{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T18:30:22Z","timestamp":1768415422078,"version":"3.49.0"},"reference-count":56,"publisher":"SAGE Publications","issue":"5-6","license":[{"start":{"date-parts":[[2018,9,17]],"date-time":"2018-09-17T00:00:00Z","timestamp":1537142400000},"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":["Structural Health Monitoring"],"published-print":{"date-parts":[[2019,11]]},"abstract":"<jats:p> The structural health monitoring relies on the continuous observation of a dynamic system over time to identify its actual condition, detect abnormal behaviors, and predict future states. The regular changes in environmental factors have been reported as one of the main challenges for the application of structural health monitoring systems. These influences in the structural responses are in general nonlinear, affecting the damage-sensitive features in the most varied forms. The usual process to remove these normal changes is referred to as data normalization. In that regard, principal component analysis is probably the most studied algorithm in structural health monitoring, having numerous versions to learn strong nonlinear normal changes. However, in most cases, not all variability is properly accounted for via the existing nonlinear principal component analysis approaches, resulting in poor damage detection and quantification performances. In this article, a new paradigm based on deep principal component analysis, rooted in the deep learning field, is presented to overcome these limitations. This approach extracts the most salient underlying feature distributions by stacking multiple feedforward neural networks trained to learn an identity mapping of the input variables, where the network inputs are reproduced into the outputs. Similar to the traditional nonlinear principal component analysis\u2013based approach, our approach identifies a nonlinear output-only model of an undamaged structure by comprising modal features into an internal bottleneck layer, which implicitly represents the independent environmental factors. The proposed technique is validated through the application on a progressively damaged prestressed concrete bridge and a three-span suspension bridge. The experimental results demonstrate that capturing the most slight nonlinear variations in the data can lead to improved data normalization and, consequently, better damage detection and quantification performances. <\/jats:p>","DOI":"10.1177\/1475921718799070","type":"journal-article","created":{"date-parts":[[2018,9,18]],"date-time":"2018-09-18T05:38:46Z","timestamp":1537249126000},"page":"1444-1463","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":51,"title":["Deep principal component analysis: An enhanced approach for structural damage identification"],"prefix":"10.1177","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7897-3978","authenticated-orcid":false,"given":"Mois\u00e9s","family":"Silva","sequence":"first","affiliation":[{"name":"Applied Electromagnetism Laboratory, Universidade Federal do Par\u00e1, Bel\u00e9m, Brazil"}]},{"given":"Adam","family":"Santos","sequence":"additional","affiliation":[{"name":"Applied Electromagnetism Laboratory, Universidade Federal do Par\u00e1, Bel\u00e9m, Brazil"},{"name":"Faculty of Computing and Electrical Engineering, Universidade Federal do Sul e Sudeste do Par\u00e1, Marab\u00e1, Brazil"}]},{"given":"Reginaldo","family":"Santos","sequence":"additional","affiliation":[{"name":"Applied Electromagnetism Laboratory, Universidade Federal do Par\u00e1, Bel\u00e9m, Brazil"}]},{"given":"Eloi","family":"Figueiredo","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Universidade Lus\u00f3fona de Humanidades e Tecnologias, Lisbon, Portugal"},{"name":"CONSTRUCT\u2014Institute of R&D in Structures and Construction, Porto, Portugal"}]},{"given":"Claudomiro","family":"Sales","sequence":"additional","affiliation":[{"name":"Applied Electromagnetism Laboratory, Universidade Federal do Par\u00e1, Bel\u00e9m, Brazil"}]},{"given":"Jo\u00e3o CWA","family":"Costa","sequence":"additional","affiliation":[{"name":"Applied Electromagnetism Laboratory, Universidade Federal do Par\u00e1, Bel\u00e9m, Brazil"}]}],"member":"179","published-online":{"date-parts":[[2018,9,17]]},"reference":[{"key":"bibr1-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1177\/1077546316674544"},{"key":"bibr2-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsv.2015.03.038"},{"key":"bibr3-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1002\/9781118443118.ch7"},{"key":"bibr4-1475921718799070","first-page":"455","volume-title":"Damage assessment of structures VII","volume":"347","author":"Sampaio R","year":"2007"},{"key":"bibr5-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2006.1935"},{"key":"bibr6-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1007\/s13349-011-0015-7"},{"key":"bibr7-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1177\/1475921713502836"},{"key":"bibr8-1475921718799070","first-page":"717","volume-title":"Proceedings of the 4th international workshop on structural health monitoring: from diagnostic & prognostics to structural health monitoring","author":"Kullaa J."