Process monitoring using variational autoencoder for high-dimensional nonlinear processes. Lee, S., Kwak, M., Tsui, K., L., & Kim, S., B. Engineering Applications of Artificial Intelligence, 83(May):13-27, Elsevier Ltd, 2019.
![Process monitoring using variational autoencoder for high-dimensional nonlinear processes [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper ![Process monitoring using variational autoencoder for high-dimensional nonlinear processes [link]](https://bibbase.org/img/filetypes/link.svg "link")
Website doi abstract bibtex
Paper Website doi abstract bibtex In many industries, statistical process monitoring techniques play a key role in improving processes through variation reduction and defect prevention. Modern large-scale industrial processes require appropriate monitoring techniques that can efficiently address high-dimensional nonlinear processes. Such processes have been successfully monitored with several latent variable-based methods. However, because these monitoring methods use Hotelling's T2 statistics in the reduced space, a normality assumption underlies the construction of these tools. This assumption has limited the use of latent variable-based monitoring charts in both nonlinear and nonnormal situations. In this study, we propose a variational autoencoder (VAE) as a monitoring method that can address both nonlinear and nonnormal situations in high-dimensional processes. VAE is appropriate for T2 charts because it causes the reduced space to follow a multivariate normal distribution. The effectiveness and applicability of the proposed VAE-based chart were demonstrated through experiments on simulated data and real data from a thin-film-transistor liquid-crystal display process.
@article{
title = {Process monitoring using variational autoencoder for high-dimensional nonlinear processes},
type = {article},
year = {2019},
keywords = {High-dimensional process,Multivariate control chart,Nonlinear process,Statistical process monitoring,Variational autoencoder},
pages = {13-27},
volume = {83},
websites = {https://doi.org/10.1016/j.engappai.2019.04.013},
publisher = {Elsevier Ltd},
id = {4d5dbb66-19e2-385a-b231-14741e2efe35},
created = {2022-04-05T05:35:08.233Z},
file_attached = {true},
profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},
group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},
last_modified = {2022-04-05T05:35:25.215Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
private_publication = {false},
abstract = {In many industries, statistical process monitoring techniques play a key role in improving processes through variation reduction and defect prevention. Modern large-scale industrial processes require appropriate monitoring techniques that can efficiently address high-dimensional nonlinear processes. Such processes have been successfully monitored with several latent variable-based methods. However, because these monitoring methods use Hotelling's T2 statistics in the reduced space, a normality assumption underlies the construction of these tools. This assumption has limited the use of latent variable-based monitoring charts in both nonlinear and nonnormal situations. In this study, we propose a variational autoencoder (VAE) as a monitoring method that can address both nonlinear and nonnormal situations in high-dimensional processes. VAE is appropriate for T2 charts because it causes the reduced space to follow a multivariate normal distribution. The effectiveness and applicability of the proposed VAE-based chart were demonstrated through experiments on simulated data and real data from a thin-film-transistor liquid-crystal display process.},
bibtype = {article},
author = {Lee, Seulki and Kwak, Mingu and Tsui, Kwok Leung and Kim, Seoung Bum},
doi = {10.1016/j.engappai.2019.04.013},
journal = {Engineering Applications of Artificial Intelligence},
number = {May}
}Downloads: 0
{"_id":"TD5oeoFEtxjtrtEYe","bibbaseid":"lee-kwak-tsui-kim-processmonitoringusingvariationalautoencoderforhighdimensionalnonlinearprocesses-2019","author_short":["Lee, S.","Kwak, M.","Tsui, K., L.","Kim, S., B."],"bibdata":{"title":"Process monitoring using variational autoencoder for high-dimensional nonlinear processes","type":"article","year":"2019","keywords":"High-dimensional process,Multivariate control chart,Nonlinear process,Statistical process monitoring,Variational autoencoder","pages":"13-27","volume":"83","websites":"https://doi.org/10.1016/j.engappai.2019.04.013","publisher":"Elsevier Ltd","id":"4d5dbb66-19e2-385a-b231-14741e2efe35","created":"2022-04-05T05:35:08.233Z","file_attached":"true","profile_id":"235249c2-3ed4-314a-b309-b1ea0330f5d9","group_id":"1ff583c0-be37-34fa-9c04-73c69437d354","last_modified":"2022-04-05T05:35:25.215Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"private_publication":false,"abstract":"In