teacher 活動時間：112年2月18日（星期六）13時00分
活動地點：國家地震工程中心101會議室（台北市大安區辛亥路三段200號）
活動課程：
1.耐震弱層補強計畫簡介與審查注意事項 (講師：國家地震工程研究中心)
2.耐震弱層補強工法之設計、評估與施工-開口磚牆耐震補強工法 (講師：施忠賢結構技師事務所 施忠賢技師)
3.耐震弱層補強工法之設計、評估與施工-軟補強典型街屋簡易補強工法 (講師：國立成功大學建築學系 杜怡萱教授)
4.耐震弱層補強工法之設計、評估與施工-超高性能纖維混凝土UHPC補強工法 (講師：國立成功大學土木工程學系 洪崇展教授)
*報名網址：https://conf.ncree.org.tw/indexCht.aspx?n=A11202180 (報名人數上限80人)
*此活動可申請建築師、技師及公務人員積分(點)
本期期刊為特刊
人工智慧在結構工程之應用特刊
客座主編：林子剛
「結構工程」季刊第146期(第37卷第4期)
電子檔已經上線。歡迎會員登入後下載全文。
中文網址: 第37卷第4期 (2022)
英文網址: Vol.37 / No.4 (2022)
若有任何意見歡迎 email 至 csse@csse.org.tw。
人工智慧在結構工程之應用特刊
客座主編：林子剛
| 標題 | 「人工智慧在結構工程之應用」引言 |
|---|---|
| 作者 | 林子剛 |
|
近年人工智慧(AI,artificial intelligence)正對各個領域帶來前所未有革命性的影響，土木結構工程亦朝向「智慧化」邁進。結構工程導入人工智慧，運用在大量的資料彙整、分析及尋找規律上，透過AI 能有效且快速地節省人力，可直接對接進入施工過程，讓大量常規項目規劃和設計變得快速，比起以往人工判讀更具備效能與效率。美國國家科學基金會（NSF）開發了一套名為BRAILS（大規模人工智慧建築識別）的工具，可以檢測城市建築在地震、颶風或海嘯中可能面臨的風險，此即是人工智慧結合土木結構工程的案例之一。 結構工程期刊企盼藉由此次特刊的機會，向各界介紹國內人工智慧在結構工程應用之成果。本特刊收錄了「結合神經網路熵與卷積神經網路於結構健康診斷」、「使用機器學習和統計資訊進行異常訊號檢測和分類」、「深度學習於提升地震模擬振動臺加速度性能之研究」、「含巡檢規劃、劣化辨識、損傷量化之進階建物劣化檢測架構」及「基於深度學習之合成配電網絡建置研究」。希冀藉由這些篇章的介紹，能更深入瞭解人工智慧在結構工程之應用發展與趨勢，讓臺灣在土木結構工程專案管理實務中，嘗試建立類似的工具，進而保障建築安全。 國立陽明交通大學土木工程學系 林子剛 教授 謹誌 |
| 標題 | 含巡檢規劃、劣化辨識、損傷量化之進階建物劣化檢測架構 |
|---|---|
| 作者 | 許舜翔、許筠曼、洪昊天、林禹齊、張家銘、陳宗珷、陳俊仲 |
| 關鍵字 | 目視檢測、損傷偵測、損傷量化、深度學習 |
| 摘要 | 目視檢測常用於結構檢測中，以快速評估建物中構件或材料之耐用性，及尋找可能的損傷。然而，傳統目視檢測相當耗費人力及時間，鑒於以上問題，本研究開發一個進階的建物劣化檢測架構，其中功能包括巡檢規劃、即時劣化識別、損傷程度判別及記錄詳細的損傷狀況。於該架構中，首先規劃巡檢草圖，提供檢測時最有效率檢測路徑；接著本研究使用Scaled-YOLOv4，進行損傷物件偵測，該方法於大規模場域中，也能快速檢測損傷，並使用SOLOv2 模型，對混凝土裂縫位置進行像素等級之實例分割，以利更精確的裂縫量化；最後，根據檢測到的劣化嚴重性及面積大小，對構件的損傷程度進行評級。本研究以一所小學之走廊進行實際場域驗證，目的為檢測和量化混凝土構件之表面劣化。由驗證結果可見，藉由本研究之進階建物劣化檢測架構，於劣化辨識、損傷量化和檢測效率上，相較傳統建物目視檢測都獲得顯著改善。 |
| Title | Framework of Advanced Building Inspection withRoute Planning, Defect Detection, and Damage Rating |
|---|---|
| Author | Shun-Hsiang Hsu, Ho-Tin Hung, Yun-Man Hsu, Chia-Ming Chang, Tzung-Wu Chen, Chun-Chung Chen |
| Keywords | visual inspection; damage detection; damage quantification; deep learning |
| Abstract | Visual inspection is commonly adopted for building operation, maintenance, and safety. The durability and defects of components or materials in buildings can be quickly assessed through visual inspection. However, implementations of visual inspection are substantially time-consuming, labor-intensive, and error-prone because useful auxiliary tools that can instantly highlight defects or damage locations from images are not available. Therefore, an advanced building inspection framework is developed and implemented with route planning, realtime and detailed damage recognition, and damage rating in this study. The inspection route sketching is first exploited to provide an efficient plan with significantly reduced disruption. Then, Scaled-YOLOv4 and SOLOv2 models are considered in this study to detect defects even in a large-scale field quickly and acquire pixel-level damage recognition for more precise quantification, respectively. Finally, damage levels of components are rated following the importance and numbers per unit area of the detected defects. This entire framework is also implemented and verified by the hallway of an elementary school to detect and quantify surface damage of concrete components. As seen in the results, the conventional building inspection is significantly improved by the aid of the proposed framework in terms of damage localization, damage quantification, and inspection efficiency. |
| 標題 | 圖神經網路於線性靜力分析之應用 |
|---|---|
| 作者 | 周遠同、黎光曜 、郭柏志、張慰慈、黃尹男、陳俊杉 |
| 關鍵字 | |
