Loading…
Non-convex sparse regularization for impact force identification
Many convex regularization methods, such as the classical Tikhonov regularization based on l2-norm penalty and the standard sparse regularization method based on l1-norm penalty, have been widely investigated for impact force identification. However, in many practical applications, these regularizat...
Saved in:
| Published in: | Journal of sound and vibration 2020-07, Vol.477, p.115311, Article 115311 |
|---|---|
| Main Authors: | , , , |
| Format: | Article |
| Language: | English |
| Subjects: | |
| Citations: | Items that this one cites Items that cite this one |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | cdi_FETCH-LOGICAL-c325t-bbfe72cdadb96987b47fff3411d4c42a416d2d22a62c2b630205ef7a9f0564043 |
|---|---|
| cites | cdi_FETCH-LOGICAL-c325t-bbfe72cdadb96987b47fff3411d4c42a416d2d22a62c2b630205ef7a9f0564043 |
| container_end_page | |
| container_issue | |
| container_start_page | 115311 |
| container_title | Journal of sound and vibration |
| container_volume | 477 |
| creator | Qiao, Baijie Ao, Chunyan Mao, Zhu Chen, Xuefeng |
| description | Many convex regularization methods, such as the classical Tikhonov regularization based on l2-norm penalty and the standard sparse regularization method based on l1-norm penalty, have been widely investigated for impact force identification. However, in many practical applications, these regularization methods commonly underestimate the true solution. In this paper, we propose a non-convex sparse regularization method based on lp-norm (0 |
| doi_str_mv | 10.1016/j.jsv.2020.115311 |
| format | article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2440492310</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0022460X20301425</els_id><sourcerecordid>2440492310</sourcerecordid><originalsourceid>FETCH-LOGICAL-c325t-bbfe72cdadb96987b47fff3411d4c42a416d2d22a62c2b630205ef7a9f0564043</originalsourceid><addsrcrecordid>eNp9kE1LxDAQhoMouK7-AG8Fz12TaZpu8aIsfsGiFwVvIU0mkrLb1KRb1F9v1nr2NDPM-87HQ8g5owtGmbhsF20cF0Ah1awsGDsgM0brMl-WYnlIZpQC5FzQt2NyEmNLKa15wWfk-sl3ufbdiJ9Z7FWImAV8321UcN9qcL7LrA-Z2_ZKD_tUY-YMdoOzTv_2T8mRVZuIZ39xTl7vbl9WD_n6-f5xdbPOdQHlkDeNxQq0UaapRb2sGl5ZawvOmOGag-JMGDAASoCGRhTpkRJtpWpLS8EpL-bkYprbB_-xwzjI1u9Cl1ZK4ElQQ8FoUrFJpYOPMaCVfXBbFb4ko3IPSrYygZJ7UHIClTxXkwfT-aPDIKN22Gk0LqAepPHuH_cP6wxwnw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2440492310</pqid></control><display><type>article</type><title>Non-convex sparse regularization for impact force identification</title><source>Elsevier</source><creator>Qiao, Baijie ; Ao, Chunyan ; Mao, Zhu ; Chen, Xuefeng</creator><creatorcontrib>Qiao, Baijie ; Ao, Chunyan ; Mao, Zhu ; Chen, Xuefeng</creatorcontrib><description>Many convex regularization methods, such as the classical Tikhonov regularization based on l2-norm penalty and the standard sparse regularization method based on l1-norm penalty, have been widely investigated for impact force identification. However, in many practical applications, these regularization methods commonly underestimate the true solution. In this paper, we propose a non-convex sparse regularization method based on lp-norm (0 < p < 1) penalty, to seek the sufficiently sparse and highly accurate solution of impact force identification. Firstly, a non-convex optimization model based on lp-norm penalty instead of l2-norm penalty or l1-norm penalty is developed for regularizing inverse problems of impact force identification to overcome the mismatch between l0-norm and l1-norm regularizations. Secondly, an iteratively reweighed l1-norm algorithm is introduced to solve such a non-convex model through transforming it into a series of l1-norm regularizations. Finally, numerical simulation and experimental validation are carried out to evaluate the effectiveness and performance of lp-norm regularization when 0 = p ≤ 1. Our numerical results demonstrate that, compared to the state-of-the-art Tikhonov regularization and l1-norm regularization, the solution of lp-norm regularization achieves more stability, sparseness and accuracy when dealing with the heavily noisy response. Additionally, both numerical and experimental results demonstrate that the peak relative error of the identified impact force using lp-norm regularization has a decreasing tendency as p is approaching 0; while the identification of lp-norm regularization with 0 = p ≤ 1/2 bears no significant difference, which always outperforms that the identification with 1/2 = p ≤ 1.
