Novel transformer based on gated convolutional neural network for dynamic soft sensor modeling of industrial processes

Z Geng, Z Chen, Q Meng, Y Han - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Industrial process data are usually time-series data collected by sensors, which have the
characteristics of high nonlinearity, dynamics, and noises. Many existing soft sensor …

Dynamic historical information incorporated attention deep learning model for industrial soft sensor modeling

Y Wang, D Liu, C Liu, X Yuan, K Wang… - Advanced Engineering …, 2022 - Elsevier
Due to the limitations of sampling conditions and sampling techniques in many real
industrial processes, the process data under different sampling conditions subject to …

A multistep sequence-to-sequence model with attention LSTM neural networks for industrial soft sensor application

L Ma, Y Zhao, B Wang, F Shen - IEEE Sensors Journal, 2023 - ieeexplore.ieee.org
Soft sensor technology is widely used in industries to handle highly nonlinear, dynamic, time-
dependent sequence data of industrial processes for predicting the key variables associated …

A novel soft sensor modeling approach based on difference-LSTM for complex industrial process

J Zhou, X Wang, C Yang… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
The main purpose of soft sensor modeling is to capture the dynamic nonlinear features
between the easy-to-measure auxiliary variables and the difficult-to-measure key variables …

Quality variable prediction for nonlinear dynamic industrial processes based on temporal convolutional networks

X Yuan, S Qi, Y Wang, K Wang, C Yang… - IEEE Sensors …, 2021 - ieeexplore.ieee.org
Soft sensors have been extensively developed to estimate the difficult-to-measure quality
variables for real-time process monitoring and control. Process nonlinearities and dynamics …

Nonlinear dynamic soft sensor modeling with supervised long short-term memory network

X Yuan, L Li, Y Wang - IEEE transactions on industrial …, 2019 - ieeexplore.ieee.org
Soft sensor has been extensively utilized in industrial processes for prediction of key quality
variables. To build an accurate virtual sensor model, it is very significant to model the …

Deep learning for quality prediction of nonlinear dynamic processes with variable attention‐based long short‐term memory network

X Yuan, L Li, Y Wang, C Yang… - The Canadian Journal of …, 2020 - Wiley Online Library
Industrial processes are often characterized with high nonlinearities and dynamics. For soft
sensor modelling, it is important to model the nonlinear and dynamic relationship between …

Soft sensor model for dynamic processes based on multichannel convolutional neural network

X Yuan, S Qi, YAW Shardt, Y Wang, C Yang… - … and Intelligent Laboratory …, 2020 - Elsevier
Soft sensors have been extensively used to predict the difficult-to-measure key quality
variables. The robust soft sensors should be able to sufficiently extract the local dynamic and …

Probabilistic sequential network for deep learning of complex process data and soft sensor application

Q Sun, Z Ge - IEEE Transactions on Industrial Informatics, 2018 - ieeexplore.ieee.org
Soft sensing of quality/key variables is critical to the control and optimization of industrial
processes. One of the main drawbacks of data-driven soft sensors is to deal with the …

Deep learning with spatiotemporal attention-based LSTM for industrial soft sensor model development

X Yuan, L Li, YAW Shardt, Y Wang… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Industrial process data are naturally complex time series with high nonlinearities and
dynamics. To model nonlinear dynamic processes, a long short-term memory (LSTM) …