This paper aims to solve the problem of dynamic changes in bridges in complex environments. Based on the DBN modeling method, real-time classification prediction of bridge technical status is realized to timely discover potential risks. The Dynamic Bayesian Network (DBN) model is introduced, and a bridge technical status prediction method based on real-time data is proposed. By modeling time series data and multivariate relationships, the changes in the bridge technical status are predicted, and the bridge health status is updated in real time, thereby achieving early warning of potential risks. The experimental results show that by using bridge data over a 6-month period for prediction and identification, the analysis and prediction accuracy rate reached 96.7%. This indicates that the DBN model has high reliability and stability in prediction and classification tasks, and can accurately identify samples of different categories, especially in dealing with complex bridge damage detection scenarios, showing strong performance, and its effect is greatly improved compared with other traditional models. Similarly, this paper also conducted experiments in multiple occasions to test the model in different complex environments, and its accuracy rates were 92.5%, 91.8%, 90.2%, and 91% respectively. Bridge detection through the DBN model can efficiently process complex time series data, predict the health status of the bridge in real time, improve the accuracy of monitoring and early warning capabilities, and provide more reliable bridge safety protection.
AbdallahAMAtaderoRAOzbekME. A state-of-the-art review of bridge inspection planning: current situation and future needs. J Bridge Eng2022; 27: 03121001.
2.
JeongESeoJWackerJ. Literature review and technical survey on bridge inspection using unmanned aerial vehicles. J Perform Construct Facil2020; 34: 04020113.
3.
KuraniADoshiPVakhariaA, et al.A comprehensive comparative study of artificial neural network (ANN) and support vector machines (SVM) on stock forecasting. Ann Data Sci2023; 10: 183–208.
4.
ZhangHZouQJuY, et al.Distance-based support vector machine to predict DNA N6-methyladenine modification. Curr Bioinf2022; 17: 473–482.
5.
AbdolrasolMGMHussainSMSUstunTS, et al.Artificial neural networks based optimization techniques: a review. Electronics2021; 10: 2689.
6.
YangGRWangXJ. Artificial neural networks for neuroscientists: a primer. Neuron2020; 107: 1048–1070.
7.
AdeniranIAAbhulimenAOObiki-OsafieleAN, et al.Data-Driven approaches to improve customer experience in banking: techniques and outcomes. Int J Manage Entrepreneurship Res2024; 6: 2797–2818.
8.
ChafjiriASGheibiMChahkandiB, et al.Enhancing flood risk mitigation by advanced data-driven approach. Heliyon2024; 10(18): e37758.
9.
SaidinSSJamadinAAbdul KudusS, et al.An overview: the application of vibration-based techniques in bridge structural health monitoring. Int J Concr Struct Mater2022; 16: 69.
10.
CampbellLEConnorRJWhiteheadJM, et al.Benchmark for evaluating performance in visual inspection of fatigue cracking in steel bridges. J Bridge Eng2020; 25: 04019128.
11.
MaZChungJLiuP, et al.Bridge displacement estimation by fusing accelerometer and strain gauge measurements. Struct Control Health Monit2021; 28: e2733.
12.
LiuZXiaoGLiuH, et al.Multi-sensor measurement and data fusion. IEEE Instrum Meas Mag2022; 25: 28–36.
13.
FlahMNunezIBen ChaabeneW, et al.Machine learning algorithms in civil structural health monitoring: a systematic review. Arch Comput Methods Eng2021; 28: 2621–2643.
14.
AlhijaziMZeeshanQQinZ, et al.Finite element analysis of natural fibers composites: a review. Nanotechnol Rev2020; 9: 853–875.
15.
IbrahimAMirjaliliSEl-SaidM, et al.Wind speed ensemble forecasting based on deep learning using adaptive dynamic optimization algorithm. IEEE Access2021; 9: 125787–125804.
16.
SheykhmousaMMahdianpariMGhanbariH, et al.Support vector machine versus random forest for remote sensing image classification: a meta-analysis and systematic review. IEEE J Sel Top Appl Earth Obs Remote Sens2020; 13: 6308–6325.
17.
