Long-term structural health monitoring for bridge based on back propagation neural network and long and short-term memory

Abstract

Bridges are critical components of transportation infrastructure. To ensure the long-term performance of bridges and the safety of the public, regular inspections are required during their service. Structural performance assessments are subject to various conditions. Structural deterioration is caused by complex environmental and operational conditions (EOCs) including temperature changes, truckloads, chemical corrosion, etc. In this study, an in-site structural health monitoring (SHM) system is designed and deployed on the Caohekou Bridge in China with a series of sensors installed, providing continuous real-time data for 4 years. Crack width, vertical deformation, concrete strains, temperature, longitudinal displacement and acceleration are monitored and assessed. Time-history monitoring data are comprehensively analysed to advance our understanding of structural deterioration caused by time and temperature. It is very common to lose data during the monitoring process, especially in the long-term run. To overcome the challenge of missing data package and to realize early warning, methods including an SHM systems face, a back propagation neural network and a long short-term memory are proposed to predict the bridge responses under the change of EOCs. It has been proved that the performance of predicted crack widths is close to that of the measured value, and the trend of change is consistent. Such results indicate that approaches proposed that quantitatively assess in-service structure are promising. Therefore, effective and efficient maintenance decisions can be made to ensure an immediate response, long-term safety and serviceability of bridge structures.

Financial Risk Early Warning Model for Listed Companies Using BP Neural Network and Rough Set Theory

“…BPNN can use different training functions, including trainlm, traingc, and traingd [45]. Due to the moderate model size, comparative analysis is conducted and the trainlm function is selected to improve the algorithm's efficiency [46], [47]. In conclusion, Figure 4 illustrates the algorithm flow of BPNN in FREW for listed companies.…”

Restoration of a Landmark Balanced Cantilever Bridge Considering Different Resilience and Sustainability Strategies

“…As a way to bypass many of the above-mentioned considerations our team proposes a digitalized approach to damage assessment, which can be applied on a wide range of structural assets (both residential and infrastructure) and relies heavily on state-of-the-art computational tools. Numerous approaches with different levels of interaction with the structure have been proposed through recent years, for example deflection-based monitoring system using sensor and signal processing technology [17] or connected pipe systems [18]. However, no approach is currently streamlined and considered as most optimum due to the fluctuating accuracy levels between the techniques in various occasions.…”

Influence of the ANN Hyperparameters on the Forecast Accuracy of RAC’s Compressive Strength

“…Due to the simplicity of implementing the BP algorithm, most studies developed and published in the civil engineering field that use ANNs opt for BP to train neural networks [18][19][20][21][22][23][24][25][26][27][28][29]. Moselhi et al [30] were the first to investigate the application of artificial neural networks for modeling construction-related problems.…”