[HTML][HTML] Data analytics and machine learning for smart process manufacturing: Recent advances and perspectives in the big data era

C Shang, F You - Engineering, 2019 - Elsevier
Safe, efficient, and sustainable operations and control are primary objectives in industrial
manufacturing processes. State-of-the-art technologies heavily rely on human intervention …

Slow down to go better: A survey on slow feature analysis

P Song, C Zhao - IEEE Transactions on Neural Networks and …, 2022 - ieeexplore.ieee.org
Temporal data contain a wealth of valuable information, playing an essential role in various
machine-learning tasks. Slow feature analysis (SFA), one of the most classic temporal …

Retrospective comparison of several typical linear dynamic latent variable models for industrial process monitoring

J Zheng, C Zhao, F Gao - Computers & Chemical Engineering, 2022 - Elsevier
Process dynamic behaviors resulting from closed-loop control and the inherence of
processes are ubiquitous in industrial processes and bring a considerable challenge for …

Process data analytics via probabilistic latent variable models: A tutorial review

Z Ge - Industrial & Engineering Chemistry Research, 2018 - ACS Publications
Dimensionality reduction is important for the high-dimensional nature of data in the process
industry, which has made latent variable modeling methods popular in recent years. By …

Fault-tolerant soft sensors for dynamic systems

H Chen, B Huang - IEEE Transactions on Control Systems …, 2023 - ieeexplore.ieee.org
Unpredicted faults occurring in automation systems deteriorate the performance of soft
sensors and may even lead to incorrect results. To address the problem, this study develops …

Supervised variational autoencoders for soft sensor modeling with missing data

R Xie, NM Jan, K Hao, L Chen… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Autoencoder (AE) is a deep neural network that has been widely utilized in process industry
owing to its superior abilities of feature extraction and data reconstruction. Recently …

Dual attention-based encoder–decoder: A customized sequence-to-sequence learning for soft sensor development

L Feng, C Zhao, Y Sun - IEEE Transactions on Neural …, 2020 - ieeexplore.ieee.org
Soft sensor techniques have been applied to predict the hard-to-measure quality variables
based on the easy-to-measure process variables in industry scenarios. Since the products …

Slow-varying dynamics-assisted temporal capsule network for machinery remaining useful life estimation

Y Qin, C Yuen, Y Shao, B Qin… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Capsule network (CapsNet) acts as a promising alternative to the typical convolutional
neural network, which is the dominant network to develop the remaining useful life (RUL) …

A generalized probabilistic monitoring model with both random and sequential data

W Yu, M Wu, B Huang, C Lu - Automatica, 2022 - Elsevier
Many multivariate statistical analysis methods and their corresponding probabilistic
counterparts have been adopted to develop process monitoring models in recent decades …

Data-driven batch-end quality modeling and monitoring based on optimized sparse partial least squares

Q Jiang, X Yan, H Yi, F Gao - IEEE Transactions on Industrial …, 2019 - ieeexplore.ieee.org
Batch-end quality modeling is used to predict the quality by using batch measurements and
generally involves a large number of predictor variables. However, not all of the variables …