| 摘要 | 結構設計是朝向最佳化的迭代過程，目前多依賴結構工程師過往的經驗結合結構分析的結果完成。結構最佳化設計需反覆進行結構分析，如何加速結構分析則是重要的突破關鍵。本研究使用深度學習模型作為線性靜力分析之代理模型，提供快速即時且精準之結構反應預測。因著結構物之空間幾何關係與圖資料結構之間之相似性，本研究將結構物表達成圖，並以圖神經網路模型去學習結構物所受之外力與結構物反應之間的關係。在透過由結構軟體所生成包含隨機樓層數、跨數、樑柱長度，以及隨機大小的側向外施載重之結構分析資料集訓練後，圖神經網路模型不僅顯示了其在預測位移以及力具有良好之表現，模型也具有很好之泛化能力，能夠預測在訓練時從未接觸過的、更高的結構物。在特徵重要性分析中也顯示模型所學習到之特徵具有一定之物理意義。 |
| Title | Linear Static Analysis with Graph Neural Networks |
|---|---|
| Author | Yuan-Tung Chou, Kuang-Yao Li, Po-Chih Kuo, Wei-Tze Chang, Yin-Nan Huang , Chuin-Shan Chen |
| Keywords | |
| Abstract | Structural design is an iterative process for optimum selection, which relies on structural analysis results and experience from structural engineers. Since iterative structural analysis is a necessary for getting a good design, accelerating structural analysis is an important task. In this work, we adopt deep learning approaches as a surrogate model for linear static analysis, which provides fast and accurate structural response prediction. Based on the similarity between the structure’s topology and graph data structure, we represent structures as graphs and leverage graph neural networks (GNNs) to learn the relationship between given external forces and corresponding structural responses. The GNN model is trained with random-generated structures, including random story number, span number, beam-column length, and value of external forces. The results show that the GNN model has good performance on displacement and force predictions and excellent generalizability on unseen, taller structures. In addition, it is shown that based on the analysis of feature importance, the GNN model can extract important physical attributes from the input features. |
| 標題 | 使用機器學習和統計資訊進行異常訊號檢測和分類 |
|---|---|
| 作者 | 林天郇、黃謝恭、周肇昱 |
| 關鍵字 | 異常訊號、機器學習、模式識別網路、GoogLeNet |
| 摘要 | 結構健康監測（structural health monitoring，SHM）和結構完整性管理（structural integrity management，SIM）為逐漸興起的技術，為了持續檢測結構狀態並不斷追蹤結構劣化，海量的資料伴隨著不正常的量測數據正不斷的被產生，至此，檢測與分類這些帶來問題的異常訊號大多依靠人工，這不僅費時費力，工作更是乏味。在本研究中，檢測與分類異常訊號的工作將被機器學習的技術取代，並嘗試利用統計學的優勢來提高檢測與分類的正確性，模式識別網路（pattern recognition network）被採納來使用一維的輸入資料，而GoogLeNet 被引入來使用二維的輸入資料，並利用一組現地量測資料進行學習，其結果顯示兩種機器學習的技術均可有效的檢測與分類異常訊號，並且其算力需求與正確性是個權衡下的結果，因此對於兩種技術的使用情境將可視應用的需求而定。 |
| Title | DATA ANOMALIES DETECTION AND CLASSIFICATION USING MACHINE LEARNING AND STATISTIC INFORMATION |
|---|---|
| Author | Tian-Xun Lin, Shieh-Kung Huang, Jau-Yu Chou |
| Keywords | data anomaly, machine learning, pattern recognition network, GoogLeNet |
| Abstract | Structural health monitoring (SHM) and structural integrity management (SIM) are emerging recently. To continuously track the condition and constantly detect early deterioration of the infrastructure, huge amounts of data are produced and abnormal measurement is inevitable. The corrupted data can produce a lot of problems and, generally, they are examined and classified by humans. In this study, the detection and classification are replaced by the techniques of machine learning (ML) and improved by using statistic information. The neural networks based on 1-dimensional and 2-dimensional data are studied via a field dataset collected from a long-span cable-stayed bridge. Therefore, a shallow network, called pattern recognition network, is selected to use 1-dimensional data as an input and a deep network, GoogLeNet, is selected to use 2-dimensional data. The results show that both models can detect and classify the data anomalies and the usage depends on the assigned application and the trade-off between computation and performance. |
| 標題 | 結合神經網路熵與卷積神經網路於結構健康診斷系統應用之研究 |
|---|---|
| 作者 | 林子剛、林易廷、郭凱維 |
| 關鍵字 | 結構健康監測、神經網路熵、卷積神經網路 |