},{"key":"bibr9-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1177\/1475921711419995"},{"key":"bibr10-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2014.2299528"},{"key":"bibr11-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2015.2450352"},{"key":"bibr12-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2016.02.027"},{"key":"bibr13-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2005.04.001"},{"key":"bibr14-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2010.01.023"},{"key":"bibr15-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2012.03.050"},{"key":"bibr16-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1088\/0964-1726\/10\/3\/314"},{"key":"bibr17-1475921718799070","first-page":"187","volume-title":"Proceedings of the 3rd international conference on identification in engineering systems","author":"Manson G"},{"key":"bibr18-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2012.0031"},{"key":"bibr19-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2012.08.026"},{"key":"bibr20-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2006.1925"},{"key":"bibr21-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1006\/jsvi.1999.2514"},{"key":"bibr22-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2004.12.002"},{"key":"bibr23-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2014.05.029"},{"key":"bibr24-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2015.07.045"},{"key":"bibr25-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2004.12.003"},{"key":"bibr26-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90014-2"},{"key":"bibr27-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(94)00098-7"},{"key":"bibr28-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1006\/jsvi.1996.0747"},{"key":"bibr29-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1002\/aic.690370209"},{"key":"bibr30-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7091-0399-9_2"},{"key":"bibr31-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1177\/1475921710388971"},{"key":"bibr32-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2011.01.005"},{"key":"bibr33-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1088\/0964-1726\/18\/12\/125022"},{"key":"bibr34-1475921718799070","first-page":"139217","volume":"2015","author":"Yuqing Z","year":"2015","journal-title":"Shock Vib"},{"key":"bibr35-1475921718799070","volume-title":"Deep Learning","author":"Goodfellow I","year":"2016"},{"key":"bibr36-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"bibr37-1475921718799070","doi-asserted-by":"crossref","first-page":"153","DOI":"10.7551\/mitpress\/7503.003.0024","volume-title":"Advances in neural information processing systems 19","author":"Bengio Y","year":"2007"},{"key":"bibr38-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80023-1"},{"key":"bibr39-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"bibr40-1475921718799070","unstructured":"Luttrell SP. A unified theory of density models and auto-encoders. DERA technical report, DERA, Cambridge, 31 October 1997."},{"key":"bibr41-1475921718799070","first-page":"37","volume-title":"Proceedings of the 2011 international conference on unsupervised and transfer learning workshop","volume":"27","author":"Baldi P"},{"key":"bibr42-1475921718799070","unstructured":"Van der Maaten L, Postma E, van den Herik J. Dimensionality reduction: a comparative review. Technical report, Tilburg University, Tilburg, 26 October 2009."},{"key":"bibr43-1475921718799070","first-page":"1096","volume-title":"Proceedings of the 25th international conference on machine learning","author":"Vincent P"},{"key":"bibr44-1475921718799070","first-page":"580","volume-title":"Advances in neural information processing systems 5","author":"DeMers D","year":"1993"},{"key":"bibr45-1475921718799070","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.7551\/mitpress\/7503.003.0147","volume-title":"Advances in neural information processing systems 19","author":"Ranzato MA","year":"2007"},{"key":"bibr46-1475921718799070","volume-title":"An introduction to multivariate statistical analysis","author":"Anderson TW","year":"1984"},{"key":"bibr47-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1109\/78.295198"},{"key":"bibr48-1475921718799070","first-page":"869","volume-title":"IEEE international instrumentation and measurement technology conference (I2MTC) proceedings","author":"Santos ADF"},{"key":"bibr49-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"bibr50-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1006\/mssp.1999.1249"},{"key":"bibr51-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1016\/j.engstruct.2014.08.042"},{"key":"bibr52-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1002\/1096-9845(200102)30:2<149::AID-EQE1>3.0.CO;2-Z"},{"key":"bibr53-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1177\/1475921716654433"},{"key":"bibr54-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1007\/s13349-013-0038-3"},{"key":"bibr55-1475921718799070","first-page":"747","volume-title":"Proceedings of the 6th European workshop on structural health monitoring","author":"Figueiredo E"},{"key":"bibr56-1475921718799070","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb00917.x"}],"container-title":["Structural Health Monitoring"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1475921718799070","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/1475921718799070","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1475921718799070","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T22:27:10Z","timestamp":1740781630000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/1475921718799070"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,17]]},"references-count":56,"journal-issue":{"issue":"5-6","published-print":{"date-parts":[[2019,11]]}},"alternative-id":["10.1177\/1475921718799070"],"URL":"https:\/\/doi.org\/10.1177\/1475921718799070","relation":{},"ISSN":["1475-9217","1741-3168"],"issn-type":[{"value":"1475-9217","type":"print"},{"value":"1741-3168","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,9,17]]}}}