Integrated Ensemble Framework for using Strain Gauges and Accelerometers to Monitor Building Stability in Real Time

To ensure safety and soundness in high-load zones, structural health monitoring is crucial. To monitor the stability of buildings, this research introduced the StrucSense ensemble, an ensemble learning approach that integrates time series data from BMA280 accelerometers with spatial data from strain gauges. In this study, the temporal accelerometer data is evaluated using long short-term memory (LSTM), while the spatial strain data is interpreted using a convolutional neural network. We will use this model to predict structural stability through proactive decision-making. The ensemble model is measured using a number of metrics, including accuracy, precision, recall, and F1 score. In addition to identifying potential risks like deformation, fractures, and load imbalances, the Suggested StrucSense Ensemble also makes recommendations for helpful information on load maintenance. We can obtain real-time structural monitoring with our StrucSense Ensemble architecture.