| 摘要 | 本研究以神經網路熵(Neural Network Entropy, NNetEn)為研究基礎，並將此熵分析方法與卷積神經網路(Convolutional Neural Network, CNN)結合，發展出一套具實用性之結構健康監測系統。為了驗證其系統之可行性，將進行七層樓鋼構架的破壞實驗，並建置與鋼構架相同結構特徵之數值模型。首先使用狀態空間法建立數值模型，模擬與鋼構架相同之十六種破壞模式，並將破壞時之各樓層加速度訊號以神經網路熵進行分析，建立熵值資料庫，再將此熵值資料庫用以訓練類神經網路模型。前期研究之熵值是藉由人為觀察後定義其閥值，藉以判斷結構是否破壞，因此為了避免人為因素的誤判及自動化判讀，本研究以可視化之 heatmap 量化熵值變化，並選用適用於影像處理的卷積神經網路分析，透過將熵值轉為圖像資料之方式不僅能夠減少模型中之參數量還能提升其運算速度。神經網路模型在訓練過程中藉由提取熵值中的破壞特徵並學習，在訓練完成後模型即能在識別輸入資料的破壞特徵後定位結構物之破壞區域。最後，透過國家地震工程研究中心之七層樓鋼構架驗證所設計之十六種破壞案例，逐例討論模型的輸出值並以混淆矩陣量化數值模擬和實驗驗證之預測結果。本研究提出的結構健康診斷系統，將新興之熵分析方法結合類神經網路，其最終驗證實驗之測試樣本結果其準確率 93.13%。 |
| Title | Application of Convolution Neural Network and Neural Network Entropy Algorithm for Structural Health Monitoring |
|---|---|
| Author | Tzu-Kang Lin, Yi-Ting Lin, Kai-Wei Kuo |
| Keywords | Structural Health Monitoring, NNetEn, Convolution Neural Network |
| Abstract | This study combines Neural Network Entropy (NNetEn) and Convolutional Neural Network (CNN) to develop a practical structural health monitoring system. In order to verify the feasibility of the system, the failure experiment of a seven-story steel frame has been carried out with a numerical model of the same structural characteristics as the steel frame. The state space method is used to simulate the sixteen failure modes on the steel frame, where the acceleration signals of each floor at the time of failure are analyzed by neural network entropy. An entropy database is established based on the model to train the neural network model. To avoid the misjudgment and automatic interpretation of human factors, this study uses the visualized heatmap to quantify the change of entropy value, and the convolutional neural network analysis is selected for image processing. By converting the entropy value into image data, not only the number of parameters in the model can be reduced, but its operation speed can be improved. During the training process, the neural network model extracts and learns the damage features in the entropy value. After the training is completed, the model can allocate the damage area of the structure by identifying the damage features of the input data. Finally, through the verification of 16 failure cases simulated on the seven-story steel frame of the National Center for Research on Earthquake Engineering (NCREE), the performance of the proposed SHM system is evaluated by both numerical simulation and experimental verification with confusion matrix. The SHM system proposed in this study combines the emerging entropy analysis method with a neural network. The test results of the final verification have an accuracy rate of 93.13%. |
| 標題 | 深度學習於提升地震模擬振動臺加速度性能之研究 |
|---|---|
| 作者 | 賴魁星、陳沛清 |
| 關鍵字 | 地震模擬振動臺、加速度控制、三參數控制器、深度學習、長短期記憶神經網路 |
| 摘要 | 地震模擬振動臺是地震工程研究重要的實驗設備，已廣泛應用在各種結構系統的耐震性能試驗，諸如鋼筋混凝土結構、鋼結構、隔減震結構以及精密設備等，因此振動臺加速度控制之精確與否在振動臺實驗中特別重要。本研究提出使用深度學習的方式， 使用了長短期記憶(Long Short-TermMemory, LSTM)神經網路，透過大量實驗資料訓練出振動臺的外迴路控制器。本研究使用油壓驅動之大型單軸向振動臺，設計一組鋼構造試體安裝其上並進行大量的振動臺實驗，以得到LSTM 之訓練資料，再將訓練所得到的LSTM 作為前饋控制器，加裝在振動臺既有的三參數控制架構中，藉此補償振動臺加速度控制的動態響應。實驗結果證明LSTM 前饋控制器可有效地降低振動臺的加速度誤差，並減少試體與振動臺的互制現象，使振動臺之加速度性得到顯著的提升。本研究成果顯示應用深度學習於提升振動臺加速度表現的發展潛能，未來可進行更多的相關研究，以改善振動臺實驗之測試品質。 |
| Title | Improved Acceleration Tracking Performance of Seismic Simulators using Supervised Deep Learning |
|---|---|
| Kui-Xing Lai and Pei-Ching Chen | |
| Keywords | Seismic shake table; acceleration control, three-variable control; deep learning, long short-term memory neural network |
