TWI661214B - On-site earthquake early warning system and method thereof accommodating automatic site effect calibration - Google Patents
On-site earthquake early warning system and method thereof accommodating automatic site effect calibration Download PDFInfo
- Publication number
- TWI661214B TWI661214B TW105139172A TW105139172A TWI661214B TW I661214 B TWI661214 B TW I661214B TW 105139172 A TW105139172 A TW 105139172A TW 105139172 A TW105139172 A TW 105139172A TW I661214 B TWI661214 B TW I661214B
- Authority
- TW
- Taiwan
- Prior art keywords
- site
- earthquake
- spectrum ratio
- early warning
- situ
- Prior art date
Links
Landscapes
- Geophysics And Detection Of Objects (AREA)
- Alarm Systems (AREA)
Abstract
一種自動化校正地盤特性之現地型地震預警系統，包含有一現地型地震儀，用來產生一地震預特徵資訊以及一地動資訊；一地震資料庫，耦接於該現地型地震儀，用來根據該地動資訊，產生至少一地盤特性參數；一人工智慧演算模組，耦接於該現地型地震儀及該地震資料庫，用來根據該地震預特徵資訊以及該至少一地盤特性參數，產生一地震預警資訊；以及一地震警報模組，耦接於該人工智慧演算模組，用來發布該地震預警資訊。 An in-situ earthquake early warning system for automatically correcting the characteristics of a site includes an in-situ seismometer to generate an earthquake pre-feature information and a geo-motion information; an earthquake database coupled to the in-situ seismometer and used to Ground motion information to generate at least one site characteristic parameter; an artificial intelligence calculation module coupled to the in-situ seismometer and the seismic database for generating an earthquake based on the seismic pre-feature information and the at least one site characteristic parameter Early warning information; and an earthquake warning module coupled to the artificial intelligence calculation module for publishing the earthquake warning information.
Description
本發明係指一種現地型地震預警系統及相關方法，尤指一種可自動化校正地盤特性之現地型地震預警系統與相關方法。 The invention relates to an on-site earthquake early warning system and related methods, and more particularly to an on-site earthquake early warning system and related methods that can automatically correct the characteristics of a site.
由於地震學、數位自動運算處理、通訊傳輸技術以及用來對大量地震參數進行分析之演算模型的演進，使得地震預警(Earthquake early warning，EEW)技術得以在過去數十年內被廣泛地研究。一般而言，地震預警技術可分為區域型(Regional)地震預警技術及現地型(On-Site)地震預警技術兩類。由於區域型地震預警技術使用來自多個設置於震央附近之地震測站的量測數據，因此區域型地震預警技術估測之地震參數的準確度，通常比現地型地震預警技術的估測準確度高。 Due to the evolution of seismology, digital automatic processing, communication transmission technology, and calculation models used to analyze a large number of seismic parameters, Earthquake early warning (EEW) technology has been widely studied in the past decades. Generally speaking, earthquake early warning technology can be divided into two types: regional earthquake early warning technology and on-site earthquake early warning technology. Because the regional earthquake warning technology uses measurement data from multiple seismic stations located near the epicenter, the accuracy of the seismic parameters estimated by the regional earthquake warning technology is usually better than the accuracy of the on-site earthquake warning technology. high.
然而，對於位處地震活動頻繁地區之建物，時常需面臨地震帶來的破壞及損失。尤其在靠近震央之區域，其震度往往遠大於震央外圍區域之震度，導致在破壞性震波抵達外圍區域前，區域型地震預警所提供的抵達時間(lead-time)有誤。有鑑於此，習知技術實有改進之必要。 However, for buildings located in areas with frequent seismic activity, they often need to face the damage and losses caused by earthquakes. Especially in the area near the epicenter, the magnitude of the earthquake is often much greater than that in the periphery of the epicenter, leading to the wrong lead-time provided by the regional earthquake warning before the destructive seismic wave reaches the peripheral area. In view of this, it is necessary to improve the conventional technology.
