.png){kind=icon}
返回
Graph-guided masked autoencoder for process anomaly detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.psep.2024.04.052.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Developing an accurate and reliable anomaly detection model is of great significance for safe operation in the process industry. To minimize false positives, it is crucial to accurately model the intricate topological and nonlinear connections among variables. In this study, a process anomaly detection method based on graphguided masked autoencoder (GGMAE) is proposed by introducing the concept of the graph to the process industry. GGMAE first constructs a topology graph according to the process flowchart. Then, the patch and mask mechanism forces GGMAE to learn the process intrinsic information to reconstruct the input according to the variable topological relationship and temporal characteristics. Additionally, Kullback-Leibler divergence is used as the loss to ensure that the distribution of input and output is consistent. Experiments on two publicly available anomaly detection benchmarks demonstrate the superiority of GGMAE over existing methods. Visualization of the results demonstrates the physically compliant reconstruction logic.
Keyword:
Anomaly detection
Data -driven modeling
Graph learning
Autoencoder
Process industry
期刊
IF:
7.8
论文数:
10.0K
被引数:
3.8W
机构
引用论文
.png){kind=icon}
Anomaly Detection Based on Convolutional Recurrent Autoencoder for IoT Time Series基于卷积递归自编码器的物联网时间序列异常检测
PREAI
分享收藏Process topology convolutional network model for chemical process fault diagnosis化工过程故障诊断的过程拓扑卷积网络模型
PREAI
分享收藏CausalViT: Domain generalization for chemical engineering process fault detection and diagnosis
PREAI
分享收藏
分享收藏Consistent Anomaly Detection and Localization of Multivariate Time Series via Cross-Correlation Graph-Based EncoderDecoder GAN基于互相关图的编码器解码器GAN的多元时间序列一致异常检测与定位
PREAI
分享收藏
查看更多内容