Pub Date : 2024-01-01DOI: 10.1007/s00158-023-03719-1
Jinhang Zhou, Gang Zhao, Yan Zeng, Gang Li
{"title":"A novel topology optimization method of plate structure based on moving morphable components and grid structure","authors":"Jinhang Zhou, Gang Zhao, Yan Zeng, Gang Li","doi":"10.1007/s00158-023-03719-1","DOIUrl":"https://doi.org/10.1007/s00158-023-03719-1","url":null,"abstract":"","PeriodicalId":21994,"journal":{"name":"Structural and Multidisciplinary Optimization","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139631544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-01Epub Date: 2024-07-10DOI: 10.1007/s00158-024-03816-9
Yulin Guo, Paromita Nath, Sankaran Mahadevan, Paul Witherell
This paper investigates a novel approach to efficiently construct and improve surrogate models in problems with high-dimensional input and output. In this approach, the principal components and corresponding features of the high-dimensional output are first identified. For each feature, the active subspace technique is used to identify a corresponding low-dimensional subspace of the input domain; then a surrogate model is built for each feature in its corresponding active subspace. A low-dimensional adaptive learning strategy is proposed to identify training samples to improve the surrogate model. In contrast to existing adaptive learning methods that focus on a scalar output or a small number of outputs, this paper addresses adaptive learning with high-dimensional input and output, with a novel learning function that balances exploration and exploitation, i.e., considering unexplored regions and high-error regions, respectively. The adaptive learning is in terms of the active variables in the low-dimensional space, and the newly added training samples can be easily mapped back to the original space for running the expensive physics model. The proposed method is demonstrated for the numerical simulation of an additive manufacturing part, with a high-dimensional field output quantity of interest (residual stress) in the component that has spatial variability due to the stochastic nature of multiple input variables (including process variables and material properties). Various factors in the adaptive learning process are investigated, including the number of training samples, range and distribution of the adaptive training samples, contributions of various errors, and the importance of exploration versus exploitation in the learning function.
{"title":"Active learning for adaptive surrogate model improvement in high-dimensional problems.","authors":"Yulin Guo, Paromita Nath, Sankaran Mahadevan, Paul Witherell","doi":"10.1007/s00158-024-03816-9","DOIUrl":"10.1007/s00158-024-03816-9","url":null,"abstract":"<p><p>This paper investigates a novel approach to efficiently construct and improve surrogate models in problems with high-dimensional input and output. In this approach, the principal components and corresponding features of the high-dimensional output are first identified. For each feature, the active subspace technique is used to identify a corresponding low-dimensional subspace of the input domain; then a surrogate model is built for each feature in its corresponding active subspace. A low-dimensional adaptive learning strategy is proposed to identify training samples to improve the surrogate model. In contrast to existing adaptive learning methods that focus on a scalar output or a small number of outputs, this paper addresses adaptive learning with high-dimensional input and output, with a novel learning function that balances exploration and exploitation, i.e., considering unexplored regions and high-error regions, respectively. The adaptive learning is in terms of the active variables in the low-dimensional space, and the newly added training samples can be easily mapped back to the original space for running the expensive physics model. The proposed method is demonstrated for the numerical simulation of an additive manufacturing part, with a high-dimensional field output quantity of interest (residual stress) in the component that has spatial variability due to the stochastic nature of multiple input variables (including process variables and material properties). Various factors in the adaptive learning process are investigated, including the number of training samples, range and distribution of the adaptive training samples, contributions of various errors, and the importance of exploration versus exploitation in the learning function.</p>","PeriodicalId":21994,"journal":{"name":"Structural and Multidisciplinary Optimization","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11236939/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141617153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-21DOI: 10.1007/s00158-023-03707-5