因此，本發明主要提供一種可自動化校正地盤特性之現地型地震預警系統及相關方法。 Therefore, the present invention mainly provides an on-site earthquake early warning system and related methods that can automatically correct the characteristics of the site.
本發明揭露一種現地型地震預警系統及方法，其係從單一測站量測到的垂直地表加速度(Vertical Ground Acceleration，VGA)中，擷取地震事件產生的壓力波(P-wave)之部分預特徵，據以預測即將抵達同一測站之地震震度。此外，在考量場址效應(Site Effect)的前提下，測站的地盤條件及地盤參數會影響現地型地震預警系統的預測結果，例如三十公尺深土壤之平均剪力波速(Average Shear-Wave Velocity of the Upper 30 Meters of Sediment，簡稱Vs30)、單站頻譜比(Horizontal-to-Vertical Spectral Ratio，HVSR)及其對應之主頻頻率(dominant frequency)，因此上述參數可作為辨識不同測站及場址效應的地盤參數。據此，本發明透過人工智慧(Artificial Intelligence，AI)演算法，對壓力波之部分預特徵、Vs30、單站頻譜比以及其主頻頻率等參數，進行自動化校正演算，進一步估計最大地表加速度(peak ground acceleration，PGA)，以降低最大地表加速度之估計值與實際量測值間的誤差。如此可提升現地型地震預警系統的準確性，以降低地震所造成的人員傷亡及經濟損失。 The invention discloses an in-situ earthquake early warning system and method, which extracts a part of the pre-wave pressure (P-wave) generated by a seismic event from a vertical ground acceleration (VGA) measured at a single station. Characteristics to predict the magnitude of an earthquake that will soon arrive at the same station. In addition, under the premise of considering the Site Effect, the site conditions and site parameters of the station will affect the prediction results of the on-site earthquake early warning system, such as the average shear wave velocity of 30 meters deep soil (Average Shear- Wave Velocity of the Upper 30 Meters of Sediment (Vs30), Horizontal-to-Vertical Spectral Ratio (HVSR) and its corresponding dominant frequency, so the above parameters can be used to identify different stations And site parameters. According to this, the present invention uses artificial intelligence (Artificial Intelligence, AI) algorithms to perform automatic correction calculations on some pre-characteristics of pressure waves, Vs30, single-station spectrum ratio, and its main frequency frequency to further estimate the maximum surface acceleration ( peak ground acceleration (PGA) to reduce the error between the estimated maximum ground acceleration and the actual measured value. In this way, the accuracy of the on-site earthquake early warning system can be improved to reduce the casualties and economic losses caused by the earthquake.
10‧‧‧現地地震預警系統 10‧‧‧ Local earthquake early warning system
100‧‧‧人工智慧演算模組 100‧‧‧ Artificial Intelligence Calculus Module
110‧‧‧現地型地震儀 110‧‧‧local seismometer
120‧‧‧地震資料庫 120‧‧‧ Earthquake Database
130‧‧‧地震警報模組 130‧‧‧earthquake alarm module
E_info‧‧‧地震預特徵資訊 E_info‧‧‧ Earthquake Pre-Characteristic Information
S_info‧‧‧地動資訊 S_info‧‧‧ground information
S_para‧‧‧地盤特性參數 S_para‧‧‧ Site Characteristics
RST‧‧‧演算結果 RST‧‧‧Calculation result
ALT‧‧‧地震警報 ALT‧‧‧earthquake alert
40‧‧‧流程 40‧‧‧Process
400、401、402‧‧‧步驟 400, 401, 402‧‧‧ steps
第1圖為本發明實施例一現地地震預警系統之示意圖。 FIG. 1 is a schematic diagram of an on-site earthquake early warning system according to the first embodiment of the present invention.
第2A圖至第2D圖繪示在一特定條件下，現地地震預警系統預測最大地表加速度對量測最大地表加速度之相關性。 Figures 2A to 2D show the correlation between the predicted maximum surface acceleration and the measured maximum surface acceleration under a specific condition by the on-site earthquake early warning system.
