Similarity control in topology optimization under static and crash loading scenarios

Yousaf, M. Salman; Bujny, Mariusz; Zurbrugg, Nathan; Detwiler, Duane; Duddeck, Fabian

doi:10.1080/0305215x.2020.1806257

Cited by 7 publications

(12 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dissimilarity metric of the current topology to the data set, analogically to the metrics used in the other works [48], [49], is defined as follows:…”

Section: Similarity-based Evolutionary Level Set Methodsmentioning

confidence: 99%

“…Although the obtained designs significantly improve the structural performance, they are far from the hood frames used in the industry, which is a common problem in TO. To some extent, this problem might be mitigated by defining new load cases and imposing additional manufacturing constraints, however, in general case it is difficult to describe all the design criteria in a closed mathematical form [49], and cumbersome manual post-processing of TO results is necessary to obtain manufacturable structures.…”

Section: Similarity-based Topology Optimization Using Evolutionary Level Set Methodsmentioning

confidence: 99%

“…One of the criteria especially important from the perspective of industrial applications of TO is the similarity of the topology being optimized to a certain reference structure [48], [49], which can be, e.g., a prior good design or a part of the design space preferred by the engineer. As a result, manifold criteria related to manufacturability, limitations of the assembly process, economical restrictions, or even aesthetics, can be implicitly incorporated into TO [49]. Very often designs with a certain degree of similarity to the existing structures are preferred, to maximize the commonality of products within a certain group of models, as it is often the case in the automotive industry.…”

Section: Structural Topology Optimizationmentioning

confidence: 99%

See 2 more Smart Citations

CarHoods10k: An Industry-Grade Data Set for Representation Learning and Design Optimization in Engineering Applications

Bujny

Ramnath

Shah

et al. 2022

IEEE Trans. Evol. Computat.

Self Cite

View full text Add to dashboard Cite

Large-scale, high-quality data sets are central to the development of advanced machine learning techniques that increase the effectiveness of existing optimization methods or even inspire novel ones. Especially in the engineering domain such high quality data sets are rare due to confidentiality concerns and generation costs, be it computational or manual efforts. We therefore introduce the OSU-Honda Automobile Hood Dataset (CarHoods10k), an industry-grade 3D vehicle hood data set of over 10000 shapes along with mechanical performance data that were validated against real-world hood designs by industry experts. CarHoods10k offers researchers and practitioners the unique opportunity to develop novel methods on realistic data with relevance to real-world vehicle design. To illustrating central use cases, we first apply methods from geometric deep learning to learn a compact latent representation for design space exploration. Second, we use machine learning models to predict mechanical hood performance from the learned latent representation. We thus demonstrate the effectiveness of machine learning for building metamodels, which are used in design optimization whenever possible to replace costly engineering simulations. Third, we integrate CarHoods10k in a topology optimization approach based on evolutionary algorithms to demonstrate its capability to search for high-performing structures, while maintaining manufacturability constraints.

show abstract

“…The dissimilarity metric of the current topology to the data set, analogically to the metrics used in the other works [48], [49], is defined as follows:…”

Section: Similarity-based Evolutionary Level Set Methodsmentioning

confidence: 99%

Section: Similarity-based Topology Optimization Using Evolutionary Level Set Methodsmentioning

confidence: 99%

Section: Structural Topology Optimizationmentioning

confidence: 99%

See 1 more Smart Citation

CarHoods10k: An Industry-Grade Data Set for Representation Learning and Design Optimization in Engineering Applications

Bujny

Ramnath

Shah

et al. 2022

IEEE Trans. Evol. Computat.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In our previous works 33 , 34 , we have validated the ESM using standard TO benchmark test cases and demonstrated its usefulness in solving nonlinear dynamic crash as well as industrial-scale problems. Despite the high practical value of ESM, it remained computationally costly, since, to find a design of a given similarity w.r.t.…”

Section: Introductionmentioning

confidence: 99%

“…In the context of crash load cases, which are essential in the development of car body structures, analytical sensitivities are usually not available 32 and alternative methods, such as heuristic HCA approach 13 , 14 or the MMC-based nongradient techniques 8 – 11 have to be used. To address such problems, recently, an Energy Scaling Method (ESM) 33 , 34 , which is able to control similarity of the structure being optimized to a reference design, was proposed. Since the method directly scales the elemental energies obtained from the finite element simulation model, it is independent of the density update rules utilized in the underlying TO approach, and, therefore, can be used with both gradient-based and nongradient methods like HCA.…”

Section: Introductionmentioning

confidence: 99%

Learning hyperparameter predictors for similarity-based multidisciplinary topology optimization

Bujny,

Yousaf,

Zurbrugg

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

Topology optimization (TO) plays a significant role in industry by providing engineers with optimal material distributions based exclusively on the information about the design space and loading conditions. Such approaches are especially important for current multidisciplinary design tasks in industry, where the conflicting criteria often lead to very unintuitive solutions. Despite the progress in integrating manufacturing constraints into TO, one of the main factors restricting the use of TO in practice is the users’ limited control of the final material distribution. To address this problem, recently, a universal methodology for enforcing similarity to reference structures in various TO methods by applying scaling of elemental energies was proposed. The method, however, requires an expensive hyperparameter sampling, which involves running multiple TO processes to find the design of a given similarity to a reference structure. In this article, we propose a novel end-to-end approach for similarity-based TO, which integrates a machine learning model to predict the hyperparameters of the method, and provide the engineer, at minimal computational cost, with a design satisfying multidisciplinary criteria expressed by the similarity to a reference. The training set for the model is generated based on an academic linear elastic problem, but the model generalizes well to both nonlinear dynamic crash and industrial-scale TO problems. We show the latter by applying the proposed methodology to a real-world multidisciplinary TO problem of a car hood frame, which demonstrates the usefulness of the approach in industrial settings.

show abstract

Clustering Topologically-Optimized Designs Based on Structural Deformation

Hutapea

Dommaraju

Bujny

et al. 2022

Proceedings of the Munich Symposium on Lightweight Design 2021

View full text Add to dashboard Cite

Similarity control in topology optimization under static and crash loading scenarios

Cited by 7 publications

References 26 publications

CarHoods10k: An Industry-Grade Data Set for Representation Learning and Design Optimization in Engineering Applications

CarHoods10k: An Industry-Grade Data Set for Representation Learning and Design Optimization in Engineering Applications

Learning hyperparameter predictors for similarity-based multidisciplinary topology optimization

Clustering Topologically-Optimized Designs Based on Structural Deformation

Contact Info

Product

Resources

About