Transfer dynamic latent variable modeling for quality prediction of multimode processes
Quality prediction is beneficial to intelligent inspection, advanced process control, operation
optimization, and product quality improvements of complex industrial processes. Most of the …
optimization, and product quality improvements of complex industrial processes. Most of the …
One-dimensional residual GANomaly network-based deep feature extraction model for complex industrial system fault detection
X Deng, L Xiao, X Liu, X Zhang - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
In the era of industrial big data, traditional shallow machine learning-based data analytical
technologies cannot handle complex industrial system fault detection issue effectively. In …
technologies cannot handle complex industrial system fault detection issue effectively. In …
Adversarial transferred data-assisted soft sensor for enhanced multigrade quality prediction
Although recent transfer learning soft sensors show promising applications in multigrade
chemical processes, good prediction performance mainly relies on available target domain …
chemical processes, good prediction performance mainly relies on available target domain …
Domain adaptation for few-sample nonlinear process monitoring with deep networks
Multiple modes are ubiquitous in current industrial processes, and the amount of historical
data contained in different modes may vary considerably. Insufficient data can easily lead to …
data contained in different modes may vary considerably. Insufficient data can easily lead to …
Electro-hydraulic SBW fault diagnosis method based on novel 1DCNN-LSTM with attention mechanisms and transfer learning
S Zhang, W Liang, W Zhao, Z Luan, C Wang… - Mechanical Systems and …, 2024 - Elsevier
Abstract The Electro-hydraulic Steer-by-Wire (EH-SBW) is the future trend of commercial
vehicle steering systems due to their dual actuator redundancy. The accurate fault diagnosis …
vehicle steering systems due to their dual actuator redundancy. The accurate fault diagnosis …
Self-Tuning Transfer Dynamic Convolution Autoencoder for Quality Prediction of Multimode Processes With Shifts
Process shift of multimode process involving data distribution and dynamic relation makes
traditional transfer learning methods be intractable and even result in negative transfer. To …
traditional transfer learning methods be intractable and even result in negative transfer. To …
Unsupervised domain adversarial network for few-sample fault detection in industrial processes
Industrial processes are evolving to become larger and more integrated, resulting in
frequent transitions between different operating conditions. When performing fault detection …
frequent transitions between different operating conditions. When performing fault detection …
Predictions of multiple food quality parameters using near-infrared spectroscopy with a novel multi-task genetic programming approach
Y Yang, S Sun, L Pan, M Huang, Q Zhu - Food Control, 2023 - Elsevier
In order to meet the increasing demand for food safety and quality, new methods for
simultaneous and rapid determination of multiple food quality parameters (FQPs) are …
simultaneous and rapid determination of multiple food quality parameters (FQPs) are …
Historical Information-Aided Monitoring of Few-Sample Modes in Industrial Processes With Orthogonal Transferred Projection
K Wang, X Lei, W Zhou, S Cheng… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Few-sample modes are easy to appear when a new working condition is triggered in
industrial processes especially during the early stages of the new working mode. However …
industrial processes especially during the early stages of the new working mode. However …
Nonlinear dynamic transfer partial least squares for domain adaptive regression
Z Zhao, G Yan, M Ren, L Cheng, R Li, Y Pang - ISA transactions, 2024 - Elsevier
Aiming to address soft sensing model degradation under changing working conditions, and
to accommodate dynamic, nonlinear, and multimodal data characteristics, this paper …
to accommodate dynamic, nonlinear, and multimodal data characteristics, this paper …