http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Shieh-Kung Huang (검색결과 2 건)
- 무료
- 기관 내 무료
- 유료
-
SHM data anomaly classification using machine learning strategies: A comparative study
Shieh-Kung Huang,Jau-Yu Chou,Yuguang Fu,Chia-Ming Chang 국제구조공학회 2022 Smart Structures and Systems, An International Jou Vol.29 No.1
Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.
-
Application of subspace identification on the recorded seismic response data of Pacoima Dam
Yu, I-No,Huang, Shieh-Kung,Loh, Kenneth J.,Loh, Chin-Hsiung Techno-Press 2019 Structural monitoring and maintenance Vol.6 No.4
Two seismic response data from the CSMIP strong motion instrumentation of Pacoima dam are selected: San Fernando earthquake (Jan 13, 2001; ML=4.3) and Newhall earthquake (Sept. 1, 2011; ML=4.2), for the identification of the dam system. To consider the spatially nonuniform input ground motion along the dam abutment, the subspace identification technique with multiple-input and multiple-output is used to extract the dynamic behavior of the dam-reservoir interaction system. It is observed that the dam-reservoir interaction is significant from the identification of San Fernando earthquake data. The influence of added mass (from the reservoir) during strong ground motion will create a tuned-mass damper phenomenon on the dam body. The fundamental frequency of the dam will be tuned to two different frequencies but with the same mode shapes. As for the small earthquake event, the dam-reservoir interaction is insignificant.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
