Mariusz Bujny

Mariusz Bujny

Auto-generated profile, based on publicly available information

Mariusz Bujny

Honda Research Institute Europe GmbH

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2019 in Computer Methods in Applied Mechanics and Engineering
Verified
Journal Article
Closed access
ERElena Raponi
Elena Raponi
MBMariusz Bujny
Mariusz Bujny
MOMarkus Olhofer
Markus Olhofer
NANikola Aulig
Nikola Aulig
SBSimonetta Boria
Simonetta Boria
FDFabian Duddeck
Fabian Duddeck

2 June 2017 in International Journal of Crashworthiness
Verified
Journal Article
Closed access
MBMariusz Bujny
Mariusz Bujny
NANikola Aulig
Nikola Aulig
MOMarkus Olhofer
Markus Olhofer
FDFabian Duddeck
Fabian Duddeck
Structural topology optimisation (TO) methods are well established in many engineering disciplines. However, for highly non-linear problems, including crashworthiness, methods are less developed and still subject to active research. In particular, due to the simplifications made in the state-of-the-art methods as well as heuristic character of most of them, the optimality of the obtained structures is arguable. In this paper, a TO approach based on the level set method and evolutionary algorithms is presented. The method is free from the heuristic assumptions and therefore, allows for a direct optimisation of the underlying crash problem. As a result, a reliable information about the optima of crash problems can be obtained. In order to assure the consistency of the results, a comprehensive study of optimisation settings is performed and discussed. Optimisation results for 2D crash test cases are presented and general conclusions concerning the behaviour of the optimal crash structures are derived.

28 January 2022 in IEEE Transactions on Evolutionary Computation
Verified
Journal Article
Open access
PWPatricia Wollstadt
Patricia Wollstadt
MBMariusz Bujny
Mariusz Bujny
SRSatchit Ramnath
Satchit Ramnath
JSJami J. Shah
Jami J. Shah
DDDuane Detwiler
Duane Detwiler
SMStefan Menzel
Stefan Menzel
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.

1 January 2016
Verified
Conference Paper
Closed access
MBMariusz Bujny
Mariusz Bujny
NANikola Aulig
Nikola Aulig
MOMarkus Olhofer
Markus Olhofer
FDFabian Duddeck
Fabian Duddeck

22 April 2022 in Applied Intelligence
Verified
Journal Article
Open access
PDF file
NDNivesh Dommaraju
Nivesh Dommaraju
MBMariusz Bujny
Mariusz Bujny
SMStefan Menzel
Stefan Menzel
MOMarkus Olhofer
Markus Olhofer
FDFabian Duddeck
Fabian Duddeck
In the early stages of engineering design, multitudes of feasible designs can be generated using structural optimization methods by varying the design requirements or user preferences for different performance objectives. Data mining such potentially large datasets is a challenging task. An unsupervised data-centric approach for exploring designs is to find clusters of similar designs and recommend only the cluster representatives for review. Design similarity can be defined not only on a purely functional level but also based on geometric properties, such as size, shape, and topology. While metrics such as chamfer distance measure the geometrical differences intuitively, it is more useful for design exploration to use metrics based on geometric features, which are extracted from high-dimensional 3D geometric data using dimensionality reduction techniques. If the Euclidean distance in the geometric features is meaningful, the features can be combined with performance attributes resulting in an aggregate feature vector that can potentially be useful in design exploration based on both geometry and performance. We propose a novel approach to evaluate such derived metrics by measuring their similarity with the metrics commonly used in 3D object classification. Furthermore, we measure clustering accuracy, which is a state-of-the-art unsupervised approach to evaluate metrics. For this purpose, we use a labeled, synthetic dataset with topologically complex designs. From our results, we conclude that Pointcloud Autoencoder is promising in encoding geometric features and developing a comprehensive design exploration method.

6 September 2021 in Structural and Multidisciplinary Optimization
Verified
Journal Article
Closed access
PDF file
MBMariusz Bujny
Mariusz Bujny
MOMarkus Olhofer
Markus Olhofer
NANikola Aulig
Nikola Aulig
FDFabian Duddeck
Fabian Duddeck