.png){kind=icon}
返回
Unsupervised dam anomaly detection with spatial-temporal variational autoencoder
.png){kind=icon}
PRE
AI
DOI：10.1177/14759217211073301.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The anomaly detection and health monitoring of dams have attracted increasing attention. To detect the temporal and spatial anomalies of the dam, a novel spatial-temporal variational autoencoder is proposed. The proposed model is based on the sequential variational autoencoder, and its backbone is fulfilled by the recurrent neural network and graph convolutional network to capture the temporal and spatial features in both the generative and inference models. To obtain a normal pattern, we made an assumption that the normal values should be temporally smooth and spatially similar. Then, the smoothness and similarity-inducing operations are used in the framework of the proposed model. Through the addition of smoothness and similarity losses in sequential variational autoencoder, the proposed model can obtain a temporally smooth and spatially similar pattern. For verification, an arch dam is taken as an example. Through comparison among six baseline models, the proposed model detects the temporal and spatial anomalies accurately and stably.
Keyword:
dam engineering
sequential variational autoencoder
unsupervised anomaly detection
multivariate times series
期刊
S
IF:
5.7
论文数:
2.3K
被引数:
1.1W
机构
引用论文
Supervised Variational Autoencoders for Soft Sensor Modeling With Missing Data用于具有缺失数据的软传感器建模的监督变分自编码器
PREAI
分享收藏分享收藏Evaluation of an analytical method for the determination of polybrominated (PBDD/PBDF) in human adipose.png)
Chemosphere
ChemosphereIF0
PREAI
分享收藏Structural damage identification based on unsupervised feature-extraction via Variational Auto-encoderMEASUREMENT
MEASUREMENTIF5.6
PREAI
分享收藏Reaction of different tomato cultivars toward race 1 of Fusarium oxysporum f. sp. lycopersiciGenetika
OAAI
GenetikaIF0
OAAI分享收藏
查看更多内容