Advanced Predictive Structural Health Monitoring in High-Rise Buildings Using Recurrent Neural Networks

• Published in: Buildings (Basel) Vol. 14; no. 10; p. 3261
• Main Authors: Ghaffari, Abbas, Shahbazi, Yaser, Mokhtari Kashavar, Mohsen, Fotouhi, Mohammad, Pedrammehr, Siamak
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.10.2024
• Subjects: Accuracy; Algorithms; Automation; Bridges; Buildings; Datasets; Deep learning; Earthquakes; FEA; Finite element method; Fourier transforms; Genetic algorithms; Genetic diversity; High rise buildings; high-rise structure; Information management; Lateral displacement; Lateral loads; Long short-term memory; LSTM; Machine learning; Methods; Multiple objective analysis; Neural networks; optimization; Optimization techniques; Real time; Recurrent neural networks; RNN; Seismic engineering; Sensors; SHM; Skyscrapers; Structural health monitoring; Structural integrity; Tall buildings; Typhoons; Vertical loads; Vibration; Wavelet transforms; Iran
• ISSN: 2075-5309; 2075-5309
• DOI: 10.3390/buildings14103261

This study proposes a machine learning (ML) model to predict the displacement response of high-rise structures under various vertical and lateral loading conditions. The study combined finite element analysis (FEA), parametric modeling, and a multi-objective genetic algorithm to create a robust and diverse dataset of loading scenarios for developing a predictive ML model. The ML model was trained using a recurrent neural network (RNN) with Long Short-Term Memory (LSTM) layers. The developed model demonstrated high accuracy in predicting time series of vertical, lateral (X), and lateral (Y) displacements. The training and testing results showed Mean Squared Errors (MSE) of 0.1796 and 0.0033, respectively, with R2 values of 0.8416 and 0.9939. The model’s predictions differed by only 0.93% from the actual vertical displacement values and by 4.55% and 7.35% for lateral displacements in the Y and X directions, respectively. The results demonstrate the model’s high accuracy and generalization ability, making it a valuable tool for structural health monitoring (SHM) in high-rise buildings. This research highlights the potential of ML to provide real-time displacement predictions under various load conditions, offering practical applications for ensuring the structural integrity and safety of high-rise buildings, particularly in high-risk seismic areas.