Data Reconciliation for Energy System Flowsheets

Yong, Jun Yow; Nemet, Andreja; Bogataj, Miloš; Zore, Žan; Varbanov, Petar Sabev; Kravanja, Zdravko; Klemeš, Jiří Jaromír

doi:10.1016/b978-0-444-63428-3.50384-2

Cited by 4 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…How to effectively capture the features related to the quality prediction from the sensory data remains a major challenge. The intrinsic nonlinearity and dynamics in the process industry may give rise to great difficulty . Although several statistical and machine learning methods have been utilized to address the problem, the overall performance is largely case-dependent.…”

Section: Introductionmentioning

confidence: 99%

“…The intrinsic nonlinearity and dynamics in the process industry may give rise to great difficulty. 27 Although several statistical and machine learning methods have been utilized to address the problem, the overall performance is largely case-dependent. Though datadriven modeling is usually treated as a black-box technique, for the existing methods, the ignorance of the process knowledge is probably the biggest obstacle to obtaining good performance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Soft-Sensor Development through Deep Learning with Spatial and Temporal Feature Extraction of Complex Processes

Xie

Yao

Zhu

et al. 2022

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Data-driven soft sensing techniques have been widely applied to predict the quality variables in the process industry. The temporal and spatial structure information is important for process modeling because it helps extract the nonlinear and dynamic characteristics from data. Deep learning can be used to mimic the physical linking structure by designing similar node connections in the neural network. Taking a complex process with countercurrent unit connection as a demonstration, this paper proposes using a bidirectional long short-term memory-based network with spatiotemporal feature extraction for soft-sensor development. An attention mechanism is further conducted for the feature learning from space and time simultaneously. The effectiveness of the proposed method is validated through a simulation example and a real industrial example.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%