TY - GEN

T1 - Learning-based topology variation in evolutionary level set topology optimization

AU - Bujny, Mariusz

AU - Olhofer, Markus

AU - Aulig, Nikola

AU - Duddeck, Fabian

N1 - Publisher Copyright:
© 2018 Association for Computing Machinery.

PY - 2018/7/2

Y1 - 2018/7/2

N2 - The main goal in structural Topology Optimization is to find an optimal distribution of material within a defined design domain, under specified boundary conditions. This task is frequently solved with gradient-based methods, but for some problems, e.g. in the domain of crash Topology Optimization, analytical sensitivity information is not available. The recent Evolutionary Level Set Method (EA-LSM) uses Evolutionary Strategies and a representation based on geometric Level Set Functions to solve such problems. However, computational costs associated with Evolutionary Algorithms are relatively high and grow significantly with rising dimensionality of the optimization problem. In this paper, we propose an improved version of EA-LSM, exploiting an adaptive representation, where the number of structural components increases during the optimization. We employ a learning-based approach, where a pre-trained neural network model predicts favorable topological changes, based on the structural state of the design. The proposed algorithm converges quickly at the beginning, determining good designs in low-dimensional search spaces, and the representation is gradually extended by increasing structural complexity. The approach is evaluated on a standard minimum compliance design problem and its superiority with respect to a random adaptive method is demonstrated.

AB - The main goal in structural Topology Optimization is to find an optimal distribution of material within a defined design domain, under specified boundary conditions. This task is frequently solved with gradient-based methods, but for some problems, e.g. in the domain of crash Topology Optimization, analytical sensitivity information is not available. The recent Evolutionary Level Set Method (EA-LSM) uses Evolutionary Strategies and a representation based on geometric Level Set Functions to solve such problems. However, computational costs associated with Evolutionary Algorithms are relatively high and grow significantly with rising dimensionality of the optimization problem. In this paper, we propose an improved version of EA-LSM, exploiting an adaptive representation, where the number of structural components increases during the optimization. We employ a learning-based approach, where a pre-trained neural network model predicts favorable topological changes, based on the structural state of the design. The proposed algorithm converges quickly at the beginning, determining good designs in low-dimensional search spaces, and the representation is gradually extended by increasing structural complexity. The approach is evaluated on a standard minimum compliance design problem and its superiority with respect to a random adaptive method is demonstrated.

KW - Adaptation

KW - Big Data

KW - Data mining

KW - Deep learning

KW - Evolution Strategies

KW - Mechanical engineering

KW - Neural networks

KW - Self-adaptation

UR - http://www.scopus.com/inward/record.url?scp=85050603728&partnerID=8YFLogxK

U2 - 10.1145/3205455.3205528

DO - 10.1145/3205455.3205528

M3 - Conference contribution

AN - SCOPUS:85050603728

T3 - GECCO 2018 - Proceedings of the 2018 Genetic and Evolutionary Computation Conference

SP - 825

EP - 832

BT - GECCO 2018 - Proceedings of the 2018 Genetic and Evolutionary Computation Conference

PB - Association for Computing Machinery, Inc

T2 - 2018 Genetic and Evolutionary Computation Conference, GECCO 2018

Y2 - 15 July 2018 through 19 July 2018

ER -