| Abstract | Seismic shake table testing has been widely used for various structural systems such as steel structures, reinforced-concrete structures, energy-dissipated and base-isolated buildings, and nonstructural components etc. Therefore, accurate replication of shake table acceleration is particularly important to these tests. In this study, supervised deep learning approach is applied as an alternative for seismic shake table control. The Long Short-Term Memory (LSTM) neural network is built for training the controller to improve acceleration performance of the shake table. A large-scale servo-hydraulic uniaxial shake table is adopted. A steel specimen is designed and fabricated for performing a large number of shake table tests. Then, the shake table testing data are used to train a feedforward controller using LSTM which is implemented close to an existing Three-Variable Control (TVC) loop. The validating experimental results prove that the acceleration tracking performance is improved compared with conventional TVC. The control-structure interaction is also suppressed. The experimental results demonstrate the proposed control scheme reduces the acceleration tracking error effectively compared with conventional TVC control. The research results also show great potential for deep learning application to seismic shake table control in the future. Keywords: Constitutive model, anisotropy, shear-slip and re-contact, mesh-sensitivity, non-proportional loading, concrete, finite element |
| 標題 | 基於深度學習之合成配電網絡建置研究 |
|---|---|
| 作者 | 林岳鴻、林其穎 |
| 關鍵字 | 合成配電網絡、深度學習、物體識別、地理標籤 |
| 摘要 | 現今時代處於能源高消耗的處境且加上地球暖化帶來的災害規模日益嚴重，使人們對於公共資產管理、減少能源消耗、預測災害損失更加重視。本研究提出利用深度學習建置合成電力網路，以便未來使用其擬真模型進行電網可靠度分析。本研究利用街景圖配合物體識別及計算交集的方式定位出電線桿之地理資訊，並利用此地理資訊建立其合成電力網路。研究首先使用Mask R-CNN 與YOLOv4 物體識別模型，進行時長之條件控制訓練，並比較兩種模型的精確度得出適合此研究之方法。接續調整其參數配置，比較不同參數下對於此研究的最佳模型設置。對於區域的研究進行每條街的個別物體識別，並設計兩種排序方式進行電線桿排序，分別為經緯度以及最短路徑，利用兩種排序方式進行基於馬爾科夫隨機場(Markov random field,MRF)和基於方位線(line of bearing, LOB)與基於密度之聚類演算法(Densitybasedspatial clustering of application with noise, DBCSCAN)兩種方式計算交集，接著進行電線桿之補遺，使其更符合真實電線桿最大容許間距。最後，利用距離迭代的方式合併所有街道並刪除重複預測的電線桿點位，得出四種結果。使用四種結果與真實電線桿地理資訊進行精度比對，選擇出最適者並利用最小生成樹(minimum spanning tree, MST)建立電力網路，建立後分析並比較其性質與真實電力網絡的區別。未來可使用此模型進行改善，使其更符合真實電力網路，並使用其合成電力網絡進行電網可靠度分析、公共資產管理、災害分析等分析。 |
| Title | Synthetic Power Distribution Network Construction Based on Deep Learning Algorithm |
|---|---|
| Yue-Hung Lin and Chi-Ying Lin | |
| Keywords | synthetic power distribution network, deep learning, object detection, geo-positioning |
| Abstract | Global warming has caused high energy consumption and an increasing scale of disasters, which make people draw more attention to public asset management to reduce energy consumption and predict losses caused by disasters. Based on a deep learning based object detection approach, this study develops a synthetic power distribution network that can serve as an alternative to the real power distribution net-work and be used to analyze its reliability. This research uses the street view images to detect utility poles and conduct geo-positioning to locate utility poles on the map. For object detection, the Mask R-CNN and YOLOv4 are trained with controlled du-ration, and then the accuracy of the two models is compared to determine which method is suitable for this research. Second, the model’s hyperparameters are adjusted and compared to determine the best model setting for the object detection task in this study. Then the selected model is used to perform the object detection task for each street in the research region. Two sorting methods, namely, the latitude and longitude sorting method and the shortest path sorting method, are proposed to sort the poles for pole geopositioning and supplementation. With two sorting methods, pole geopositioning is conducted based on two approaches: The first is the Markov random field (MRF) approach, and the second is the line