期刊
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
卷 156, 期 -, 页码 581-597出版社
ELSEVIER
DOI: 10.1016/j.psep.2021.10.036
关键词
Process monitoring; Orthogonal attention; Variational self-attentive autoencoder; Fault detection; Fault identification
资金
- National Science and Technology Innovation 2030 Major Project of the Ministry of Science and Technology of China [2018AAA0101605]
- National Natural Science Foundation of China [21878171]
The proposed orthogonal self-attentive variational autoencoder (OSAVA) model in this paper is capable of simultaneously performing fault detection and identification tasks, and providing interpretable results. Evaluation on the Tennessee Eastman process (TEP) demonstrates promising fault detection rate and low detection delay for the OSAVA model.
Industrial processes are becoming increasingly large and complex, thus introducing potential safety risks and requiring an effective approach to maintain safe production. Intelligent process monitoring is critical to prevent losses and avoid casualties in modern industry. As the digitalization of process industry deepens, data-driven methods offer an exciting avenue to address the demands for monitoring complex systems. Nevertheless, many of these methods still suffer from low accuracy and slow response. Besides, most blackbox models based on deep learning can only predict the existence of faults, but cannot provide further interpretable analysis, which greatly confines their usage in decision-critical scenarios. In this paper, we propose a novel orthogonal self-attentive variational autoencoder (OSAVA) model for process monitoring, consisting of two components, orthogonal attention (OA) and variational self-attentive autoencoder (VSAE). Specifically, OA is utilized to extract the correlations between different variables and the temporal dependency among different timesteps; VSAE is trained to detect faults through a reconstruction-based method, which employs self-attention mechanisms to comprehensively consider information from all timesteps and enhance detection performance. By jointly leveraging these two models, the OSAVA model can effectively perform fault detection and identification tasks simultaneously and deliver interpretable results. Finally, extensive evaluation on the Tennessee Eastman process (TEP) demonstrates that the proposed OSAVA-based fault detection and identification method shows promising fault detection rate as well as low detection delay and can provide interpretable identification of the abnormal variables, compared with representative statistical methods and state-of-the-art deep learning methods. (c) 2021 Institution of Chemical Engineers. Published by Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据