Prediction of Structural Damage Trends Based on the Integration of LSTM and SVR
Source abstract
Abstract
Currently, accidents in civil engineering buildings occur frequently, resulting in significant economic damage and a large number of casualties. Therefore, it is particularly important to predict the trend of early damage to building structures. Early structural damages are difficult to correctly identify, and obtaining the required accuracy using a single traditional time-series prediction method is difficult. In this study, we propose a novel method based on the integration of support vector regression (SVR) and long short-term memory (LSTM) networks to predict structural damage trends. First, the acceleration vibration signal of the structure is decomposed using the variational mode decomposition (VMD) method, and the decomposed components are transformed with Hilbert transform to obtain the instantaneous frequency. Then, the instantaneous frequency is input into the LSTM–SVR integrated model for damage trend prediction. The results indicate that the VMD method effectively eliminates modal aliasing and decomposes various intrinsic components of the signal. Compared with individual LSTM and SVR models, the integration model has a higher prediction accuracy for small samples in a chaotic time series that is 6.56%, 2.56%, and 3.7%, respectively. The standard deviation of the absolute percentage error (SDAPE) values of the three operating conditions under the integrated method decreased 0.0994, 0.0869, and 0.0921, which improved the stability of prediction. The mean absolute percentage error (MAPE) of the integration method is an order of magnitude higher than that of the LSTM model.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Structural Health Monitoring Techniques · Infrastructure Maintenance and Monitoring · Wind and Air Flow Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Energy and Electrical Engineering, Chang’an University, Xi’an 710018, China
Funding
Key Research and Development Program of Shaanxi Province
References (44)
Show source-provided references
1. Research status and future prospects of space structure health monitoring
2. Structural health monitoring based on inner product matrix and deep learning
3. Prediction model for blast-induced structural damage based on an optimized Bayes discriminant analysis model10.1016/j.apm.2022.05.011 ↗
4. Structural health monitoring of civil engineering structures by using the internet of things: A review
5. A novel delamination damage detection strategy based on inverse finite element method for structural health monitoring of composite structures10.1016/j.ymssp.2023.110202 ↗
6. Insights on the impact of structural health monitoring systems on the operation and maintenance of offshore wind support structures10.1016/j.strusafe.2021.102154 ↗
7. Improved Classification Scheme Using Fused Wavelet Packet Transform Based Features for Intelligent Myoelectric Prostheses10.1109/TIE.2019.2946536 ↗
8. Hybrid pixel based method for multimodal image fusion based on Integration of Pulse Coupled Neural Network (PCNN) and Genetic Algorithm (GA) using Empirical Mode Decomposition (EMD)10.1016/j.micpro.2022.104665 ↗
9. Variational mode decomposition10.1109/TSP.2013.2288675 ↗
10. Wu, J. (2019). Short-Term Power Load Forecasting Based on VMD and Improved Extreme Learning Machine, Xi’an University of Technology.
11. A novel hybrid model for wind speed prediction based on VMD and neural network considering atmospheric uncertainties10.1109/ACCESS.2019.2915582 ↗
12. Application of Improved Least Squares Support Vector Machine in the Forecast of Daily Water Consumption10.1007/s11277-018-5393-2 ↗
13. Estimation of vibration stability in milling of thin-walled parts using operational modal analysis10.1007/s00170-021-07051-0 ↗
14. Forecasting stock price using integrated artificial neural network and metaheuristic algorithms compared to time series models10.1007/s00500-021-05775-5 ↗
15. Low cycle fatigue life prediction of titanium alloy using genetic algorithm-optimized BP artificial neural network10.1016/j.ijfatigue.2023.107609 ↗
16. Echo state networks with improved particles warm Optimization algorithm for electricity demand foecasting
17. Hybrid deep learning and GARCH-family models for forecasting volatility of cryptocurrencies
18. Short and mid-term sea surface temperature prediction using time-series satellite data and LSTM-Ada Boost combination approach10.1016/j.rse.2019.111358 ↗
19. A dual-tree complex wavelet enhanced convolutional LSTM neural network for structural health monitoring of automotive suspension10.1016/j.measurement.2019.01.038 ↗
20. Long short-term memory network with multi-resolution singular value decomposition for prediction of bearing performance degradation10.1016/j.measurement.2020.107582 ↗
21. State-of-health estimation and remaining useful life prediction for the lithium-ion battery based on a variant long short term memory neural network10.1016/j.jpowsour.2020.228069 ↗
22. Prediction of watershed pollutant flux based on LSTM neural network
23. Short-term wind power prediction based on CNN-LSTM
24. Temperature prediction based on space-time optimization LSTM deep learning network
25. ∆free-LSTM: An error distribution free deep learning for short-term traffic flow forecasting10.1016/j.neucom.2023.01.009 ↗
26. Parallel State Fusion LSTM-based Early-cycle Stage Lithium-ion Battery RUL Prediction Under Lebesgue Sampling Framework10.1016/j.ress.2023.109315 ↗
27. A CNN-LSTM framework for flight delay prediction10.1016/j.eswa.2023.120287 ↗
28. Coupling prediction model for long-term displacements of arch dams based on long short-term memory network10.1002/stc.2548 ↗
29. Integration of Multi-Gaussian fitting and LSTM neural networks for health monitoring of an automotive suspension component10.1016/j.jsv.2018.05.007 ↗
30. Prediction method of pipe joint opening-closing deformation of immersed tunnel based on singular spectrum analysis and SSA-SVR10.1016/j.apor.2023.103526 ↗
31. Non-invasive Load Decomposition of Substation Based on Deep Convolutional Neural Network and Support Vector Machine
32. Comparative analysis of BPNN, SVR, LSTM, Random Forest, and LSTM-SVR for conditional simulation of non-Gaussian measured fluctuating wind pressures10.1016/j.ymssp.2022.109285 ↗
33. A Study on the Prediction of Book Borrowing Based on ARIMA-SVR Model10.1016/j.procs.2021.05.057 ↗
34. Air pollutant prediction based on ARIMA-WOA-LSTM model10.1016/j.apr.2023.101761 ↗
35. Long Short Term Memory Recurrent Neural Network (LSTM-RNN) Based Workload Forecasting Model For Cloud Datacenters10.1016/j.procs.2017.12.087 ↗
36. Roadside Unit Visibility Prediction Method Based on SVR
37. Multiregion Indirect Resistivity Detection Method for Oil-impregnated Paper in Power Transformer Based on SVR
38. Liu, H. (2020). Stock Index Futures Price Forecasting Scheme Based on LSTM-SVR Hybrid Model, Shanghai Normal University.
39. Trend prediction of structural health status based on EWT and FESN
40. Yang, Y., Xu, L., Han, H., Ren, Z., Wu, K., and Liu, F. (2023). Soft measurement and prediction of refrigerant leakage based on SVR-LSTM. Int. J. Refrig., in press.10.1016/j.ijrefrig.2023.04.021 ↗
41. An EMD-LSTM-SVR model for the short-term roll and sway predictions of semi-submersible10.1016/j.oceaneng.2022.111460 ↗
42. Predicting the settlement of geosynthetic-reinforced soil foundations using evolutionary artificial intelligence technique10.1016/j.geotexmem.2021.04.007 ↗
43. (2006, August 01). Available online: http://cive.seas.wustl.edu/wusceel/ASCE.shm/experim_phase_2.htm.
44. Bayesian Analysis of the Phase II IASC-ASCE Structural Health Monitoring Experimental Benchmark Data10.1061/(ASCE)0733-9399(2004)130:10(1233) ↗