Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Zhuofu Pan"'
Publikováno v:
IEEE Transactions on Automation Science and Engineering. 20:167-178
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::153d305927ec8c00aea5c87883927b93
https://doi.org/10.1109/tase.2022.3144583
https://doi.org/10.1109/tase.2022.3144583
Publikováno v:
International Journal of Robust and Nonlinear Control. 32:9120-9138
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8634f690ce1bb13aec5ce7d80bc0aadd
https://doi.org/10.1002/rnc.6328
https://doi.org/10.1002/rnc.6328
Publikováno v:
International Journal of Robust and Nonlinear Control. 32:7057-7073
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7fdaa9603a70fe5c62f385878fce4b5b
https://doi.org/10.1002/rnc.6182
https://doi.org/10.1002/rnc.6182
Imputation of Missing Values in Time Series Using an Adaptive-Learned Median-Filled Deep Autoencoder
Publikováno v:
IEEE transactions on cybernetics.
Missing values are ubiquitous in industrial data sets because of multisampling rates, sensor faults, and transmission failures. The incomplete data obstruct the effective use of data and degrade the performance of data-driven models. Numerous imputat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ed45cc33e9f1028ac7658b2cc2cf0b10
https://pubmed.ncbi.nlm.nih.gov/35507613
https://pubmed.ncbi.nlm.nih.gov/35507613
Unsupervised neural networks (NNs) specialize in mining potential patterns from unlabeled data in a self-organizing manner. Recently, they have also been employed as observers for process monitoring using the generated residual signals. However, few
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::385eb932d552a45551db65cb17c53be7
https://doi.org/10.36227/techrxiv.19617534.v1
https://doi.org/10.36227/techrxiv.19617534.v1
This paper presents a segmental autoencoder-based fault detection (FD) framework for nonlinear dynamic systems. The basic idea behind the proposed FD scheme is to identify a generalized kernel representation based on the representation knowledge lear
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::317b299a3ee2ae661ee5a7605a309a50
https://doi.org/10.36227/techrxiv.19067813
https://doi.org/10.36227/techrxiv.19067813
Publikováno v:
Knowledge-Based Systems. 230:107350
Recently, deep learning has become a popular tool for fault detection and diagnosis in chemical processes to learn complex nonlinear features. However, the features extracted from most traditional deep networks are only good representation for the ra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::06d19afcbf4baf6c75b18f79138f7450
https://doi.org/10.1016/j.knosys.2021.107350
https://doi.org/10.1016/j.knosys.2021.107350
Publikováno v:
ISA transactions. 96
Deep learning networks have been recently utilized for fault detection and diagnosis (FDD) due to its effectiveness in handling industrial process data, which are often with high nonlinearities and strong correlations. However, the valuable informati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c22ea46496fe009ce251731ce6130d78
https://pubmed.ncbi.nlm.nih.gov/31324340
https://pubmed.ncbi.nlm.nih.gov/31324340