使用機器學習和統計資訊進行異常訊號檢測和分類

DATA ANOMALIES DETECTION AND CLASSIFICATION USING MACHINE LEARNING AND STATISTIC INFORMATION

林天郇(Tian-Xun Lin) ； 黃謝恭(Shieh-Kung Huang) ； 周肇昱(Jau-Yu Chou)

《結構工程》 37卷4期 (2022/12) Pp. 41-63

https://doi.org/10.6849/SE.202212_37(4).0003

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。

關鍵字

異常訊號 ； 機器學習 ； 模式識別網路 ； GoogLeNet

並列摘要

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.

並列關鍵字

data anomaly ； machine learning ； pattern recognition network ； GoogLeNet

參考文獻

Bao, Y., Li, J., Nagayama, T., Xu, Y., Spencer Jr, B. F., & Li, H. (2021). The 1st international project competition for structural health monitoring (IPC-SHM, 2020): a summary and benchmark problem. Structural Health Monitoring, 20(4), 2229-2239.

Bao, Y., Tang, Z., Li, H., & Zhang, Y. (2019). Computer vision and deep learning–based data anomaly detection method for structural health monitoring. Structural Health Monitoring, 18(2), 401-421.

Barandela, R., Valdovinos, R. M., & Sánchez, J. S. (2003). New applications of ensembles of classifiers. Pattern Analysis & Applications, 6(3), 245-256.

Battiti, R. (1992). First-and second-order methods for learning: between steepest descent and Newton's method. Neural computation, 4(2), 141-166.

Bryson, A. E., Ho, Y. C. (1969). Applied optimal control: optimization, estimation, and control. Blaisdell Publishing Company or Xerox College Publishing. 1969: 481.