UllahISuXZhuJ, et al.Evaluation of localization by extended kalman filter, unscented kalman filter, and particle filter-based techniques. Wireless Commun Mobile Comput2020; 2020: 8898672.
18.
Vurtur BadarinathPChierichettiMDavoudi KakhkiF. A machine learning approach as a surrogate for a finite element analysis: status of research and application to one dimensional systems. Sensors2021; 21: 1654.
19.
RizzoPEnshaeianA. Challenges in bridge health monitoring: a review. Sensors2021; 21: 4336.
20.
WanSGuanSTangY. Advancing bridge structural health monitoring: insights into knowledge-driven and data-driven approaches. J Data Sci Intell Syst2024; 2: 129–140.
21.
OthmanGZeebareeDQ. The applications of discrete wavelet transform in image processing: a review. J Soft Comput Data Min2020; 1: 31–43.
22.
ZhangNCaniniKSilvaS, et al.Fast linear interpolation. ACM J Emerging Technol Comput Syst (JETC)2021; 17: 1–15.
23.
EleftheriadisCKarakonstantisG. Energy-efficient fast Fourier transform for real-valued applications. IEEE Trans Circuits Syst II: Express Briefs2022; 69: 2458–2462.
24.
ScutariM. Bayesian Network models for incomplete and dynamic data. Stat Neerl2020; 74: 397–419.
25.
DongGHanWWangY. Dynamic Bayesian network-based lithium-ion battery health prognosis for electric vehicles. IEEE Trans Ind Electron2020; 68: 10949–10958.
26.
GaoHSuHCaiY, et al.Trajectory prediction of cyclist based on dynamic Bayesian network and long short-term memory model at unsignalized intersections. Sci China Inf Sci2021; 64: 172207.
27.
CongSZhouY. A review of convolutional neural network architectures and their optimizations. Artif Intell Rev2023; 56: 1905–1969.
28.
LindemannBMüllerTVietzH, et al.A survey on long short-term memory networks for time series prediction. Procedia Cirp2021; 99: 650–655.
29.
GhimireSYaseenZMFarooqueAA, et al.Streamflow prediction using an integrated methodology based on convolutional neural network and long short-term memory networks. Sci Rep2021; 11: 17497.
30.
ChenCZhangQKashaniMH, et al.Forecast of rainfall distribution based on fixed sliding window long short-term memory. Eng Appl Comput Fluid Mech2022; 16: 248–261.
31.
WangXZhaoQXiR, et al.Review of bridge structural health monitoring based on GNSS: from displacement monitoring to dynamic characteristic identification. IEEE Access2021; 9: 80043–80065.
32.
Kang JSChungKHongEJ. Multimedia knowledge-based bridge health monitoring using digital twin. Multimedia Tools Appl2021; 80: 34609–34624.
33.
LiuHChenCGuoZ, et al.Overall grouting compactness detection of bridge prestressed bellows based on RF feature selection and the GA-SVM model. Constr Build Mater2021; 301: 124323.
34.
ReyadMSarhanAMArafaM. A modified Adam algorithm for deep neural network optimization. Neural Comput Appl2023; 35: 17095–17112.
35.
XindeLIDunkinFDezertJ. Multi-source information fusion: progress and future. Chin J Aeronaut2024; 37: 24–58.
36.
TangYChenYZhouD. Measuring uncertainty in the negation evidence for multi-source information fusion. Entropy2022; 24: 1596.
37.
ElmazFEyckermanRCasteelsW, et al.CNN-LSTM architecture for predictive indoor temperature modeling. Build Environ2021; 206: 108327.
38.
RostamianAO’HaraJG. Event prediction within directional change framework using a CNN-LSTM model. Neural Comput Appl2022; 34: 17193–17205.
39.
OmerMMargettsLMoslehMH, et al.Inspection of concrete bridge structures: case study comparing conventional techniques with a virtual reality approach. J Bridge Eng2021; 26: 05021010.
40.
LeeJHYoonSKimB, et al.A new image-quality evaluating and enhancing methodology for bridge inspection using an unmanned aerial vehicle. Smart Struct Syst2021; 27: 209–226.