of bearing (LOB) with density-based spatial clustering of application with noise (DBSCAN). After determining the detected pole location, pole supplementation is conducted to ensure the maximum allowable distance between poles. Third, four sets of results are obtained by merging all streets and removing duplicate poles by means of distance iteration. Finally, four results are compared with the coordinates of real utility poles. The most suitable method for study region is selected to establish the synthetic power distribution network using the minimum spanning tree (MST). In the future, this model can be improved to make it more in line with the real power distribution network, and the synthetic power distribution network can be used for power grid reliability analysis, public asset management, disaster analysis, power demand-supply analysis, etc. |
Special Issue: Application of Artificial Intelligence in Structural Engineering
Guest Editor: Tzu-Kang Lin
| Title | Framework of Advanced Building Inspection withRoute Planning, Defect Detection, and Damage Rating |
|---|---|
| Author | Shun-Hsiang Hsu, Ho-Tin Hung, Yun-Man Hsu, Chia-Ming Chang, Tzung-Wu Chen, Chun-Chung Chen |
| Keywords | visual inspection; damage detection; damage quantification; deep learning |
| Abstract | Visual inspection is commonly adopted for building operation, maintenance, and safety. The durability and defects of components or materials in buildings can be quickly assessed through visual inspection. However, implementations of visual inspection are substantially time-consuming, labor-intensive, and error-prone because useful auxiliary tools that can instantly highlight defects or damage locations from images are not available. Therefore, an advanced building inspection framework is developed and implemented with route planning, realtime and detailed damage recognition, and damage rating in this study. The inspection route sketching is first exploited to provide an efficient plan with significantly reduced disruption. Then, Scaled-YOLOv4 and SOLOv2 models are considered in this study to detect defects even in a large-scale field quickly and acquire pixel-level damage recognition for more precise quantification, respectively. Finally, damage levels of components are rated following the importance and numbers per unit area of the detected defects. This entire framework is also implemented and verified by the hallway of an elementary school to detect and quantify surface damage of concrete components. As seen in the results, the conventional building inspection is significantly improved by the aid of the proposed framework in terms of damage localization, damage quantification, and inspection efficiency. |
| Title | Linear Static Analysis with Graph Neural Networks |
|---|---|
| Author | Yuan-Tung Chou, Kuang-Yao Li, Po-Chih Kuo, Wei-Tze Chang, Yin-Nan Huang , Chuin-Shan Chen |
| Keywords | |
| Abstract | Structural design is an iterative process for optimum selection, which relies on structural analysis results and experience from structural engineers. Since iterative structural analysis is a necessary for getting a good design, accelerating structural analysis is an important task. In this work, we adopt deep learning approaches as a surrogate model for linear static analysis, which provides fast and accurate structural response prediction. Based on the similarity between the structure’s topology and graph data structure, we represent structures as graphs and leverage graph neural networks (GNNs) to learn the relationship between given external forces and corresponding structural responses. The GNN model is trained with random-generated structures, including random story number, span number, beam-column length, and value of external forces. The results show that the GNN model has good performance on displacement and force predictions and excellent generalizability on unseen, taller structures. In addition, it is shown that based on the analysis of feature importance, the GNN model can extract important physical attributes from the input features. |
