Machinery Health Monitoring Based on Unsupervised Feature Learning via Generative Adversarial Networks. Dai, J., Wang, J., Huang, W., Shi, J., & Zhu, Z. IEEE/ASME Transactions on Mechatronics, 25(5):2252–2263, October, 2020. Conference Name: IEEE/ASME Transactions on Mechatronicsdoi abstract bibtex It confronts great difficulty to apply traditional artificial intelligence (AI) techniques to machinery prognostics and health management in manufacturing systems due to the lack of abnormal samples corresponding to different fault conditions. This article explores an unsupervised feature learning method for machinery health monitoring by proposing a generative adversarial networks (GAN) model that exploits the merits of the autoencoder and the traditional GAN. The major contribution is that the data distribution of the normal samples is accurately learned by the GAN model within both the signal spectrum and latent representation spaces. Specifically, the discriminative feature for machinery health monitoring is learned in an unsupervised manner by the proposed method in three steps. First, the proposed GAN model is trained by the normal samples of the inspected machine with the aim to correctly reconstruct the signal spectrum and its latent representation. Then, the trained model is applied to test the online samples of the same machine with unknown health conditions. Finally, the dissimilarity between the tested samples and their reconstructed ones in the latent representation space is taken as the discriminative feature. The feature value will increase significantly if a fault occurs in the inspected machine because the abnormal samples are never trained in the proposed GAN model. Experimental studies on three different machines are conducted to validate the proposed method and its superiority over the traditional methods in detecting abnormal points and characterizing fault propagation.
@article{dai_machinery_2020,
title = {Machinery {Health} {Monitoring} {Based} on {Unsupervised} {Feature} {Learning} via {Generative} {Adversarial} {Networks}},
volume = {25},
issn = {1941-014X},
doi = {10.1109/TMECH.2020.3012179},
abstract = {It confronts great difficulty to apply traditional artificial intelligence (AI) techniques to machinery prognostics and health management in manufacturing systems due to the lack of abnormal samples corresponding to different fault conditions. This article explores an unsupervised feature learning method for machinery health monitoring by proposing a generative adversarial networks (GAN) model that exploits the merits of the autoencoder and the traditional GAN. The major contribution is that the data distribution of the normal samples is accurately learned by the GAN model within both the signal spectrum and latent representation spaces. Specifically, the discriminative feature for machinery health monitoring is learned in an unsupervised manner by the proposed method in three steps. First, the proposed GAN model is trained by the normal samples of the inspected machine with the aim to correctly reconstruct the signal spectrum and its latent representation. Then, the trained model is applied to test the online samples of the same machine with unknown health conditions. Finally, the dissimilarity between the tested samples and their reconstructed ones in the latent representation space is taken as the discriminative feature. The feature value will increase significantly if a fault occurs in the inspected machine because the abnormal samples are never trained in the proposed GAN model. Experimental studies on three different machines are conducted to validate the proposed method and its superiority over the traditional methods in detecting abnormal points and characterizing fault propagation.},
number = {5},
journal = {IEEE/ASME Transactions on Mechatronics},
author = {Dai, Jun and Wang, Jun and Huang, Weiguo and Shi, Juanjuan and Zhu, Zhongkui},
month = oct,
year = {2020},
note = {Conference Name: IEEE/ASME Transactions on Mechatronics},
keywords = {Artificial intelligence (AI), Feature extraction, Gallium nitride, Generative adversarial networks, Generators, Monitoring, Training, deep learning, ecml, generative adversarial networks (GAN), machinery health monitoring, smart manufacturing, unsupervised learning},
pages = {2252--2263},
}
Downloads: 0
{"_id":"7mbKEzW3tahmjWMNa","bibbaseid":"dai-wang-huang-shi-zhu-machineryhealthmonitoringbasedonunsupervisedfeaturelearningviagenerativeadversarialnetworks-2020","author_short":["Dai, J.","Wang, J.","Huang, W.","Shi, J.","Zhu, Z."],"bibdata":{"bibtype":"article","type":"article","title":"Machinery Health Monitoring Based on Unsupervised Feature Learning via Generative Adversarial Networks","volume":"25","issn":"1941-014X","doi":"10.1109/TMECH.2020.3012179","abstract":"It confronts great difficulty to apply traditional artificial intelligence (AI) techniques to machinery prognostics and health management in manufacturing systems due to the lack of abnormal samples corresponding to different fault conditions. This article explores an unsupervised feature learning method for machinery health monitoring by proposing a generative adversarial networks (GAN) model that exploits the merits of the autoencoder and the traditional GAN. The major contribution is that the data distribution of the normal samples is accurately learned by the GAN model within both the signal spectrum and latent representation spaces. Specifically, the