Development of a Cloud-Based Real-Time Building Health Monitoring and Prediction System Using AI and IoT Sensors

In this study, a cloud-based real-time building health monitoring and prediction system using AI and IoT sensors was developed. To predict the building condition, which constitutes time-series data, statistical-based ARIMA and AI-based LSTM prediction models were designed, and the effectiveness of the proposed prediction models was experimentally verified using a 1/8-scaled miniaturized structure. The prediction accuracy in terms of MAPE (less than 1%) was experimentally confirmed to be satisfactory. Moreover, a method for analyzing dimensional structure deformation was developed by combining multiple sensor measurements, and its effectiveness was verified through the case study of a real earthquake-damaged building.

Characterization of Six-Degree-of-Freedom Sensors for Building Health Monitoring

Six-degree-of-freedom (6DoF) sensors measure translation along three axes and rotation around three axes. These collocated measurements make it possible to fully describe building motion without the need for an external reference point. This is an advantage for building health monitoring, which uses interstory drift and building eigenfrequencies to monitor stability. In this paper, IMU50 6DoF sensors are characterized to determine their suitability for building health monitoring. The sensors are calibrated using step table methods and by comparison with earth’s rotation and gravity. These methods are found to be comparable. The sensor’s self-noise is examined through the power spectral density and the Allan deviation of data recorded in a quiet environment. The effect of temperature variation is tested between 14 and 50 °C. It appears that the self-noise of the rotation components increases while the self-noise of the acceleration components decreases with temperature. The comparison of the sensor self-noise with ambient building signal and higher amplitude shaking shows that these sensors are in general not sensitive enough for ambient signal building health monitoring in the frequency domain, but could be useful for monitoring interstory drift and building motion during, for example, strong earthquake shaking in buildings similar to those examined here.