| Title | DATA ANOMALIES DETECTION AND CLASSIFICATION USING MACHINE LEARNING AND STATISTIC INFORMATION |
|---|---|
| Author | Tian-Xun Lin, Shieh-Kung Huang, Jau-Yu Chou |
| Keywords | data anomaly, machine learning, pattern recognition network, GoogLeNet |
| Abstract | Structural health monitoring (SHM) and structural integrity management (SIM) are emerging recently. To continuously track the condition and constantly detect early deterioration of the infrastructure, huge amounts of data are produced and abnormal measurement is inevitable. The corrupted data can produce a lot of problems and, generally, they are examined and classified by humans. In this study, the detection and classification are replaced by the techniques of machine learning (ML) and improved by using statistic information. The neural networks based on 1-dimensional and 2-dimensional data are studied via a field dataset collected from a long-span cable-stayed bridge. Therefore, a shallow network, called pattern recognition network, is selected to use 1-dimensional data as an input and a deep network, GoogLeNet, is selected to use 2-dimensional data. The results show that both models can detect and classify the data anomalies and the usage depends on the assigned application and the trade-off between computation and performance. |
| Title | Application of Convolution Neural Network and Neural Network Entropy Algorithm for Structural Health Monitoring |
|---|---|
| Author | Tzu-Kang Lin, Yi-Ting Lin, Kai-Wei Kuo |
| Keywords | Structural Health Monitoring, NNetEn, Convolution Neural Network |
| Abstract | This study combines Neural Network Entropy (NNetEn) and Convolutional Neural Network (CNN) to develop a practical structural health monitoring system. In order to verify the feasibility of the system, the failure experiment of a seven-story steel frame has been carried out with a numerical model of the same structural characteristics as the steel frame. The state space method is used to simulate the sixteen failure modes on the steel frame, where the acceleration signals of each floor at the time of failure are analyzed by neural network entropy. An entropy database is established based on the model to train the neural network model. To avoid the misjudgment and automatic interpretation of human factors, this study uses the visualized heatmap to quantify the change of entropy value, and the convolutional neural network analysis is selected for image processing. By converting the entropy value into image data, not only the number of parameters in the model can be reduced, but its operation speed can be improved. During the training process, the neural network model extracts and learns the damage features in the entropy value. After the training is completed, the model can allocate the damage area of the structure by identifying the damage features of the input data. Finally, through the verification of 16 failure cases simulated on the seven-story steel frame of the National Center for Research on Earthquake Engineering (NCREE), the performance of the proposed SHM system is evaluated by both numerical simulation and experimental verification with confusion matrix. The SHM system proposed in this study combines the emerging entropy analysis method with a neural network. The test results of the final verification have an accuracy rate of 93.13%. |