discriminative feature for machinery health monitoring is learned in an unsupervised manner by the proposed method in three steps. First, the proposed GAN model is trained by the normal samples of the inspected machine with the aim to correctly reconstruct the signal spectrum and its latent representation. Then, the trained model is applied to test the online samples of the same machine with unknown health conditions. Finally, the dissimilarity between the tested samples and their reconstructed ones in the latent representation space is taken as the discriminative feature. The feature value will increase significantly if a fault occurs in the inspected machine because the abnormal samples are never trained in the proposed GAN model. Experimental studies on three different machines are conducted to validate the proposed method and its superiority over the traditional methods in detecting abnormal points and characterizing fault propagation.","number":"5","journal":"IEEE/ASME Transactions on Mechatronics","author":[{"propositions":[],"lastnames":["Dai"],"firstnames":["Jun"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Jun"],"suffixes":[]},{"propositions":[],"lastnames":["Huang"],"firstnames":["Weiguo"],"suffixes":[]},{"propositions":[],"lastnames":["Shi"],"firstnames":["Juanjuan"],"suffixes":[]},{"propositions":[],"lastnames":["Zhu"],"firstnames":["Zhongkui"],"suffixes":[]}],"month":"October","year":"2020","note":"Conference Name: IEEE/ASME Transactions on Mechatronics","keywords":"Artificial intelligence (AI), Feature extraction, Gallium nitride, Generative adversarial networks, Generators, Monitoring, Training, deep learning, ecml, generative adversarial networks (GAN), machinery health monitoring, smart manufacturing, unsupervised learning","pages":"2252–2263","bibtex":"@article{dai_machinery_2020,\n\ttitle = {Machinery {Health} {Monitoring} {Based} on {Unsupervised} {Feature} {Learning} via {Generative} {Adversarial} {Networks}},\n\tvolume = {25},\n\tissn = {1941-014X},\n\tdoi = {10.1109/TMECH.2020.3012179},\n\tabstract = {It confronts great difficulty to apply traditional artificial intelligence (AI) techniques to machinery prognostics and health management in manufacturing systems due to the lack of abnormal samples corresponding to different fault conditions. This article explores an unsupervised feature learning method for machinery health monitoring by proposing a generative adversarial networks (GAN) model that exploits the merits of the autoencoder and the traditional GAN. The major contribution is that the data distribution of the normal samples is accurately learned by the GAN model within both the signal spectrum and latent representation spaces. Specifically, the discriminative feature for machinery health monitoring is learned in an unsupervised manner by the proposed method in three steps. First, the proposed GAN model is trained by the normal samples of the inspected machine with the aim to correctly reconstruct the signal spectrum and its latent representation. Then, the trained model is applied to test the online samples of the same machine with unknown health conditions. Finally, the dissimilarity between the tested samples and their reconstructed ones in the latent representation space is taken as the discriminative feature. The feature value will increase significantly if a fault occurs in the inspected machine because the abnormal samples are never trained in the proposed GAN model. Experimental studies on three different machines are conducted to validate the proposed method and its superiority over the traditional methods in detecting abnormal points and characterizing fault propagation.},\n\tnumber = {5},\n\tjournal = {IEEE/ASME Transactions on Mechatronics},\n\tauthor = {Dai, Jun and Wang, Jun and Huang, Weiguo and Shi, Juanjuan and Zhu, Zhongkui},\n\tmonth = oct,\n\tyear = {2020},\n\tnote = {Conference Name: IEEE/ASME Transactions on Mechatronics},\n\tkeywords = {Artificial intelligence (AI), Feature extraction, Gallium nitride, Generative adversarial networks, Generators, Monitoring, Training, deep learning, ecml, generative adversarial networks (GAN), machinery health monitoring, smart manufacturing, unsupervised learning},\n\tpages = {2252--2263},\n}\n\n\n\n","author_short":["Dai, J.","Wang, J.","Huang, W.","Shi, J.","Zhu, Z."],"key":"dai_machinery_2020","id":"dai_machinery_2020","bibbaseid":"dai-wang-huang-shi-zhu-machineryhealthmonitoringbasedonunsupervisedfeaturelearningviagenerativeadversarialnetworks-2020","role":"author","urls":{},"keyword":["Artificial intelligence (AI)","Feature extraction","Gallium nitride","Generative adversarial networks","Generators","Monitoring","Training","deep learning","ecml","generative adversarial networks (GAN)","machinery health monitoring","smart manufacturing","unsupervised learning"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["artificial intelligence (ai)","feature extraction","gallium nitride","generative adversarial networks","generators","monitoring","training","deep learning","ecml","generative adversarial networks (gan)","machinery health monitoring","smart manufacturing","unsupervised learning"],"search_terms":["machinery","health","monitoring","based","unsupervised","feature","learning","via","generative","adversarial","networks","dai","wang","huang","shi","zhu"],"title":"Machinery Health Monitoring Based on Unsupervised Feature Learning via Generative Adversarial Networks","year":2020}