•A non-convex sparse regularization method based on lp-norm (0 < p < 1) is proposed for impact force identification.•Iteratively reweighted l1-norm minimization is introduced for solving lp-norm regularization of impact identification.•Compared with existing regularizations, the non-convex sparse regularization has much sparser and more accurate result.•The identification performance of lp-norm regularization (0 ≤ p ≤ 1) is evaluated on different p values.</description><identifier>ISSN: 0022-460X</identifier><identifier>EISSN: 1095-8568</identifier><identifier>DOI: 10.1016/j.jsv.2020.115311</identifier><language>eng</language><publisher>Amsterdam: Elsevier Ltd</publisher><subject>Algorithms ; Computational geometry ; Computer simulation ; Convex analysis ; Convexity ; Identification methods ; Impact force identification ; Impact loads ; Inverse problem ; Inverse problems ; Lp-norm regularization ; Mathematical models ; Non-convex ; Numerical analysis ; Optimization ; Regularization ; Regularization methods ; Simulation</subject><ispartof>Journal of sound and vibration, 2020-07, Vol.477, p.115311, Article 115311</ispartof><rights>2020 Elsevier Ltd</rights><rights>Copyright Elsevier Science Ltd. Jul 7, 2020</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c325t-bbfe72cdadb96987b47fff3411d4c42a416d2d22a62c2b630205ef7a9f0564043</citedby><cites>FETCH-LOGICAL-c325t-bbfe72cdadb96987b47fff3411d4c42a416d2d22a62c2b630205ef7a9f0564043</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Qiao, Baijie</creatorcontrib><creatorcontrib>Ao, Chunyan</creatorcontrib><creatorcontrib>Mao, Zhu</creatorcontrib><creatorcontrib>Chen, Xuefeng</creatorcontrib><title>Non-convex sparse regularization for impact force identification</title><title>Journal of sound and vibration</title><description>Many convex regularization methods, such as the classical Tikhonov regularization based on l2-norm penalty and the standard sparse regularization method based on l1-norm penalty, have been widely investigated for impact force identification. However, in many practical applications, these regularization methods commonly underestimate the true solution. In this paper, we propose a non-convex sparse regularization method based on lp-norm (0 < p < 1) penalty, to seek the sufficiently sparse and highly accurate solution of impact force identification. Firstly, a non-convex optimization model based on lp-norm penalty instead of l2-norm penalty or l1-norm penalty is developed for regularizing inverse problems of impact force identification to overcome the mismatch between l0-norm and l1-norm regularizations. Secondly, an iteratively reweighed l1-norm algorithm is introduced to solve such a non-convex model through transforming it into a series of l1-norm regularizations. Finally, numerical simulation and experimental validation are carried out to evaluate the effectiveness and performance of lp-norm regularization when 0 = p ≤ 1. Our numerical results demonstrate that, compared to the state-of-the-art Tikhonov regularization and l1-norm regularization, the solution of lp-norm regularization achieves more stability, sparseness and accuracy when dealing with the heavily noisy response. Additionally, both numerical and experimental results demonstrate that the peak relative error of the identified impact force using lp-norm regularization has a decreasing tendency as p is approaching 0; while the identification of lp-norm regularization with 0 = p ≤ 1/2 bears no significant difference, which always outperforms that the identification with 1/2 = p ≤ 1.
•A non-convex sparse regularization method based on lp-norm (0 < p < 1) is proposed for impact force identification.•Iteratively reweighted l1-norm minimization is introduced for solving lp-norm regularization of impact identification.•Compared with existing regularizations, the non-convex sparse regularization has much sparser and more accurate result.•The identification performance of lp-norm regularization (0 ≤ p ≤ 1) is evaluated on different p values.</description><subject>Algorithms</subject><subject>Computational geometry</subject><subject>Computer simulation</subject><subject>Convex analysis</subject><subject>Convexity</subject><subject>Identification methods</subject><subject>Impact force identification</subject><subject>Impact loads</subject><subject>Inverse problem</subject><subject>Inverse problems</subject><subject>Lp-norm regularization</subject><subject>Mathematical models</subject><subject>Non-convex</subject><subject>Numerical analysis</subject><subject>Optimization</subject><subject>Regularization</subject><subject>Regularization methods</subject><subject>Simulation</subject><issn>0022-460X</issn><issn>1095-8568</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><recordid>eNp9kE1LxDAQhoMouK7-AG8Fz12TaZpu8aIsfsGiFwVvIU0mkrLb1KRb1F9v1nr2NDPM-87HQ8g5owtGmbhsF20cF0Ah1awsGDsgM0brMl-WYnlIZpQC5FzQt2NyEmNLKa15wWfk-sl3ufbdiJ9Z7FWImAV8321UcN9qcL7LrA-Z2_ZKD_tUY-YMdoOzTv_2T8mRVZuIZ39xTl7vbl9WD_n6-f5xdbPOdQHlkDeNxQq0UaapRb2sGl5ZawvOmOGag-JMGDAASoCGRhTpkRJtpWpLS8EpL-bkYprbB_-xwzjI1u9Cl1ZK4ElQQ8FoUrFJpYOPMaCVfXBbFb4ko3IPSrYygZJ7UHIClTxXkwfT-aPDIKN22Gk0LqAepPHuH_cP6wxwnw</recordid><startdate>20200707</startdate><enddate>20200707</enddate><creator>Qiao, Baijie</creator><creator>Ao, Chunyan</creator><creator>Mao, Zhu</creator><creator>Chen, Xuefeng</creator><general>Elsevier Ltd</general><general>Elsevier