研究生: |
黃昭文 Chao-Wen Huang |
---|---|
論文名稱: |
卷積神經網路應用於初達波預估當站最大地表加速度之研究 An application of CNN to early prediction of PGA using on-site P-waves |
指導教授: |
許丁友
Ting-Yu Hsu |
口試委員: |
周瑞生
Jui-Sheng Chou 郭俊翔 Chun-Hsiang Kuo 張家銘 Chia-Ming Chang |
學位類別: |
碩士 Master |
系所名稱: |
工程學院 - 營建工程系 Department of Civil and Construction Engineering |
論文出版年: | 2020 |
畢業學年度: | 108 |
語文別: | 中文 |
論文頁數: | 102 |
中文關鍵詞: | P波 、深度學習 、卷積神經網路 、現地型地震預警 |
外文關鍵詞: | P-wave, deep learning, convolution neural network, earthquake early warning |
相關次數: | 點閱:266 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
強震預警主要目的為在強震波來臨前,能準確地發佈警報,以避免人員的傷亡與財產的損失,同時避免因為過度預測的誤報,所造成社會成本的損失。因此,準確的預測該次地震的震度,為強震預警技術研發的首要目標之一。近年來,得益於電腦硬體設備的進步,深度學習的應用有了大幅度的成長,其中卷積神經網路(CNN)的出現,使得影像辨識領域能有更多的發展性。過去已有研究使用初達波的萃取出之特徵參數,透過支援向量機(SVM)等人工智慧進行訓練,以預測該次地震於當地即將發生之最大地表加速度(PGA),亦即所謂的現地型強震預警技術。本研究省去萃取初達波參數的步驟,直接以P波抵達後三秒的加速度歷時資料與其頻譜作為輸入,透過CNN進行訓練,預測出該次地震之PGA。在相同的地震資料下,SVR模型對於預測PGA的均方根對數誤差為0.748,而CNN則為0.4911,顯見本研究所提出之方法可以明顯提升PGA預測準確程度。
The Earthquake Early Warning (EEW) systems aim to alert before the arrival of strong seismic waves, thus to prevent or reduce casualties and economic loss. The main purpose of this study is to predict the intensity of an earthquake more accurately. Recently, benefit from the progress of computer hardware, deep learning techniques improve substantially. The advent of the Convolution Neural Network (CNN) makes image recognition more feasible. Previous studies had already used some characteristic parameters of the primary wave to predict the peak ground acceleration (PGA) of the same earthquake at the same site using a support vector machine or an artificial neural network. This study uses acceleration time history and its Fourier spectrum amplitude of the first three seconds after P-wave arrival as input data of a CNN to predict PGA. Based on the results of 10,000 earthquake data, the root mean square lognormal error (RMSLE) of the predicted PGA values base on the SVM model of the previous study was 0.748, while the one using the CNN model was only 0.4911.
Hsu, T.-Y., et al., Rapid on-site peak ground acceleration estimation based on support vector regression and P-wave features in Taiwan. Soil Dynamics and Earthquake Engineering, 2013. 49: p. 210-217.
2. Satriano, C., et al., Earthquake early warning: Concepts, methods and physical grounds. Soil Dynamics and Earthquake Engineering, 2011. 31(2): p. 106-118.
3. Gao, Y. and K.M. Mosalam, Deep Transfer Learning for Image-Based Structural Damage Recognition. Computer-Aided Civil and Infrastructure Engineering, 2018. 33(9): p. 748-768.
4. Cha, Y.-J., W. Choi, and O. Büyüköztürk, Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks. Computer-Aided Civil and Infrastructure Engineering, 2017. 32(5): p. 361-378.
5. Li, D., et al., Acoustic emission wave classification for rail crack monitoring based on synchrosqueezed wavelet transform and multi-branch convolutional neural network. Structural Health Monitoring, 2020: p. 147592172092279.
6. Shrestha, A. and J. Dang, Deep Learning-Based Real-Time Auto Classification of Smartphone Measured Bridge Vibration Data. Sensors, 2020. 20(9).
7. Wu, R.-T. and M. Jahanshahi, Deep Convolutional Neural Network for Structural Dynamic Response Estimation and System Identification. Journal of Engineering Mechanics, 2019. 145: p. 04018125.
8. Shi, B., et al., An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. 2016. 39(11): p. 2298-2304.
9. Yu, Y., et al., A novel deep learning-based method for damage identification of smart building structures. Structural Health Monitoring, 2018. 18(1): p. 143-163.
10. Meier, M.-A., How “good” are real-time ground motion predictions from Earthquake Early Warning systems? Journal of Geophysical Research: Solid Earth, 2017. 122(7): p. 5561-5577.
11. Hoshiba, M., et al., How precisely can we anticipate seismic intensities? A study of uncertainty of anticipated seismic intensities for the Earthquake Early Warning method in Japan. Earth, Planets and Space, 2010. 62(8): p. 611-620.
12. 河角廣, 震度と震度階. 地震 第1輯, 1943. 15(1): p. 6-12.