| Title | Improved Acceleration Tracking Performance of Seismic Simulators using Supervised Deep Learning |
|---|---|
| Author | Kui-Xing Lai and Pei-Ching Chen |
| Keywords | Seismic shake table; acceleration control, three-variable control; deep learning, long short-term memory neural network |
| Abstract | Seismic shake table testing has been widely used for various structural systems such as steel structures, reinforced-concrete structures, energy-dissipated and base-isolated buildings, and nonstructural components etc. Therefore, accurate replication of shake table acceleration is particularly important to these tests. In this study, supervised deep learning approach is applied as an alternative for seismic shake table control. The Long Short-Term Memory (LSTM) neural network is built for training the controller to improve acceleration performance of the shake table. A large-scale servo-hydraulic uniaxial shake table is adopted. A steel specimen is designed and fabricated for performing a large number of shake table tests. Then, the shake table testing data are used to train a feedforward controller using LSTM which is implemented close to an existing Three-Variable Control (TVC) loop. The validating experimental results prove that the acceleration tracking performance is improved compared with conventional TVC. The control-structure interaction is also suppressed. The experimental results demonstrate the proposed control scheme reduces the acceleration tracking error effectively compared with conventional TVC control. The research results also show great potential for deep learning application to seismic shake table control in the future. Keywords: Constitutive model, anisotropy, shear-slip and re-contact, mesh-sensitivity, non-proportional loading, concrete, finite element |
| Title | Synthetic Power Distribution Network Construction Based on Deep Learning Algorithm |
|---|---|
| Author | Yue-Hung Lin and Chi-Ying Lin |
| Keywords | synthetic power distribution network, deep learning, object detection, geo-positioning |
| Abstract | Global warming has caused high energy consumption and an increasing scale of disasters, which make people draw more attention to public asset management to reduce energy consumption and predict losses caused by disasters. Based on a deep learning based object detection approach, this study develops a synthetic power distribution network that can serve as an alternative to the real power distribution net-work and be used to analyze its reliability. This research uses the street view images to detect utility poles and conduct geo-positioning to locate utility poles on the map. For object detection, the Mask R-CNN and YOLOv4 are trained with controlled du-ration, and then the accuracy of the two models is compared to determine which method is suitable for this research. Second, the model’s hyperparameters are adjusted and compared to determine the best model setting for the object detection task in this study. Then the selected model is used to perform the object detection task for each street in the research region. Two sorting methods, namely, the latitude and longitude sorting method and the shortest path sorting method, are proposed to sort the poles for pole geopositioning and supplementation. With two sorting methods, pole geopositioning is conducted based on two approaches: The first is the Markov