An Accurate and Interpretable Framework for Trustworthy Process Monitoring

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Hao, Wang, Zhiyu, Niu, Yunlong, Liu, Zhaoran, Li, Haozhe, Liao, Yilin, Huang, Yuxin, Liu, Xinggao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911539079938048
author Wang, Hao
Wang, Zhiyu
Niu, Yunlong
Liu, Zhaoran
Li, Haozhe
Liao, Yilin
Huang, Yuxin
Liu, Xinggao
author_facet Wang, Hao
Wang, Zhiyu
Niu, Yunlong
Liu, Zhaoran
Li, Haozhe
Liao, Yilin
Huang, Yuxin
Liu, Xinggao
contents Trustworthy process monitoring seeks to build an accurate and interpretable monitoring framework, which is critical for ensuring the safety of energy conversion plant (ECP) that operates under extreme working conditions such as high pressure and temperature. Contemporary self-attentive models, however, fall short in this domain for two main reasons. First, they rely on step-wise correlations that fail to involve physically meaningful semantics in ECP logs, resulting in suboptimal accuracy and interpretability. Second, attention matrices are frequently cluttered with spurious correlations that obscure physically meaningful ones, further impeding effective interpretation. To overcome these issues, we propose AttentionMixer, a framework aimed at improving both accuracy and interpretability of existing methods and establish a trustworthy ECP monitoring framework. Specifically, to tackle the first issue, we employ a spatial adaptive message passing block to capture variate-wise correlations. This block is coupled with a temporal adaptive message passing block through an \textit{mixing} operator, yielding a multi-faceted representation of ECP logs accounting for both step-wise and variate-wise correlations. Concurrently, to tackle the second issue, we employ a sparse message passing regularizer to filter out spurious correlations. We validate the efficacy of AttentionMixer using two real-world datasets from the radiation monitoring network for Chinese nuclear power plants.
format Preprint
id arxiv_https___arxiv_org_abs_2302_10426
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle An Accurate and Interpretable Framework for Trustworthy Process Monitoring
Wang, Hao
Wang, Zhiyu
Niu, Yunlong
Liu, Zhaoran
Li, Haozhe
Liao, Yilin
Huang, Yuxin
Liu, Xinggao
Artificial Intelligence
Machine Learning
Signal Processing
Applications
Trustworthy process monitoring seeks to build an accurate and interpretable monitoring framework, which is critical for ensuring the safety of energy conversion plant (ECP) that operates under extreme working conditions such as high pressure and temperature. Contemporary self-attentive models, however, fall short in this domain for two main reasons. First, they rely on step-wise correlations that fail to involve physically meaningful semantics in ECP logs, resulting in suboptimal accuracy and interpretability. Second, attention matrices are frequently cluttered with spurious correlations that obscure physically meaningful ones, further impeding effective interpretation. To overcome these issues, we propose AttentionMixer, a framework aimed at improving both accuracy and interpretability of existing methods and establish a trustworthy ECP monitoring framework. Specifically, to tackle the first issue, we employ a spatial adaptive message passing block to capture variate-wise correlations. This block is coupled with a temporal adaptive message passing block through an \textit{mixing} operator, yielding a multi-faceted representation of ECP logs accounting for both step-wise and variate-wise correlations. Concurrently, to tackle the second issue, we employ a sparse message passing regularizer to filter out spurious correlations. We validate the efficacy of AttentionMixer using two real-world datasets from the radiation monitoring network for Chinese nuclear power plants.
title An Accurate and Interpretable Framework for Trustworthy Process Monitoring
topic Artificial Intelligence
Machine Learning
Signal Processing
Applications
url https://arxiv.org/abs/2302.10426