Science Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>KR7</scope></search><sort><creationdate>20200707</creationdate><title>Non-convex sparse regularization for impact force identification</title><author>Qiao, Baijie ; Ao, Chunyan ; Mao, Zhu ; Chen, Xuefeng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c325t-bbfe72cdadb96987b47fff3411d4c42a416d2d22a62c2b630205ef7a9f0564043</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Algorithms</topic><topic>Computational geometry</topic><topic>Computer simulation</topic><topic>Convex analysis</topic><topic>Convexity</topic><topic>Identification methods</topic><topic>Impact force identification</topic><topic>Impact loads</topic><topic>Inverse problem</topic><topic>Inverse problems</topic><topic>Lp-norm regularization</topic><topic>Mathematical models</topic><topic>Non-convex</topic><topic>Numerical analysis</topic><topic>Optimization</topic><topic>Regularization</topic><topic>Regularization methods</topic><topic>Simulation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Qiao, Baijie</creatorcontrib><creatorcontrib>Ao, Chunyan</creatorcontrib><creatorcontrib>Mao, Zhu</creatorcontrib><creatorcontrib>Chen, Xuefeng</creatorcontrib><collection>CrossRef</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Civil Engineering Abstracts</collection><jtitle>Journal of sound and vibration</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Qiao, Baijie</au><au>Ao, Chunyan</au><au>Mao, Zhu</au><au>Chen, Xuefeng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Non-convex sparse regularization for impact force identification</atitle><jtitle>Journal of sound and vibration</jtitle><date>2020-07-07</date><risdate>2020</risdate><volume>477</volume><spage>115311</spage><pages>115311-</pages><artnum>115311</artnum><issn>0022-460X</issn><eissn>1095-8568</eissn><abstract>Many convex regularization methods, such as the classical Tikhonov regularization based on l2-norm penalty and the standard sparse regularization method based on l1-norm penalty, have been widely investigated for impact force identification. However, in many practical applications, these regularization methods commonly underestimate the true solution. In this paper, we propose a non-convex sparse regularization method based on lp-norm (0 < p < 1) penalty, to seek the sufficiently sparse and highly accurate solution of impact force identification. Firstly, a non-convex optimization model based on lp-norm penalty instead of l2-norm penalty or l1-norm penalty is developed for regularizing inverse problems of impact force identification to overcome the mismatch between l0-norm and l1-norm regularizations. Secondly, an iteratively reweighed l1-norm algorithm is introduced to solve such a non-convex model through transforming it into a series of l1-norm regularizations. Finally, numerical simulation and experimental validation are carried out to evaluate the effectiveness and performance of lp-norm regularization when 0 = p ≤ 1. Our numerical results demonstrate that, compared to the state-of-the-art Tikhonov regularization and l1-norm regularization, the solution of lp-norm regularization achieves more stability, sparseness and accuracy when dealing with the heavily noisy response. Additionally, both numerical and experimental results demonstrate that the peak relative error of the identified impact force using lp-norm regularization has a decreasing tendency as p is approaching 0; while the identification of lp-norm regularization with 0 = p ≤ 1/2 bears no significant difference, which always outperforms that the identification with 1/2 = p ≤ 1.
•A non-convex sparse regularization method based on lp-norm (0 < p < 1) is proposed for impact force identification.•Iteratively reweighted l1-norm minimization is introduced for solving lp-norm regularization of impact identification.•Compared with existing regularizations, the non-convex sparse regularization has much sparser and more accurate result.•The identification performance of lp-norm regularization (0 ≤ p ≤ 1) is evaluated on different p values.</abstract><cop>Amsterdam</cop><pub>Elsevier Ltd</pub><doi>10.1016/j.jsv.2020.115311</doi></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0022-460X |
| ispartof | Journal of sound and vibration, 2020-07, Vol.477, p.115311, Article 115311 |
| issn | 0022-460X 1095-8568 |
| language | eng |
| recordid | cdi_proquest_journals_2440492310 |
| source | Elsevier |
| subjects | Algorithms Computational geometry Computer simulation Convex analysis Convexity Identification methods Impact force identification Impact loads Inverse problem Inverse problems Lp-norm regularization Mathematical models Non-convex Numerical analysis Optimization Regularization Regularization methods Simulation |
| title | Non-convex sparse regularization for impact force identification |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T05%3A59%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Non-convex%20sparse%20regularization%20for%20impact%20force%20identification&rft.jtitle=Journal%20of%20sound%20and%20vibration&rft.au=Qiao,%20Baijie&rft.date=2020-07-07&rft.volume=477&rft.spage=115311&rft.pages=115311-&rft.artnum=115311&rft.issn=0022-460X&rft.eissn=1095-8568&rft_id=info:doi/10.1016/j.jsv.2020.115311&rft_dat=%3Cproquest_cross%3E2440492310%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c325t-bbfe72cdadb96987b47fff3411d4c42a416d2d22a62c2b630205ef7a9f0564043%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2440492310&rft_id=info:pmid/&rfr_iscdi=true |