第3A圖至第3D圖繪示在另一特定條件下，現地地震預警系統預測最大地表 加速度對量測最大地表加速度之相關性。 Figures 3A to 3D show the maximum ground surface predicted by the on-site earthquake early warning system under another specific condition. Correlation between acceleration and measured maximum surface acceleration.
第4圖為本發明實施例一現地地震預警方法之流程圖。 FIG. 4 is a flowchart of an on-site earthquake early warning method according to the first embodiment of the present invention.
人工智慧演算法可做為一種非線性統計資料模型的工具，使得輸入資料與輸出資料間的複雜關聯性可被模型化。使用人工智慧模型開發現地型地震預警系統的做法可分為二階段，於第一階段，人工智慧模型可模擬不同地表運動間的交互作用以及不同傳播路徑所引起的非線性關係，以預測最大地表加速度。接著，人工智慧模型可根據現地型地震儀紀錄的壓力波部分初始訊號來預測地震震波的抵達時間。於第二階段，由於人工智慧模型的迴圈結構，使其可根據輸入資料與輸出資料，反覆地推演出可能的極大結構響應(maximum structural response)以及進行自動校正。 Artificial intelligence algorithms can be used as a tool for non-linear statistical data models, enabling complex correlations between input data and output data to be modeled. The method of using artificial intelligence models to discover ground-type earthquake early warning systems can be divided into two stages. In the first stage, artificial intelligence models can simulate the interaction between different surface movements and the nonlinear relationship caused by different propagation paths to predict the maximum surface. Acceleration. Then, the artificial intelligence model can predict the arrival time of the seismic shock wave based on the initial signal of the pressure wave part recorded by the in-situ seismograph. In the second stage, due to the loop structure of the artificial intelligence model, based on the input data and output data, it can repeatedly derive the possible maximum structural response and perform automatic correction.
換言之，由於人工智慧模型可用來實現壓力波特徵與地震關鍵特徵之間的複雜非線性回歸模型，因此可根據壓力波特徵來預測最大地表加速度；同時，由於人工智慧模型可演算極大化結構響應及進行自動校正，因此可降低預測最大地表加速度的誤差，以準確評估地震可能導致的人員傷亡及經濟損失。人工智慧模型可及於多個子演算法所建立，其包含類神經網路(Artificial Neural Network，ANN)、機器學習(Machine learning)中的監督式學習(Supervised learning)，其中監督式學習包含支撐向量機(Support Vector Machine，SVM)、回歸分析及統計分類等演算法。 In other words, because artificial intelligence models can be used to implement complex nonlinear regression models between pressure wave features and key seismic features, the maximum surface acceleration can be predicted based on pressure wave features; meanwhile, artificial intelligence models can be calculated to maximize structural response and The automatic correction can reduce the error of the predicted maximum surface acceleration to accurately assess the possible casualties and economic losses caused by the earthquake. Artificial intelligence models can be built on multiple sub-algorithms, including supervised learning in Artificial Neural Network (ANN) and machine learning, where supervised learning includes support vectors Support vector machine (SVM), regression analysis and statistical classification algorithms.
第1圖為本發明實施例一現地地震預警系統10之示意圖。現地地震預警系統10包含有一人工智慧演算模組100、一現地型地震儀110、一地震資料庫120 及一地震警報模組130。現地型地震儀110用來產生一地震預特徵資訊E_info至人工智慧演算模組100，以及產生一地動資訊S_info至地震資料庫120。地震資料庫120用來根據地動資訊S_info，產生至少一地盤特性參數S_para至人工智慧演算模組100。 FIG. 1 is a schematic diagram of an on-site earthquake early warning system 10 according to the first embodiment of the present invention. The on-site earthquake early warning system 10 includes an artificial intelligence calculation module 100, an on-site seismometer 110, and an earthquake database 120 And a seismic alert module 130. The on-site seismometer 110 is used to generate an earthquake pre-feature information E_info to the artificial intelligence calculation module 100, and to generate a ground motion information S_info to the seismic database 120. The seismic database 120 is used to generate at least one site characteristic parameter S_para to the artificial intelligence calculation module 100 according to the ground motion information S_info.