Hao Zheng, Guozhong Zhao, Wen-Xi Han, Yang Yu, Weizhen Chen
{"title":"Concurrent optimization of actuator/sensor layout and control parameter on piezoelectric curved shells with active vibration control for minimizing transient noise","authors":"Hao Zheng, Guozhong Zhao, Wen-Xi Han, Yang Yu, Weizhen Chen","doi":"10.1007/s00158-023-03707-5","DOIUrl":"https://doi.org/10.1007/s00158-023-03707-5","url":null,"abstract":"","PeriodicalId":21994,"journal":{"name":"Structural and Multidisciplinary Optimization","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2023-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138951004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-21DOI: 10.1007/s00158-023-03703-9
Vahid Esfahanian, Mohammad Javad Izadi, Hosein Bashi, Mehran Ansari, Alireza Tavakoli, Mohammad Kordi
{"title":"Aerodynamic shape optimization of gas turbines: a deep learning surrogate model approach","authors":"Vahid Esfahanian, Mohammad Javad Izadi, Hosein Bashi, Mehran Ansari, Alireza Tavakoli, Mohammad Kordi","doi":"10.1007/s00158-023-03703-9","DOIUrl":"https://doi.org/10.1007/s00158-023-03703-9","url":null,"abstract":"","PeriodicalId":21994,"journal":{"name":"Structural and Multidisciplinary Optimization","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2023-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138948510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01DOI: 10.1007/s00158-023-03712-8
Peter D. Dunning
{"title":"Stability constraints for geometrically nonlinear topology optimization","authors":"Peter D. Dunning","doi":"10.1007/s00158-023-03712-8","DOIUrl":"https://doi.org/10.1007/s00158-023-03712-8","url":null,"abstract":"","PeriodicalId":21994,"journal":{"name":"Structural and Multidisciplinary Optimization","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138617343","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01DOI: 10.1007/s00158-023-03708-4
S. Hermansen, Erik Lund
{"title":"Multi-material and thickness optimization of laminated composite structures subject to high-cycle fatigue","authors":"S. Hermansen, Erik Lund","doi":"10.1007/s00158-023-03708-4","DOIUrl":"https://doi.org/10.1007/s00158-023-03708-4","url":null,"abstract":"","PeriodicalId":21994,"journal":{"name":"Structural and Multidisciplinary Optimization","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139015553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01DOI: 10.1007/s00158-023-03709-3
A. Tanhadoust, M. Madhkhan, M. Daei
{"title":"Two-stage optimization method for design of reinforced concrete frames using optimal pre-determined section database and non-revisiting genetic algorithm","authors":"A. Tanhadoust, M. Madhkhan, M. Daei","doi":"10.1007/s00158-023-03709-3","DOIUrl":"https://doi.org/10.1007/s00158-023-03709-3","url":null,"abstract":"","PeriodicalId":21994,"journal":{"name":"Structural and Multidisciplinary Optimization","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138616306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-01DOI: 10.1007/s00158-023-03701-x
Chungang Zhuang, Z. Xiong, Han Ding
{"title":"An efficient 2D/3D NURBS-based topology optimization implementation using page-wise matrix operation in MATLAB","authors":"Chungang Zhuang, Z. Xiong, Han Ding","doi":"10.1007/s00158-023-03701-x","DOIUrl":"https://doi.org/10.1007/s00158-023-03701-x","url":null,"abstract":"","PeriodicalId":21994,"journal":{"name":"Structural and Multidisciplinary Optimization","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138621466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An efficient uncertainty propagation analysis method of non-parameterized P-boxes based on dimension-reduction integral and maximum entropy estimation","authors":"Huichao Xie, Jinwen Li, Haibo Liu, Hao Hu, Daihui Liao","doi":"10.1007/s00158-023-03705-7","DOIUrl":"https://doi.org/10.1007/s00158-023-03705-7","url":null,"abstract":"","PeriodicalId":21994,"journal":{"name":"Structural and Multidisciplinary Optimization","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138991854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-11-29DOI: 10.1007/s00158-023-03706-6
Xianglong Wang, Dongdong Chen, Di Li, Yintang Yang
{"title":"A co-optimization method of thermal-stress coupling 3D integrated system with through silicon via","authors":"Xianglong Wang, Dongdong Chen, Di Li, Yintang Yang","doi":"10.1007/s00158-023-03706-6","DOIUrl":"https://doi.org/10.1007/s00158-023-03706-6","url":null,"abstract":"","PeriodicalId":21994,"journal":{"name":"Structural and Multidisciplinary Optimization","volume":null,"pages":null},"PeriodicalIF":3.9,"publicationDate":"2023-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139212850","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号