Wen Lv
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wen Lv has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Long Xi
School of Cybersecurity, Shaanxi Key Laboratory of Clothing Intelligence, Xi'an Polytechnic University, Xi'an, China
2 shared publications - Tao Xue
School of Cybersecurity, Xi'an Polytechnic University, Xi'an, China
2 shared publications Long Xi
1 shared publicationTao Xue
1 shared publicationTiantian Wang
1 shared publication- Tiantian Wang1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11895-11903
CRFNet: Learning Energy-based Continuous Repulsion Field for Deformable 3D Clothing Dynamics
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11895-11903
Open AccessCRFNet: Learning Energy-based Continuous Repulsion Field for Deformable 3D Clothing Dynamics
- Open Access
- 29 April 2026
- Published by Elsevier in SSRN Electronic Journal
QC-VQD-VAE: A Quality-Conditioned Vector-Quantized Diffusion Framework for Process Monitoring
Overcoming the limitations of traditional quality-related fault detection methods, which often rely heavily on direct regression analysis and struggle to capture the complex process dynamics under the influence of quality variables, this paper proposes a novel conditional process monitoring method based on a Quality-Conditioned Vector Quantized Diffusion Variational Autoencoder (QC-VQDVAE). This end-to-end trainable framework achieves precise detection of quality-relevant faults. Specifically, the method first leverages a Vector Quantized Variational Autoencoder (VQ-VAE) to extract discriminative, discrete latent features associated with quality indicators from process data. Subsequently, a Discrete Feature-Conditioned Diffusion Model (DFCDM) is designed to enhance dynamic modeling. The DFCDM integrates quality indicators as constraints, incorporates temporal embedding for dynamic modeling, and employs an initial condition injection mechanism for superior control, enabling accurate modeling of complex process dynamics and improved adaptive generalization. Experimental results on a numerical case and the Tennessee Eastman process demonstrate that the proposed QC-VQD-VAE framework outperforms both traditional and state-of-the-art methods in terms of fault detection rate, false alarm rate, and robustness, offering a reliable and scalable solution for quality-related monitoring in complex industrial processes.
- 29 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessQC-VQD-VAE: A Quality-Conditioned Vector-Quantized Diffusion Framework for Process Monitoring
Overcoming the limitations of traditional quality-related fault detection methods, which often rely heavily on direct regression analysis and struggle to capture the complex process dynamics under the influence of quality variables, this paper proposes a novel conditional process monitoring method based on a Quality-Conditioned Vector Quantized Diffusion Variational Autoencoder (QC-VQDVAE). This end-to-end trainable framework achieves precise detection of quality-relevant faults. Specifically, the method first leverages a Vector Quantized Variational Autoencoder (VQ-VAE) to extract discriminative, discrete latent features associated with quality indicators from process data. Subsequently, a Discrete Feature-Conditioned Diffusion Model (DFCDM) is designed to enhance dynamic modeling. The DFCDM integrates quality indicators as constraints, incorporates temporal embedding for dynamic modeling, and employs an initial condition injection mechanism for superior control, enabling accurate modeling of complex process dynamics and improved adaptive generalization. Experimental results on a numerical case and the Tennessee Eastman process demonstrate that the proposed QC-VQD-VAE framework outperforms both traditional and state-of-the-art methods in terms of fault detection rate, false alarm rate, and robustness, offering a reliable and scalable solution for quality-related monitoring in complex industrial processes.
- 6 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 313
Industrial anomaly detection via prompt learning with perturbation-based selective state memory units
- 6 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 313
Industrial anomaly detection via prompt learning with perturbation-based selective state memory units