{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T13:58:46Z","timestamp":1770472726273,"version":"3.49.0"},"reference-count":13,"publisher":"SAGE Publications","issue":"6","license":[{"start":{"date-parts":[[2018,6,22]],"date-time":"2018-06-22T00:00:00Z","timestamp":1529625600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2018,6,22]]},"abstract":"<jats:p>Machine learning is widely used for fault diagnosis research. In general, most models used for fault diagnosis are based on the same data distribution, whereas applying equipment to practical productions and operations are mostly done under variable conditions. This often produces changes in data distribution and makes the model unavailable. As one of the most commonly used pieces of equipment in industry, a reciprocating compressor operates under various operating conditions (e.g., variable speed), which may produce changes in data distribution. Thus, the current model established under stable conditions is no longer applicable for fault diagnosis under variable conditions. To solve this problem of variable conditions, a model should be established that 1) reduces the differences caused by different operating conditions as much as possible, and 2) learns representative fault features under different working conditions. Thus, a new strategy that employs an auxiliary model is proposed that combines a convolutional neural network (CNN) and a marginalized stacked denoising autoencoder (mSDA). In our method, 1) the pre-training model CNN is used for feature learning, and 2) the learned features are transformed by mSDA to eliminate data distribution differences between different conditions. A statistical measure based on kernel maximum mean discrepancy is used to evaluate the differences across different domains. Experimental results of a reciprocating compressor under different operating conditions demonstrate that the proposed method can learn class sensitive features and eliminate differences with changing working conditions. It also obtains higher classification accuracy for reciprocating compressor diagnosis under different working conditions.<\/jats:p>","DOI":"10.3233\/jifs-169536","type":"journal-article","created":{"date-parts":[[2018,6,26]],"date-time":"2018-06-26T14:54:08Z","timestamp":1530024848000},"page":"3595-3604","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":5,"title":["Auxiliary-model-based domain adaptation for reciprocating compressor diagnosis under variable conditions"],"prefix":"10.1177","volume":"34","author":[{"given":"Lixiang","family":"Duan","sequence":"first","affiliation":[{"name":"School of Mechanical and Transportation Engineering, China University of Petroleum (Beijing),  Changping, Beijing, China"}]},{"given":"Xuduo","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Transportation Engineering, China University of Petroleum (Beijing),  Changping, Beijing, China"}]},{"given":"Mengyun","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Mechanical and Transportation Engineering, China University of Petroleum (Beijing),  Changping, Beijing, China"}]},{"given":"Zhuang","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Mechanical and Transportation Engineering, China University of Petroleum (Beijing),  Changping, Beijing, China"}]},{"given":"Jinjiang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Transportation Engineering, China University of Petroleum (Beijing),  Changping, Beijing, China"}]}],"member":"179","published-online":{"date-parts":[[2018,6,22]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechmachtheory.2015.03.014"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2016.10.002"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2017.03.034"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1872"},{"key":"e_1_3_2_6_2","first-page":"137","volume-title":"Neural Information Processing Systems","author":"David S.B.","year":"2006","unstructured":"DavidS.B., BlitzerJ., CrammerK., PereiraF., Analysis of representations for domain adaptation, Neural Information Processing Systems, Cambridge: MIT Press, (2006), pp 137\u2013144."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2091281"},{"key":"e_1_3_2_8_2","first-page":"3515","article-title":"Selective transfer machine for personalized facial action unit detection","author":"Chu W.S.","year":"2013","unstructured":"ChuW.S., TorreF.D.L., CohnJ.F., Selective transfer machine for personalized facial action unit detection, IEEE Comput Soc Conf Comput Vis Pettern Recognit (2013), 3515\u20133522.","journal-title":"IEEE Comput Soc Conf Comput Vis Pettern Recognit"},{"key":"e_1_3_2_9_2","first-page":"1410","article-title":"Transfer joint matching for unsupervised domain adaptation","author":"Long M.","year":"2014","unstructured":"LongM., WangJ., DingG., SunJ., YuP.S., Transfer joint matching for unsupervised domain adaptation, IEEE Comput Soc Conf Comput Vis Pettern Recognit (2014), 1410\u20131417.","journal-title":"IEEE Comput Soc Conf Comput Vis Pettern Recognit"},{"key":"e_1_3_2_10_2","volume-title":"International Conference on Machine Learning","author":"Chen M.","year":"2012","unstructured":"ChenM., XuZ., WeinbergerK., ShaF., Marginalized Denoising Autoencoders for Domain Adaptation, International Conference on Machine Learning, Edinburgh Scotland, UK, 2012."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"e_1_3_2_12_2","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent P.","year":"2010","unstructured":"VincentP., LarochelleH., LajoieI., BengioY., ManzagolP.A., Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion, The Journal of Machine Learning Research11 (2010), 3371\u20133408.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_2_13_2","volume-title":"String representations and distances in deep Convolutional Neural Networks for image classification","author":"Ducottet C.","year":"2016","unstructured":"DucottetC.String representations and distances in deep Convolutional Neural Networks for image classification, Elsevier Science Inc, 2016."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btl242"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-169536","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-169536","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-169536","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T19:18:37Z","timestamp":1770405517000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-169536"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,22]]},"references-count":13,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2018,6,22]]}},"alternative-id":["10.3233\/JIFS-169536"],"URL":"https:\/\/doi.org\/10.3233\/jifs-169536","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6,22]]}}}