random field (MRF) approach, and the second is the line of bearing (LOB) with density-based spatial clustering of application with noise (DBSCAN). After determining the detected pole location, pole supplementation is conducted to ensure the maximum allowable distance between poles. Third, four sets of results are obtained by merging all streets and removing duplicate poles by means of distance iteration. Finally, four results are compared with the coordinates of real utility poles. The most suitable method for study region is selected to establish the synthetic power distribution network using the minimum spanning tree (MST). In the future, this model can be improved to make it more in line with the real power distribution network, and the synthetic power distribution network can be used for power grid reliability analysis, public asset management, disaster analysis, power demand-supply analysis, etc. |
各位老師與先進 您好：
國家地震工程研究中心(國震中心)特別邀請美國CoreBrace公司的研發工程師李昭賢博士，於2023年2月21日在國震中心進行專題演講，講題為「Seismic behavior and design of collectors in steel building structures and development of associated shake table testing methodology」，演講內容涵蓋匯集構材(Collector)與振動台試驗方法。
李昭賢博士自台大土木系研究所碩士班畢業後，即加入國震中心擔任助理研究員，在累積近十年的工作與研究經驗後，負笈美國University of California San Diego (UCSD)攻讀博士學位，在修業期間參與規劃曾執行美國國家科學基金會(National Science Foundation)計畫在UCSD進行的振動台試驗。希望透過本此活動與國內專家學者分享美國學界在鋼造匯集構材耐震設計方面的最新研究成果以及相關實驗技術開發的研究歷程，並與專業人員進行意見交流。
敬邀您與您的研究團隊出席，演講資訊如下:
時間：2023年2月21日(星期二)上午10時00分至上午11時30分
地點： 101會議室
費用：免費
名額：120人，額滿為止。
報名網址: https://conf.ncree.org.tw/index.aspx?n=A11202210
講者與演講資訊: 詳如附件
聯絡人: 國震中心建物組 莊明介副研究員(e-mail: mcchuang@narlabs.org.tw)
(交通資訊請詳見報名網站之會議場地說明，如您對活動有任何問題與建議，敬請賜教，感謝您。)
附件：
演講資訊：20230221先進抗震技術研發與應用專題演講[美國CoreBrace_李昭賢博士]_邀請卡
講者資訊：Abstract and Bio_Dr. CH Li
親愛的會員好：
代轉發國家地震工程研究中心謹訂於112年1月13日(五)於國震中心臺南實驗室(臺南市歸仁區中正南路一段2001號)舉辦
「國家地震工程研究中心實驗成果暨工程實務研討會（臺南場）」(邀請卡如附檔)，歡迎踴躍參加。
★研討會資訊：
※時間：112年1月13日(五)
※地點：國震中心臺南實驗室101演講廳(臺南市歸仁區中正南路一段2001號)
※議程：請詳附件邀請卡
※本研討會免費報名！人數上限150名
※報名網址：https://conf.ncree.org.tw/indexCht.aspx?n=NCE202210。
請於即日起至112年1月11日前完成線上報名程序。
※研討會提供公務人員與技師積點，請於報名系統登錄相關資訊。
※研討會提供參與學生研習證明。
本研討會邀請110年於本中心臺南實驗室各測試系統進行實驗之研究團隊，
以口頭演講方式發表最新實驗與研究成果。
此外，特別邀請加州大學聖地亞哥分校及科羅拉多大學丹佛分校學者進行專題演講；
同時為促進學、研界與業界之交流，亦特別邀請多位業界工程師分享工程實務經驗，
透過此平台提供地震工程領域專家、學者一個面對面交流與分享的機會。
藉由分享與交流，期能提供學界人員在未來進行結構實驗規劃及執行時能更加周詳有效率，
亦可使工程界先進了解地震工程領域最新研究趨勢與成果，創造更多產學合作與應用機會。
研討會邀集多位國內外教授及業界專家，精彩可期！
懇請將此訊息轉發給其他同事、會員與朋友們，
並以手機掃描或點選下方QR-CODE馬上報名吧！
敬祝新年快樂、健康平安。
若有任何問題，歡迎透過電子郵件 hwhuang@narlabs.org.tw 或
來電本研討會秘書黃瀚緯先生(06-230-7060#1901)聯絡。
中華民國結構工程學會 敬啟
附檔：
親愛的會員好：
代轉發國家地震工程研究中心私有建築物弱層補強專案辦公室謹訂於111年12月23日（星期五）上午9時30分假國家地震工程研究中心一樓103會議室舉辦「私有建築物耐震弱層補強專題演講」，邀請旅紐工程師許琳青技師來進行專題演講，演講主題為紐西蘭既有建築物耐震評估與補強實務經驗分享。
邀請函及議程詳附件謝謝！
敬祝 平安順心
中華民國結構工程學會 敬啟
親愛的會員您好，
本學會謹訂於中華民國111年12月17日上午8:30(星期六)假國家地震工程研究中心一樓會議室（臺北市大安區辛亥路3段200號）辦理第18屆第二次會員大會，特此通知，紙本開會通知已發送。敬邀各位會員蒞臨與會，大會通知書詳如附件，敬請查收，謝謝。
【停車資訊】本學會已向台大租借國家地震中心旁台大停車場(上午8:30~下午17:00)供會員停車，會員如開車與會，可停在該停車場，惟出入皆須配合現場人員刷卡進出且只限由辛亥路國震中心旁入口進出，無法由基隆路入口進出，尚請見諒。此外，最晚於當天（12/17）下午17:00前須駛離，否則停車場感應卡即失效，無法再進出，請大家務必配合，謝謝。）
中華民國結構工程學會 敬啟-12/05/2022
停車場地圖 :
附件:
第18屆第二次會員大會會員通知停車場地圖
親愛的會員好，
提供以下講座資訊，歡迎踴躍參加，謝謝。
中華民國結構工程學會 敬啟－11/29/2022
2022工程技術講座(3)
主辦單位：財團法人國家實驗研究院國家地震工程研究中心、
中華民國結構工程學會。
協辦單位：華熊營造股份有限公司、施忠賢結構技師事務所。
時間：民國111年12月14日 (星期三)。
地點：國家地震工程研究中心一樓R101會議室。
費用：300元整，民國111年12月7日(星期三)前截止報名。
報名方式：即日起開始報名，請上網址：https://conf.ncree.org.tw/indexCht.aspx?n=A11112140
備註：本研討會已向行政院公共工程委員會申請技師積點及公務人員終身學習護照相關證書。
聯絡人：莊勝智/sjjhuang@ncree.narl.org.tw
紀凱甯/ knchi@narlabs.org.tw
莊勝智 Sheng-Jhih, Jhuang
財團法人國家實驗研究院國家地震工程研究中心
National Center fot Research on Earthquake Engineering
地址: 台北市大安區辛亥路三段200號
TEL：02-66300829
FAX：02-66300858
E-MAIL: sjjhuang@narlabs.org.tw