Zobrazeno 1 - 10 of 19 pro vyhledávání: '"Ziqiang Pu"'
1
A One-Class Generative Adversarial Detection Framework for Multifunctional Fault Diagnoses
Autor: Chuan Li, Yun Bai, Diego Cabrera, Ziqiang Pu
Publikováno v: IEEE Transactions on Industrial Electronics. 69:8411-8419
In this article, fault diagnosis is of great significance for system health maintenance. For real applications, diagnosis accuracy suffers from unbalanced data patterns, where normal data are usually abundant than anomaly ones, leading to tremendous
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9925657e44d21b6e96244c1276d09e19
https://doi.org/10.1109/tie.2021.3108719
Zobrazit plný text záznamu
2
Sliced Wasserstein cycle consistency generative adversarial networks for fault data augmentation of an industrial robot
Autor: Ziqiang Pu, Diego Cabrera, Chuan Li, José Valente de Oliveira
We investigate the role of the loss function in cycle consistency generative adversarial networks (CycleGANs). Namely, the sliced Wasserstein distance is proposed for this type of generative model. Both the unconditional and the conditional CycleGANs
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::768af7f98075c7c5b0449d5b3bb45a06
https://hdl.handle.net/10400.1/19480
Zobrazit plný text záznamu
3
VGAN: Generalizing MSE GAN and WGAN-GP for Robot Fault Diagnosis
Autor: Ziqiang Pu, Diego Cabrera, Chuan Li, Jose Valente de Oliveira
Publikováno v: IEEE Intelligent Systems. 37:65-75
Generative adversarial networks (GANs) have shown their potential for data generation. However, this type of generative model often suffers from oscillating training processes and mode collapse, among other issues. To mitigate these, this work propos
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9becc2606f29bd3eeb85edd96d207add
https://doi.org/10.1109/mis.2022.3168356
Zobrazit plný text záznamu
6
Generative adversarial one-shot diagnosis of transmission faults for industrial robots
Autor: Ziqiang Pu, Diego Cabrera, Yun Bai, Chuan Li
Transmission systems of industrial robots are prone to get failures due to harsh operating environments. Fault diagnosis is of great significance for realizing safe operations for industrial robots. However, it is difficult to obtain faulty data in r
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5eb6350a8b6ad760ffa5fdbaa9e6fd13
https://hdl.handle.net/10400.1/19780
Zobrazit plný text záznamu
7
Akademický článek
Exploiting Generative Adversarial Networks as an Oversampling Method for Fault Diagnosis of an Industrial Robotic Manipulator
Autor: Ziqiang Pu, Diego Cabrera, René-Vinicio Sánchez, Mariela Cerrada, Chuan Li, José Valente de Oliveira
Publikováno v: Applied Sciences, Vol 10, Iss 21, p 7712 (2020)
Data-driven machine learning techniques play an important role in fault diagnosis, safety, and maintenance of the industrial robotic manipulator. However, these methods require data that, more often that not, are hard to obtain, especially data colle
Externí odkaz: https://doaj.org/article/7e964dc3684447b9a261c20ef988a179
Zobrazit plný text záznamu
8
Fault Diagnosis for Wind Turbine Gearboxes by Using Deep Enhanced Fusion Network
Autor: Chuan Li, Shaohui Zhang, Yun Bai, Ziqiang Pu
Publikováno v: Repositório Científico de Acesso Aberto de Portugal
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
The gearbox will directly affect the safety and reliability of the wind turbine, whose failure leads to low processing accuracy and certain economic losses. To address this issue, a deep enhanced fusion network (DEFN) is proposed for the fault diagno
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c3b1e0709a1ef01b457356b520b98afe
https://doi.org/10.1109/tim.2020.3024048
Zobrazit plný text záznamu
9
Exploiting graph neural network with one-shot learning for fault diagnosis of rotating machinery (PHM2021)
Autor: Shuai Yang, Xu Chen, Yun Bai, Ziqiang Pu
Due to lack of training samples, overfitting is a severe problem in fault diagnosis for mechanical devices, especially for rotating machinery. In this paper, a graph neural network (GNN) method with one-shot learning is proposed for fault diagnosis o
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a8d0da6b47bdf829f908aee79e6ef236
https://doi.org/10.21203/rs.3.rs-1245521/v1
Zobrazit plný text záznamu
10
Exploiting Generative Adversarial Networks as an Oversampling Method for Fault Diagnosis of an Industrial Robotic Manipulator
Autor: Chuan Li, Mariela Cerrada, Ziqiang Pu, Diego Cabrera, José Valente de Oliveira, René-Vinicio Sánchez
Publikováno v: Applied Sciences
Volume 10
Issue 21
Applied Sciences, Vol 10, Iss 7712, p 7712 (2020)
Repositório Científico de Acesso Aberto de Portugal
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
Data-driven machine learning techniques play an important role in fault diagnosis, safety, and maintenance of the industrial robotic manipulator. However, these methods require data that, more often that not, are hard to obtain, especially data colle
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::db4382be1ef890ba6ca6fc675e3123c6
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje