Toward Reusable Surrogate Models: Graph-Based Transfer Learning on Trusses

Abstract

Surrogate models are often employed to speed up engineering design optimization; however, they typically require that all training data conform to the same parametrization (e.g. design variables), limiting design freedom and prohibiting the reuse of historical data. In response, this paper proposes Graph-based Surrogate Models (GSMs) for space frame structures. The GSM can accurately predict displacement fields from static loads given the structure's geometry as input, enabling training across multiple parametrizations. GSMs build upon recent advancements in geometric deep learning which have led to the ability to learn on undirected graphs: a natural representation for space frames. To further promote flexible surrogate models, the paper explores transfer learning within the context of engineering design, and demonstrates positive knowledge transfer across data sets of different topologies, complexities, loads and applications, resulting in more flexible and data-efficient surrogate models for space frame structures.

Mapping artificial intelligence-based methods to engineering design stages: a focused literature review

“…We further elaborate on these applications and the potential reason why researchers have focused their AI on this design stage in the section “Conclusion”. In addition to such works, we observed that: two papers have applied NLP for processing texts to model generation (Friedrich et al 2011) and topic extraction for subsequent design performance prediction (Ball and Lewis 2020); two papers have used probabilistic modeling for generating aerodynamic designs (Ghosh et al 2021) and evaluating the environmental impact of designs (Ferrero et al 2021); one paper used network theory-based surrogate modeling for evaluating trusses (Whalen and Mueller 2022); and one paper used the Jaya algorithm as the optimization method for generating a set optimal number of design solutions (Khan and Awan 2018).…”

Design representation for performance evaluation of 3D shapes in structure-aware generative design

“…Although design researchers have been employing common surrogate models outlined in the literature and following industry practices (Cunningham, Simpson & Tucker 2019; Whalen & Mueller 2022), there is limited awareness of AutoML within the engineering design community (Regenwetter, Weaver & Ahmed 2023). Regenwetter et al (2023) took a lead in this regard by comparing the performance of surrogate models constructed using traditional methods (e.g.…”

“…Surrogate modeling is a supervised machine learning technique to approximate the output based on the labeled training dataset (i.e. pairs of inputs and their corresponding outputs) (Sun et al 2020; Whalen & Mueller 2022). Generally, in these surrogate modeling methods, each design is represented as a fixed-length vector of design parameters, referred to as vectorized design representation (VDR).…”

Machine learning for structural design models of continuous beam systems via influence zones

“…respect to system size by taking advantage of a recently developed concept known as a continuous beam's influence zone [37]. This technique could potentially form the basis to generalise a design model for continuous structural systems of arbitrary topology, and might complement other techniques that attempt to address the generalisability issue such as graph neural networks [38,39].…”