many industries, statistical process monitoring techniques play a key role in improving processes through variation reduction and defect prevention. Modern large-scale industrial processes require appropriate monitoring techniques that can efficiently address high-dimensional nonlinear processes. Such processes have been successfully monitored with several latent variable-based methods. However, because these monitoring methods use Hotelling's T2 statistics in the reduced space, a normality assumption underlies the construction of these tools. This assumption has limited the use of latent variable-based monitoring charts in both nonlinear and nonnormal situations. In this study, we propose a variational autoencoder (VAE) as a monitoring method that can address both nonlinear and nonnormal situations in high-dimensional processes. VAE is appropriate for T2 charts because it causes the reduced space to follow a multivariate normal distribution. The effectiveness and applicability of the proposed VAE-based chart were demonstrated through experiments on simulated data and real data from a thin-film-transistor liquid-crystal display process.","bibtype":"article","author":"Lee, Seulki and Kwak, Mingu and Tsui, Kwok Leung and Kim, Seoung Bum","doi":"10.1016/j.engappai.2019.04.013","journal":"Engineering Applications of Artificial Intelligence","number":"May","bibtex":"@article{\n title = {Process monitoring using variational autoencoder for high-dimensional nonlinear processes},\n type = {article},\n year = {2019},\n keywords = {High-dimensional process,Multivariate control chart,Nonlinear process,Statistical process monitoring,Variational autoencoder},\n pages = {13-27},\n volume = {83},\n websites = {https://doi.org/10.1016/j.engappai.2019.04.013},\n publisher = {Elsevier Ltd},\n id = {4d5dbb66-19e2-385a-b231-14741e2efe35},\n created = {2022-04-05T05:35:08.233Z},\n file_attached = {true},\n profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},\n group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},\n last_modified = {2022-04-05T05:35:25.215Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n private_publication = {false},\n abstract = {In many industries, statistical process monitoring techniques play a key role in improving processes through variation reduction and defect prevention. Modern large-scale industrial processes require appropriate monitoring techniques that can efficiently address high-dimensional nonlinear processes. Such processes have been successfully monitored with several latent variable-based methods. However, because these monitoring methods use Hotelling's T2 statistics in the reduced space, a normality assumption underlies the construction of these tools. This assumption has limited the use of latent variable-based monitoring charts in both nonlinear and nonnormal situations. In this study, we propose a variational autoencoder (VAE) as a monitoring method that can address both nonlinear and nonnormal situations in high-dimensional processes. VAE is appropriate for T2 charts because it causes the reduced space to follow a multivariate normal distribution. The effectiveness and applicability of the proposed VAE-based chart were demonstrated through experiments on simulated data and real data from a thin-film-transistor liquid-crystal display process.},\n bibtype = {article},\n author = {Lee, Seulki and Kwak, Mingu and Tsui, Kwok Leung and Kim, Seoung Bum},\n doi = {10.1016/j.engappai.2019.04.013},\n journal = {Engineering Applications of Artificial Intelligence},\n number = {May}\n}","author_short":["Lee, S.","Kwak, M.","Tsui, K., L.","Kim, S., B."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/48489c6f-a55e-1909-7f2f-b985d36924be/1_s20_S0952197619300983_main.pdf.pdf","Website":"https://doi.org/10.1016/j.engappai.2019.04.013"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"lee-kwak-tsui-kim-processmonitoringusingvariationalautoencoderforhighdimensionalnonlinearprocesses-2019","role":"author","keyword":["High-dimensional process","Multivariate control chart","Nonlinear process","Statistical process monitoring","Variational autoencoder"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["2252seNhipfTmjEBQ"],"keywords":["high-dimensional process","multivariate control chart","nonlinear process","statistical process monitoring","variational autoencoder"],"search_terms":["process","monitoring","using","variational","autoencoder","high","dimensional","nonlinear","processes","lee","kwak","tsui","kim"],"title":"Process monitoring using variational autoencoder for high-dimensional nonlinear processes","year":2019}