本研究致力於開發一套基於智慧型手機之建築震後即時損傷評估系統。透過建築物內之智慧型手機量測加速度反應，於觸發後數秒內立即判斷是否發生地震事件，若為地震事件則擷取振動訊號，事件結束後透過藍牙微定位(Beacon Micro-Location)技術，知曉手機在建築物較精確之樓層位置以及所在建物之相關參數，再透過Wi-Fi直連(Wi-Fi Direct)技術，與鄰近但不同樓層的手機交換量測之振動訊號與手機方向，據以解算樓層之間的層間位移，最後將最大層間位移比(Interstory Drift Ratio, IDR)與該建築物容許之門檻值進行比較，以決定該建築物可能的震損程度。
然而，手機內電子羅盤所量測之手機方向，容易受環境影響而不準確，以及各手機內置時鐘並不一致。本研究提出利用訊號處裡技術，將手機彼此方向對齊(Orientation Alignment)，並透過手機彼此網路時間校時(Network Time Protocol, NTP)達到時間同步，以降低計算層間位移的誤差。由數值模擬結果表明，若手機彼此無時間延遲，且為較近期(2019後)上市之手機，其角度誤差應可小於10度內、角度之均方根誤差(Root Mean Square Error, RMSE)小於1.25度。最後，本研究利用鋼結構試體之振動台試驗，驗證所提之方法。由試驗結果表明，角度RMSE為4.26度、層間位移比RMSE為0.091%、判別結構損傷之準確率達92.0%，因此利用智慧型手機進行震後建築損傷評估應有其可行性。

This study dedicated to developing a system of damage immediate detection of post-earthquake buildings by smartphones. The scenario is that the smartphones measured the acceleration in the buildings, once the smartphones were triggered by an excitation, an embedded artificial neural network (ANN) model would classify whether the event was earthquake or not within a few seconds. If the triggered motion was considered an earthquake event, then smartphones will record the whole vibration history of this event. After the earthquake event finished, the smartphones used beacon micro-location technique to collect the location of the smartphones in the buildings more precisely and the relevant building information. Furthermore, the smartphones exchanged the vibration data and the phone orientation with the smartphones on adjacent floors by Wi-Fi direct. Using the exchanged data, the smartphones could calculate interstory drifts in each floor. By comparing the maximum interstory drift ratio (IDR) to the allowable threshold, the possible damage level of buildings during the earthquake could be estimated.
However, due to ambient interference (e.g., magnetic field of adjacent electronics), the orientation of the smartphones measured by compass inside isn’t reliable. In addition, each smartphone’s clock drifts with time. Therefore, this study attempted to reduce the errors of the calculated interstory drift by employing signal process techniques and network time protocol (NTP) techniques to correct the orientations and to synchronize the clocks, respectively. Numerical simulation showed that the error of orientation less than 10 degree and the root mean square (RMSE) of orientation is 1.25 degree, if the smartphones are the more recent version, and assuming no time delay. Shaking table tests of a four-story steel building were conducted to verify the proposed methods. The testing results showed that the RMSE of orientation is 4.26 degree, the RMSE of IDR is 0.091% and the accuracy of damage detection of the building is 92.0%. Therefore, the proposed approach is quite feasible.

[1] Hoskere, V., Narazaki, Y., Hoang, T. A., and Spencer Jr, B. F. (2018). “Towards Automated Post-Earthquake Inspections with Deep Learning-Based Condition-Aware Models.” The 7th World Conference on Structural Control and Monitoring.
[2] FEMA. (2013). “HAZUS-MH 2.1 Earthquake Model Technical Manual.” Department of Homeland Security: Washington, DC, USA.
[3] Park, J. W., Sim, S. H., Jung, H. J. and Spencer Jr, B. F. (2013). “Development of a Wireless Displacement Measurement System Using Acceleration Responses.” Sensors 13, 8377-92.
[4] Trapani, D., Maroni, A., Debiasi, E. and Zonta, D. (2015). “In Uncertainty Evaluation of After-Earthquake Damage Detection Strategy.” 2015 IEEE Workshop on Environmental, Energy, and Structural Monitoring Systems (EESMS) Proceedings, Trento, Italy. pp 125-130.
[5] Ozer, E., M. Feng, and D. Feng. (2015). “Citizen Sensors for SHM: Towards a Crowdsourcing Platform.” Sensors 15: p. 14591-14614.
[6] Kong, Q., et al. (2018). “Structural Health Monitoring of Buildings Using Smartphone Sensors.” Seismological Research Letters, 89.
[7] Han, R., et al. (2016). “A Cyber-Physical System for Girder Hoisting Monitoring Based on Smartphones.” Sensors 16: p. 1048.
[8] Ozer, E., D. Feng, and M.Q. Feng. (2017). “Hybrid Motion Sensing and Experimental Modal Analysis Using Collocated Smartphone Camera and Accelerometers.” Measurement Science and Technology, 28(10): p. 105903.
[9] Yu, Y., et al. (2015). “Initial Validation of Mobile-Structural Health Monitoring Method Using Smartphones.” International Journal of Distributed Sensor Networks, 11(2): p. 274391.
[10] Xie, B., J. Li, and X. Zhao. (2019). “Research on Damage Detection of a 3D Steel Frame Model Using Smartphones.” Sensors, 19: p. 745.
[11] Feng, M., et al. (2015). “Citizen Sensors for SHM: Use of Accelerometer Data from Smartphones.” Sensors (Basel), 15(2): p. 2980-98.
[12] Matarazzo, T.J., et al. (2018). “Crowdsensing Framework for Monitoring Bridge Vibrations Using Moving Smartphones.” Proceedings of the IEEE, 106(4): p. 577-593.
[13] Kong, Q., et al. (2018). “Machine Learning Aspects of the MyShake Global Smartphone Seismic Network.” Seismological Research Letters, 90(2A): p. 546-552.
[14] Rochford, K., Kong, Q., et al. (2018). “MyShake: Using Human-Centered Design Methods to Promote Engagement in a Smartphone-Based Global Seismic Network.” Frontiers in Earth Science, 6: p. 237.
[15] Kong, Q., et al. (2018). “Machine Learning in Seismology: Turning Data into Insights.” Seismological Research Letters, 90(1): p. 3-14.
[16] Hsu, T.Y. and Nieh, C.P. (2020). “On-Site Earthquake Early Warning Using Smartphones.” Sensors (Basel), 20(10).
[17] 聶君平。(2019)。「現地型強震預警APP: My Shake Alert」。碩士論文，營建工程系，國立臺灣科技大學。
[18] Kos A, Tomažič S, Umek A. (2016). “Evaluation of Smartphone Inertial Sensor Performance for Cross-Platform Mobile Applications.” Sensors (Basel, Switzerland). 16(4):477.
[19] Narito Kurata. (2017). “An Autonomous Time Synchronization Sensor Device Using a Chip Scale Atomic Clock for Earthquake Observation and Structural Health Monitoring.” The 8th International Conference on Sensor Device Technologies and Applications.
[20] 蔡錴銘，李昭賢，張家銘。(2017)。「試體設計報告」。土木工程學系，國立臺灣大學。
[21] 郭相如。(2019)。「克服旋轉並融合加速度訊號之智慧型單監視器層間相對位移量測技術研發」。碩士論文，營建工程系，國立臺灣科技大學。