人工智慧演算模組100可實現一人工智慧演算模型，用來根據地震預特徵資訊E_info以及地盤特性參數S_para，產生一演算結果RST至地震警報模組130，使地震警報模組130根據演算結果RST來發布一地震警報ALT。其中，地震預特徵資訊E_info指示由一地震事件所產生壓力波之預特徵，且地盤特性參數S_para指示至少一地盤分類、一剪力波速Vs30、一單站頻譜比及單站頻譜比對應之主頻頻率。於一實施例中，剪力波速Vs30、單站頻譜比及單站頻譜比對應之主頻頻率可由另一運算模組運算後(例如，根據剪力波速Vs30及單站頻譜比，進行傅立葉轉換，以計算單站頻譜比對應之主頻頻率)，儲存於地震資料庫120中。 The artificial intelligence calculation module 100 can implement an artificial intelligence calculation model, which is used to generate an operation result RST to the earthquake alarm module 130 according to the seismic pre-feature information E_info and the site characteristic parameter S_para, so that the earthquake alarm module 130 according to the operation result RST To issue an earthquake alert ALT. Among them, the seismic pre-feature information E_info indicates the pre-feature of the pressure wave generated by an earthquake event, and the site characteristic parameter S_para indicates at least one site classification, a shear wave velocity Vs30, a single station spectrum ratio and a single station spectrum ratio. Frequency. In an embodiment, the shear wave velocity Vs30, the single-station spectrum ratio, and the main frequency corresponding to the single-station spectrum ratio can be calculated by another computing module (for example, Fourier transform is performed according to the shear wave velocity Vs30 and the single-station spectrum ratio). To calculate the main frequency corresponding to the single station spectrum ratio) and stored in the seismic database 120.
請注意，現地型地震預警技術運用壓力波及剪力波不同的傳播速率特性來預測地震震度，其中單一測站在地震初期紀錄的壓力波訊號可用來估計主要由剪力波造成的地表搖晃。在實作上，可根據單一測站(如現地型地震儀110)的量測結果，擷取壓力波在最初數秒量測之預特徵以及最後地震震度，再透過經驗回歸法則來預測估計主要由剪力波造成的地表搖晃。 Please note that in situ earthquake early warning technology uses different propagation velocity characteristics of pressure waves and shear waves to predict earthquake magnitude. The pressure wave signals recorded at a single station in the early stage of an earthquake can be used to estimate the surface shake caused mainly by shear waves. In practice, the pre-characteristics of the pressure wave measured in the first few seconds and the last seismic intensity can be captured based on the measurement results of a single station (such as the on-site seismometer 110), and then the empirical regression rule is used to predict the main Ground surface shaking caused by shear waves.
研究顯示，藉由壓力波的六特徵，包含最大加速度絕對值、最大速度絕對值(Pv)、最大位移絕對值、等效主要週期(effective predominant period)、絕對加速度積分(integral of absolute acceleration，IAA)以及速度平方積分，可得
到最準確的最大地表加速度。然而在本發明中，使用最大速度絕對值及絕對加速度積分，所得到最大地表加速度估計值，已足以逼近使用壓力波的六特徵來預測的最大地表加速度估計值。據此，為降低系統運算量，本發明僅使用最大速度絕對值及絕對加速度積分來計算最大地表加速度估計值。於一實施例中，絕對加速度積分的積分區間tp為現地型地震儀110開始測到壓力波訊號的第零秒至第三秒的時間區段，即tp=3秒。絕對加速度積分之計算方程式表示如下：
其中，ü(t)代表在壓力波抵達後，地表運動之加速度時間歷史的垂直分量。於一實施例中，現地型地震儀110紀錄到的所有加速度訊號可一併進行積分，以得到壓力波的對應速度值。 Among them, ü ( t ) represents the vertical component of the time history of the acceleration of the surface motion after the pressure wave arrives. In an embodiment, all acceleration signals recorded by the in-situ seismometer 110 can be integrated together to obtain the corresponding velocity value of the pressure wave.
