TY  - CHAP
A1  - Stenger, David
A1  - Altherr, Lena
A1  - Müller, Tankred
A1  - Pelz, Peter F.
T1  - Product family design optimization using model-based engineering techniques
T2  - Operations Research Proceedings 2017
N2  - Highly competitive markets paired with tremendous production volumes demand particularly cost efficient products. The usage of common parts and modules across product families can potentially reduce production costs. Yet, increasing commonality typically results in overdesign of individual products. Multi domain virtual prototyping enables designers to evaluate costs and technical feasibility of different single product designs at reasonable computational effort in early design phases. However, savings by platform commonality are hard to quantify and require detailed knowledge of e.g. the production process and the supply chain. Therefore, we present and evaluate a multi-objective metamodel-based optimization algorithm which enables designers to explore the trade-off between high commonality and cost optimal design of single products.
Y1  - 2018
SN  - 978-3-319-89919-0
U6  - http://dx.doi.org/10.1007/978-3-319-89920-6_66
SP  - 495
EP  - 502
PB  - Springer
CY  - Cham
ER  - 
TY  - CHAP
A1  - Stenger, David
A1  - Altherr, Lena
A1  - Abel, Dirk
T1  - Machine learning and metaheuristics for black-box optimization of product families: a case-study investigating solution quality vs. computational overhead
T2  - Operations Research Proceedings 2018
N2  - In product development, numerous design decisions have to be made. Multi-domain virtual prototyping provides a variety of tools to assess technical feasibility of design options, however often requires substantial computational effort for just a single evaluation. A special challenge is therefore the optimal design of product families, which consist of a group of products derived from a common platform. Finding an optimal platform configuration (stating what is shared and what is individually designed for each product) and an optimal design of all products simultaneously leads to a mixed-integer nonlinear black-box optimization model. We present an optimization approach based on metamodels and a metaheuristic. To increase computational efficiency and solution quality, we compare different types of Gaussian process regression metamodels adapted from the domain of machine learning, and combine them with a genetic algorithm. We illustrate our approach on the example of a product family of electrical drives, and investigate the trade-off between solution quality and computational overhead.
KW  - Product family optimization
KW  - Mixed-integer nonlinear black-box optimization
KW  - Engineering optimization
KW  - Machine learning
Y1  - 2019
SN  - 978-3-030-18499-5  (Print)
SN  - 978-3-030-18500-8 (Online)
U6  - http://dx.doi.org/10.1007/978-3-030-18500-8_47
SP  - 379
EP  - 385
PB  - Springer
CY  - Cham
ER  -