Discriminant autoencoder for feature extraction in fault diagnosis

Discriminant autoencoder for feature extraction in fault diagnosis. Luo, X., Li, X., Wang, Z., & Liang, J. Chemometrics and Intelligent Laboratory Systems, 192:103814, September, 2019.

Paper doi abstract bibtex

Nowadays, some traditional autoencoders and their extensions have been widely applied in data-driven fault diagnosis for feature extraction. However, because of the fact that traditional autoencoders could not make use of label information, the representations extracted by these traditional autoencoders may show disappointing results when handling ultimate discriminative task. In this paper, we propose a novel semi-supervised autoencoder, which is named as Discriminant Autoencoder. The training of proposed Discriminant Autoencoder includes a supervised process and an unsupervised process. And a distance penalty is added into the loss function, which enables the proposed Discriminant Autoencoder to extract more suitable representations from industrial data samples. In order to explain the effectiveness of this semi-supervised autoencoder, we carry out some experiments and give out a mathematical derivation. Here we use an industrial batch process dataset as the criterion dataset to test the performance of proposed Discriminant Autoencoder and other conventional autoencoders.

@article{luo_discriminant_2019,
	title = {Discriminant autoencoder for feature extraction in fault diagnosis},
	volume = {192},
	issn = {0169-7439},
	url = {https://www.sciencedirect.com/science/article/pii/S0169743918306257},
	doi = {10.1016/j.chemolab.2019.103814},
	abstract = {Nowadays, some traditional autoencoders and their extensions have been widely applied in data-driven fault diagnosis for feature extraction. However, because of the fact that traditional autoencoders could not make use of label information, the representations extracted by these traditional autoencoders may show disappointing results when handling ultimate discriminative task. In this paper, we propose a novel semi-supervised autoencoder, which is named as Discriminant Autoencoder. The training of proposed Discriminant Autoencoder includes a supervised process and an unsupervised process. And a distance penalty is added into the loss function, which enables the proposed Discriminant Autoencoder to extract more suitable representations from industrial data samples. In order to explain the effectiveness of this semi-supervised autoencoder, we carry out some experiments and give out a mathematical derivation. Here we use an industrial batch process dataset as the criterion dataset to test the performance of proposed Discriminant Autoencoder and other conventional autoencoders.},
	language = {en},
	urldate = {2022-05-02},
	journal = {Chemometrics and Intelligent Laboratory Systems},
	author = {Luo, Xiaoyi and Li, Xianmin and Wang, Ziyang and Liang, Jun},
	month = sep,
	year = {2019},
	keywords = {Autoencoder, Fault diagnosis, Feature extraction, Semi-supervised autoencoder},
	pages = {103814},
}

Downloads: 0

{"_id":"hfJnwebxZvPMzPQyg","bibbaseid":"luo-li-wang-liang-discriminantautoencoderforfeatureextractioninfaultdiagnosis-2019","author_short":["Luo, X.","Li, X.","Wang, Z.","Liang, J."],"bibdata":{"bibtype":"article","type":"article","title":"Discriminant autoencoder for feature extraction in fault diagnosis","volume":"192","issn":"0169-7439","url":"https://www.sciencedirect.com/science/article/pii/S0169743918306257","doi":"10.1016/j.chemolab.2019.103814","abstract":"Nowadays, some traditional autoencoders and their extensions have been widely applied in data-driven fault diagnosis for feature extraction. However, because of the fact that traditional autoencoders could not make use of label information, the representations extracted by these traditional autoencoders may show disappointing results when handling ultimate discriminative task. In this paper, we propose a novel semi-supervised autoencoder, which is named as Discriminant Autoencoder. The training of proposed Discriminant Autoencoder includes a supervised process and an unsupervised process. And a distance penalty is added into the loss function, which enables the proposed Discriminant Autoencoder to extract more suitable representations from industrial data samples. In order to explain the effectiveness of this semi-supervised autoencoder, we carry out some experiments and give out a mathematical derivation. Here we use an industrial batch process dataset as the criterion dataset to test the performance of proposed Discriminant Autoencoder and other conventional autoencoders.","language":"en","urldate":"2022-05-02","journal":"Chemometrics and Intelligent Laboratory Systems","author":[{"propositions":[],"lastnames":["Luo"],"firstnames":["Xiaoyi"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Xianmin"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Ziyang"],"suffixes":[]},{"propositions":[],"lastnames":["Liang"],"firstnames":["Jun"],"suffixes":[]}],"month":"September","year":"2019","keywords":"Autoencoder, Fault diagnosis, Feature extraction, Semi-supervised autoencoder","pages":"103814","bibtex":"@article{luo_discriminant_2019,\n\ttitle = {Discriminant autoencoder for feature extraction in fault diagnosis},\n\tvolume = {192},\n\tissn = {0169-7439},\n\turl = {https://www.sciencedirect.com/science/article/pii/S0169743918306257},\n\tdoi = {10.1016/j.chemolab.2019.103814},\n\tabstract = {Nowadays, some traditional autoencoders and their extensions have been widely applied in data-driven fault diagnosis for feature extraction. However, because of the fact that traditional autoencoders could not make use of label information, the representations extracted by these traditional autoencoders may show disappointing results when handling ultimate discriminative task. In this paper, we propose a novel semi-supervised autoencoder, which is named as Discriminant Autoencoder. The training of proposed Discriminant Autoencoder includes a supervised process and an unsupervised process. And a distance penalty is added into the loss function, which enables the proposed Discriminant Autoencoder to extract more suitable representations from industrial data samples. In order to explain the effectiveness of this semi-supervised autoencoder, we carry out some experiments and give out a mathematical derivation. Here we use an industrial batch process dataset as the criterion dataset to test the performance of proposed Discriminant Autoencoder and other conventional autoencoders.},\n\tlanguage = {en},\n\turldate = {2022-05-02},\n\tjournal = {Chemometrics and Intelligent Laboratory Systems},\n\tauthor = {Luo, Xiaoyi and Li, Xianmin and Wang, Ziyang and Liang, Jun},\n\tmonth = sep,\n\tyear = {2019},\n\tkeywords = {Autoencoder, Fault diagnosis, Feature extraction, Semi-supervised autoencoder},\n\tpages = {103814},\n}\n\n\n\n","author_short":["Luo, X.","Li, X.","Wang, Z.","Liang, J."],"key":"luo_discriminant_2019","id":"luo_discriminant_2019","bibbaseid":"luo-li-wang-liang-discriminantautoencoderforfeatureextractioninfaultdiagnosis-2019","role":"author","urls":{"Paper":"https://www.sciencedirect.com/science/article/pii/S0169743918306257"},"keyword":["Autoencoder","Fault diagnosis","Feature extraction","Semi-supervised autoencoder"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["autoencoder","fault diagnosis","feature extraction","semi-supervised autoencoder"],"search_terms":["discriminant","autoencoder","feature","extraction","fault","diagnosis","luo","li","wang","liang"],"title":"Discriminant autoencoder for feature extraction in fault diagnosis","year":2019}