另一方面，場址效應(On-site effect)為區域地質特性對特定頻段之地震波產生放大作用的現象，在地震學研究中具有相當的重要性。地動係由各種自然現象(如風吹、海浪、雨水等)與人為活動(如交通、機械振動等)所造成的地表小振動。與地震相比，其優點在於振動來源隨時存在，僅須短暫之測量時間即可得到足夠的可用資料。 On the other hand, the on-site effect is a phenomenon in which the regional geological characteristics amplify the seismic waves in a specific frequency band, and it is of considerable importance in seismic research. The ground motion is caused by various natural phenomena (such as wind, waves, rain, etc.) and human activities (such as traffic, mechanical vibration, etc.). Compared with earthquakes, the advantage is that the vibration source exists at any time, and only a short measurement time is needed to obtain sufficient available data.
因此，現地型地震儀110可為一地動量測儀，用來量測地動記錄(即，現地地動資訊S_info)，以評估在特定測站之場址效應。因此，剪力波速Vs30、單站頻譜比及單站頻譜比對應之主頻頻率可由一地震事件或一環境震動事件產生，以將地震事件及環境震動事件(即，地動造成的場址效應)間的交互作用同時納入地震預警之考量。據此，人工智慧演算模組100根據地盤特性參數S_para指示的地盤分類、剪力波速Vs30、單站頻譜比及其對應之主頻頻率，估計最大地表加速度，以降低預測誤差。 Therefore, the on-site seismometer 110 may be a ground motion measuring instrument for measuring a ground motion record (ie, the ground motion information S_info) to evaluate the site effect at a specific station. Therefore, the shear wave velocity Vs30, the single-station spectrum ratio, and the main frequency corresponding to the single-station spectrum ratio can be generated by an earthquake event or an environmental vibration event, so that the earthquake event and the environmental vibration event (ie, the site effect caused by ground motion) The interaction between them is also taken into consideration in earthquake early warning. According to this, the artificial intelligence calculation module 100 estimates the maximum surface acceleration according to the site classification indicated by the site characteristic parameter S_para, the shear wave velocity Vs30, the single-station spectrum ratio and its corresponding main frequency to reduce the prediction error.
於一實施例中，現地地震預警系統10也可運用於區域型地震預警，舉例來說，位於現地地震預警系統10偵測範圍之外的區域，若該區域與偵測範圍之地質環境類似，且對應的場址效應也具一定的相似程度，則現地地震預警系統10偵測到的地震事件亦可用於預測該區域發生的地震事件。 In an embodiment, the local earthquake warning system 10 can also be used for regional earthquake warning. For example, if the area is outside the detection range of the local earthquake warning system 10, if the area is similar to the geological environment of the detection range, And the corresponding site effect also has a certain degree of similarity, the earthquake event detected by the on-site earthquake early warning system 10 can also be used to predict the earthquake event in the area.
於一實施例中，剪力波速Vs30對應的地盤分類，可依據美國國家地震減災計畫(National Earthquake Hazard Reduction Program，簡稱NEHRP)所制定的地盤特性分類而設定，參見如下表格1。 In an embodiment, the site classification corresponding to the shear wave velocity Vs30 can be set according to the site characteristic classification established by the National Earthquake Hazard Reduction Program (NEHRP), as shown in Table 1 below.
為探究壓力波預特徵、絕對加速度積分、地盤分類、剪力波速Vs30、單站頻譜比及其對應主頻等參數，對預測最大地表加速度之準確度的影響程度，人工智慧演算模組100透過人工智慧演算法，根據不同輸入參數條件，計算出預測最大地表加速度誤差之標準差，可歸納為如下表格2。 In order to investigate the effects of pressure wave pre-characteristics, absolute acceleration integration, site classification, shear wave speed Vs30, single station frequency ratio and its corresponding main frequency on the accuracy of predicting the maximum surface acceleration, the artificial intelligence calculation module 100 uses The artificial intelligence algorithm calculates the standard deviation of the predicted maximum surface acceleration error according to different input parameter conditions, which can be summarized as Table 2 below.
