damage Trend Based on Multi-Model Integration

被引：0
作者：
Liu Y. [1 ]
Ju L. [1 ]
Li R. [1 ]
Tian T. [2 ]
机构：
[1] School of Electronic and Control Engineering, Chang’an University, Shaanxi, Xi’an
[2] Shaanxi Aero Electric Co., LTD., Shaanxi, Xi’an
来源：
Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology | 2023年 / 43卷 / 06期
关键词：
health status; instantaneous frequency; multi-model integration; trend prediction; variation mode decomposition;
D O I：
10.15918/j.tbit1001-0645.2022.119
中图分类号：
学科分类号：
摘要：
Because a single prediction model cannot fully reflect the complex laws and structural vibration information, in order to improve the accuracy of structural health trend prediction and make full use of the advantages of each model, a multi-model integrated prediction method was proposed based on depth-confidence network (DBN), long-short-term memory neural network (LSTM) and wavelet neural network (WNN). Firstly, decomposing engineering structural vibration signal into instantaneous frequency with variation mode decomposition (VMD) and Hilbert transform, the system was arranged to take the instantaneous frequency as the input for the multi-model integration to decide the weight coefficients based on a combination of the weighted average method and the voting method. And then the influence of different weights on the prediction accuracy was analyzed. Finally, some verified experiments were carried out. The experimental results show that the prediction results of the multi-model integration method are closer to the actual values when the weight value ω equals to 0.8. Compared with the traditional arithmetic average model and other three single prediction models, the multi-model integration method can provide better prediction performance and higher prediction accuracy. © 2023 Beijing Institute of Technology. All rights reserved.
引用
收藏
页码：602 / 608
页数：6
相关论文
共 16 条
  • [1] XU Xi, PU Wuchuan, Estimation of the acceleration of nonstructural component considering the effect of duration of earthquake ground motion, Earthquake Engineering and Engineering Dynamics, 39, 3, pp. 230-237, (2019)
  • [2] LIU W, PAN J, REN Y, Et al., Coupling prediction model for long-term displacements of arch dams based on long short-term memory network, Struct Control Health Monit, 27, 7, pp. 10-20, (2020)
  • [3] ZHANG Peng, SUN Bowen, LI Weishi, Et al., Phishing mail detection system based on LSTM neural network, Transactions of Beijing Institute of Technology, 40, 12, pp. 1289-1294, (2020)
  • [4] GAO Fei, ZHAO Jieqiong, LIN Chong, Et al., A SAR image recognition method based on distance metric learning, Transactions of Beijing Institute of Technology, 41, 3, pp. 334-340, (2021)
  • [5] HE Mengfu, ZHOU Youguang, LI Yang, Et al., Long short-term memory network with multi-resolution singular value decomposition for prediction of bearing performance degradation, Measurement, 156, pp. 1-9, (2020)
  • [6] WEN Qiuqiu, HUANG Wenyu, LU Baogang, Research on optimal guidance strategy of terminal speed control based on LSTM, Transactions of Beijing Institute of Technology, 42, 5, pp. 511-522, (2022)
  • [7] YANG Yun, WANG Binze, LIU Yan, Et al., Temperature prediction based on space-time optimization LSTM deep learning network, Journal of Xuzhou Institute of Technology (natural science edition), 35, 2, pp. 44-49, (2020)
  • [8] CHEN Junhua, HAO Yanhui, ZHENG Dingwen, Et al., Modeling and decision-making of features market price prediction with DBN, Computer Science, 45, pp. 75-78, (2018)
  • [9] SUN X, LI T, LI Q, Et al., Deep belief echo-state network and its application to time series prediction, Knowledge Based Systems, 130, 8, pp. 17-29, (2017)
  • [10] SHEN Y L, ZHANG J, LIU J, Et al., Short-term load forecasting of power system based on similar day method and PSO-DBN, Proceedings of 2018 2nd IEEE Conference on Energy Internet and Energy System Integration (EI2), pp. 1-6, (2018)
12