The machine learning life cycle in chemical operations–status and open challenges

M Gärtler, V Khaydarov, B Klöpper… - Chemie Ingenieur …, 2021 - Wiley Online Library
Artificial intelligence (AI) has received a lot of attention with many publications in recent
years. Interestingly related projects in the industry are mostly still in their early stages. We …

Attention-based interval aided networks for data modeling of heterogeneous sampling sequences with missing values in process industry

X Yuan, N Xu, L Ye, K Wang, F Shen… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
In complex process industries, multivariate time sequences are omnipresent, whose
nonlinearities and dynamics present two major challenges for soft sensing of important …

A multimode mechanism-guided product quality estimation approach for multi-rate industrial processes

Z Feng, Y Li, B Sun, C Yang, T Huang - Information Sciences, 2022 - Elsevier
Discrete and delayed laboratory analyses of product quality restrict the operational
optimization of industrial processes. However, it is challenging to build an accurate online …

Fuzzy stochastic configuration networks for nonlinear system modeling

K Li, J Qiao, D Wang - IEEE Transactions on Fuzzy Systems, 2023 - ieeexplore.ieee.org
This article proposes a novel randomized neuro-fuzzy model called fuzzy stochastic
configuration networks (F-SCNs), which integrates the Takagi–Sugeno (T–S) fuzzy inference …

A deep residual PLS for data-driven quality prediction modeling in industrial process

X Yuan, W Xu, Y Wang, C Yang… - IEEE/CAA Journal of …, 2024 - ieeexplore.ieee.org
Partial least squares (PLS) model is the most typical data-driven method for quality-related
industrial tasks like soft sensor. However, only linear relations are captured between the …

ConvLSTM and self-attention aided canonical correlation analysis for multioutput soft sensor modeling

X Zhu, SK Damarla, K Hao, B Huang… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
The polymerization process produces industrially important products; hence, its monitoring
and control are of paramount importance. However, the nonavailability of real-time (on …

Active fault isolation of over-actuated systems based on a control allocation approach

F Cao, Z Zhang, X He - IEEE Transactions on Instrumentation …, 2022 - ieeexplore.ieee.org
Active fault diagnosis is one of the latest frontiers in the field of fault diagnosis, which can
improve fault diagnosis performance by redesigning the control input for specific faults …

Distributed robust process monitoring based on optimized denoising autoencoder with reinforcement learning

S Chen, Q Jiang - IEEE Transactions on Instrumentation and …, 2022 - ieeexplore.ieee.org
Global monitoring for complex large-scale chemical processes is often challenging because
of complex correlations among variables. This article proposes an optimized denoising …

Multirate-former: an efficient transformer-based hierarchical network for multi-step prediction of multirate industrial processes

D Liu, Y Wang, C Liu, X Yuan… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Due to the limitations of measurement technology and cost in industrial processes, it is
difficult to obtain measured values of variables with different properties, such as flow rate …

Deep nonlinear dynamic feature extraction for quality prediction based on spatiotemporal neighborhood preserving SAE

C Liu, K Wang, Y Wang, S **e… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Complex industrial process data often exhibit nonlinear static and dynamic characteristics.
Traditional deep learning methods such as stacked autoencoder (SAE) have excellent …