條件(a)：Pv、IAA Condition (a): Pv, IAA
條件(b)：Pv、IAA、NEHRP地盤分類 Condition (b): Pv, IAA, NEHRP site classification
條件(c)：Pv、IAA、Vs30 Condition (c): Pv, IAA, Vs30
條件(d)：Pv、IAA、單站頻譜比主頻 Condition (d): Pv, IAA, single station spectrum ratio than the main frequency
條件(e)：Pv、IAA、二十單站頻譜比 Condition (e): Pv, IAA, Twenty Single Station Spectrum Ratio
其中，單站頻譜比主頻為二十筆單站頻譜比資料中，最大單站頻譜比所對應的頻率。二十單站頻譜比為相同測站紀錄的所有地震紀錄之單站頻譜比曲線的平均值，換言之，若兩個不同震動事件是由同一測站所紀錄，其可能會有相同的主頻。 Among them, the single-station spectrum ratio main frequency is the frequency corresponding to the largest single-station spectrum ratio among the twenty single-station spectrum ratio data. The 20 single station spectrum ratio is the average of the single station spectrum ratio curves of all seismic records at the same station record. In other words, if two different vibration events are recorded by the same station, they may have the same main frequency.
第2A圖至第2D圖繪示在條件(c)下，現地地震預警系統10預測最大地表加速度對量測最大地表加速度之相關性。第3A圖至第3D圖繪示在條件(e)下，現地地震預警系統10預測最大地表加速度對量測最大地表加速度之相關性。根據表格2及第2A圖至第2D圖可知，地盤分類B、C、D在條件(c)下預測 之標準差低於在條件(a)下預測之標準差。然而，地盤分類A、E在條件(c)下預測之標準差高於在條件(a)、(b)下預測之標準差。根據表格2及第3A圖至第3D圖可知，地盤分類A、B、C、D、E在條件(e)下預測之標準差最低。 Figures 2A to 2D show the correlation between the predicted maximum surface acceleration and the measured maximum surface acceleration under the condition (c). Figures 3A to 3D show the correlation between the predicted maximum surface acceleration and the measured maximum surface acceleration under the condition (e). According to Table 2 and Figures 2A to 2D, it can be known that the site classifications B, C, and D are predicted under condition (c). The standard deviation is lower than the standard deviation predicted under condition (a). However, the standard deviations predicted for site classifications A and E under condition (c) are higher than the standard deviations predicted under condition (a) and (b). According to Table 2 and Figures 3A to 3D, it can be known that the standard deviation of the prediction of site classifications A, B, C, D, and E under condition (e) is the lowest.
由此可見，壓力波預特徵、絕對加速度積分及二十單站頻譜比為影響最大地表加速度之準確度的關鍵，其中二十單站頻譜比是根據地震紀錄所計算，而非根據環境震動紀錄。 It can be seen that the pressure wave pre-characteristics, the absolute acceleration integral, and the spectrum ratio of the 20 single stations are the key factors that affect the accuracy of the maximum surface acceleration. .
上述關於現地地震預警系統10之運作可進一步歸納為一現地地震預警流程40，如第4圖所示。現地地震預警流程40包含以下步驟： The operation of the on-site earthquake early warning system 10 can be further summarized as an on-site earthquake early warning process 40, as shown in FIG. The on-site earthquake warning process 40 includes the following steps:
步驟400：開始。 Step 400: Start.
步驟401：透過人工智慧演算模型，根據地震預特徵資訊以及至少一地盤特性參數，產生地震預警資訊；其中地震預特徵資訊指示壓力波之預特徵，且至少一地盤特性參數包含地盤分類、剪力波速Vs30、單站頻譜比及其對應之主頻頻率。 Step 401: Use artificial intelligence calculation model to generate earthquake early warning information according to the seismic pre-feature information and at least one site characteristic parameter; the seismic pre-feature information indicates the pre-feature of the pressure wave, and at least one site characteristic parameter includes site classification, shear force Wave speed Vs30, single station spectrum ratio and its corresponding main frequency.
