2023
DOI: 10.1021/acsomega.2c07400
|View full text |Cite
|
Sign up to set email alerts
|

Supervised Attention-Based Bidirectional Long Short-Term Memory Network for Nonlinear Dynamic Soft Sensor Application

Abstract: Soft sensors are mathematical methods that describe the dependence of primary variables on secondary variables. A nonlinear characteristic commonly appears in modern industrial process data with increasing complexity and dynamics, which has brought challenges to soft sensor modeling. To solve these issues, a novel supervised attention-based bidirectional long short-term memory (SA-BiLSTM) is first proposed in this paper to handle the nonlinear industrial process modeling with dynamic features. In this SA-BiLST… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
10
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 13 publications
(10 citation statements)
references
References 38 publications
0
10
0
Order By: Relevance
“…Bi-LSTM structure allows the capture of important trends from data with forward and backward moving windows [50]. Thus, this study also investigates Bi-LSTM model for multivariate predictions for TWINS wind sensing board.…”
Section: Bidirectional Lstm (Bi-lstm)mentioning
confidence: 99%
“…Bi-LSTM structure allows the capture of important trends from data with forward and backward moving windows [50]. Thus, this study also investigates Bi-LSTM model for multivariate predictions for TWINS wind sensing board.…”
Section: Bidirectional Lstm (Bi-lstm)mentioning
confidence: 99%
“…In modern complex chemical production processes, real-time monitoring has proven to be an exceedingly effective method for ensuring product safety and enhancing economic benefits. Quality variables serve as essential indicators of the performance of the chemical production process and are crucial in maintaining process stability . However, due to the scarcity of economical and reliable online monitoring equipment, many quality variables in practical chemical production are acquired through offline laboratory analysis .…”
Section: Introductionmentioning
confidence: 99%
“…In such a situation, a large measurement delay occurs, which is not beneficial to process quality control and optimization. Alternatively, soft sensing methods are developed to alleviate the problem. The concerned hard-to-measure quality variables are estimated with the help of process variables. As known, adequate training samples are a key factor in reliable model construction.…”
Section: Introductionmentioning
confidence: 99%