步驟402：結束。 Step 402: End.
關於現地地震預警流程40的詳細說明可參考上述，於此不贅述。 For a detailed description of the on-site earthquake early warning process 40, reference may be made to the above, and details are not described herein.
綜上所述，本發明透過人工智慧演算模型，對壓力波之部分預特徵、地盤分類、剪力波速Vs30、單站頻譜比以及其主頻頻率等參數，進行自動化校正演算，進一步估計最大地表加速度，以降低最大地表加速度之估計值與實際量測值間的誤差。因此，本發明可提升現地型地震預警系統的準確性，以降低地震所造成的人員傷亡及經濟損失。 以上所述僅為本發明之較佳實施例，凡依本發明申請專利範圍所做之均等變化與修飾，皆應屬本發明之涵蓋範圍。 In summary, the present invention uses an artificial intelligence calculation model to perform automatic correction calculations on some pre-characteristics of pressure waves, site classification, shear wave speed Vs30, single-station spectrum ratio, and its main frequency, etc., to further estimate the maximum surface Acceleration to reduce the error between the estimated maximum surface acceleration and the actual measured value. Therefore, the present invention can improve the accuracy of the on-site earthquake early warning system to reduce the casualties and economic losses caused by the earthquake. The above description is only a preferred embodiment of the present invention, and all equivalent changes and modifications made in accordance with the scope of patent application of the present invention shall fall within the scope of the present invention.
Claims (18)
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW105139172A TWI661214B (en) | 2016-11-29 | 2016-11-29 | On-site earthquake early warning system and method thereof accommodating automatic site effect calibration |
| JP2017000377A JP6429042B2 (en) | 2016-11-29 | 2017-01-05 | Local earthquake early warning system and related method for automatic calibration of ground characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW105139172A TWI661214B (en) | 2016-11-29 | 2016-11-29 | On-site earthquake early warning system and method thereof accommodating automatic site effect calibration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| TW201819955A TW201819955A (en) | 2018-06-01 |
| TWI661214B true TWI661214B (en) | 2019-06-01 |
Family
ID=62493868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| TW105139172A TWI661214B (en) | 2016-11-29 | 2016-11-29 | On-site earthquake early warning system and method thereof accommodating automatic site effect calibration |
Country Status (2)
| Country | Link |
|---|---|
| JP (1) | JP6429042B2 (en) |
| TW (1) | TWI661214B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110032975B (en) * | 2019-04-15 | 2021-09-07 | 禁核试北京国家数据中心 | Seismic facies picking method |
| JP6985621B2 (en) | 2019-11-26 | 2021-12-22 | ダイキン工業株式会社 | Air conditioning management system |
| CN111487676B (en) * | 2020-03-31 | 2023-04-11 | 中国地震局工程力学研究所 | Method for synthesizing earthquake motion field by applying support vector machine, principal component analysis and particle swarm optimization in machine learning |
| CN111751133B (en) * | 2020-06-08 | 2021-07-27 | 南京航空航天大学 | Intelligent fault diagnosis method of deep convolutional neural network model based on non-local mean embedding |
| CN112630827B (en) * | 2020-12-07 | 2024-02-02 | 中国地震局工程力学研究所 | Surface acceleration peak parameter prediction method and system |
| CN113379105B (en) * | 2021-05-21 | 2022-05-31 | 浙江大学 | Site earthquake liquefaction disaster rapid evaluation method based on artificial intelligence |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110255371A1 (en) * | 2009-01-09 | 2011-10-20 | Charlie Jing | Hydrocarbon Detection With Passive Seismic Data |
| US20120123983A1 (en) * | 2010-11-15 | 2012-05-17 | Tectosense Ltd. | Automatic systems and methodologies for earthquake prediction and warning |
| TW201310053A (en) * | 2011-08-19 | 2013-03-01 | Nat Applied Res Laboratories | On-site instant earthquake analysis system and method, and storage medium thereof |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2011343454B2 (en) * | 2010-12-17 | 2015-07-30 | Seismic Warning Systems, Inc. | Earthquake warning system |
| JP6177628B2 (en) * | 2013-08-29 | 2017-08-09 | 公益財団法人鉄道総合技術研究所 | Immediate ground motion prediction method using underground ground motion |
| JP6399947B2 (en) * | 2015-02-25 | 2018-10-03 | Kddi株式会社 | Earthquake determination apparatus, system, program and method capable of earthquake determination by learning |
-
2016
- 2016-11-29 TW TW105139172A patent/TWI661214B/en active
-
2017
- 2017-01-05 JP JP2017000377A patent/JP6429042B2/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110255371A1 (en) * | 2009-01-09 | 2011-10-20 | Charlie Jing | Hydrocarbon Detection With Passive Seismic Data |
| US20120123983A1 (en) * | 2010-11-15 | 2012-05-17 | Tectosense Ltd. | Automatic systems and methodologies for earthquake prediction and warning |
| TW201310053A (en) * | 2011-08-19 | 2013-03-01 | Nat Applied Res Laboratories | On-site instant earthquake analysis system and method, and storage medium thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2018087799A (en) | 2018-06-07 |
| TW201819955A (en) | 2018-06-01 |
| JP6429042B2 (en) | 2018-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI661214B (en) | On-site earthquake early warning system and method thereof accommodating automatic site effect calibration | |
| KR102027252B1 (en) | Methods for differentiation of earthquake signal and prediction of earthquake intensity using randomly generated artificial seismic training data for an arbitrary zone | |
| Schiappapietra et al. | Modelling the spatial correlation of earthquake ground motion: Insights from the literature, data from the 2016–2017 Central Italy earthquake sequence and ground-motion simulations | |
| US9465121B2 (en) | System and method for on-site instant seismic analysis | |
| US20200217979A1 (en) | Observation-driven method based on iir wiener filter for microseismic data denoising | |
| Mimoglou et al. | Explicit determination of the pulse inherent in pulse‐like ground motions | |
| TWI809293B (en) | Earthquake observation device, earthquake observation method, and recording medium for recording earthquake observation program | |
| TW201435381A (en) | Artificial intelligence earthquake early warning method | |
| US10317549B2 (en) | Systems and methods for non-parametric autopicking of seismic wave features from seismic data | |
| CN114222934A (en) | Earthquake observation apparatus, earthquake observation method, and recording medium | |
| CN107272061A (en) | A kind of automatic correlation method of infrasound signals and seismic events | |
| Bindi et al. | On-site structure-specific real-time risk assessment: perspectives from the REAKT project | |
| McBrearty et al. | Basal seismicity of the Northeast Greenland ice stream | |
| JP4506625B2 (en) | Earthquake motion prediction system using real-time earthquake information | |
| Ghorbani et al. | A modern method to improve of detecting and categorizing mechanism for micro seismic events data using boost learning system | |
| Zhu et al. | Support vector machine‐based rapid magnitude estimation using transfer learning for the Sichuan–Yunnan region, China | |
| KR101923166B1 (en) | Method for correcting amplitude magnitude of seismic signal extracted from seismic ambient noise | |
| KR101914657B1 (en) | Method for extracting phase and amplitude information of seismic signal from seismic ambient noise | |
| Raghu Kanth et al. | Stochastic finite fault modeling of subduction Zone Earthquakes in Northeastern India | |
| TWI636276B (en) | Method of determining earthquake with artificial intelligence and earthquake detecting system | |
| CN103376465A (en) | System and method for earthquake real-time analysis of building floor and storage medium | |
| Boroschek et al. | Evaluation of the environmental effects on a medium rise building | |
| Huang et al. | Performance of on-site earthquake early warning system using strong-motion records from recent earthquakes | |
| US11562655B2 (en) | Aircraft rescue systems and methods using predictive models | |
| Ierimonti et al. | Application of Bayesian FE model selection for SHM of a monumental masonry palace through semi-supervised learning |