Publication
Leveraging Graph Neural Networks for Graph Regression and Effective Enumeration Reduction
(a) An illustration of the input and output of the Graph Neural Network (GNN) for a graph with a multi-split case featuring a tank and four nodes, one of which is a junction. (b) Illustration of the internal layers of the GNN. (c) Examining the results of the trained Graph Neural Network (GNN) on a new, more complex graph that was not included in the training data. This new graph has a single-split structure with 6 CPHXs, encompassing 4051 different graphs given a heat load. Here, J (Gi ) represents the labels.
Abstract
Leveraging Graph Neural Networks for Graph Regression and Effective Enumeration Reduction
Saeid Bayat, Nastaran Shahmansouri, Satya RT Peddada, Alex Tessier, Adrian Butscher, James T. Allison
We developed a graph-based framework to represent various aspects of optimal thermal management system design, with the aim of rapidly and efficiently identifying optimal design candidates. Initially, the graph-based framework is utilized to generate diverse thermal management system architectures. The dynamics of these system architectures are modeled under various loading conditions, and an open-loop optimal controller is employed to determine each system’s optimal performance. These modeled cases constitute the dataset, with the corresponding optimal performance values serving as the labels for the data. In the subsequent step, a Graph Neural Network (GNN) model is trained on 30% of the labeled data to predict the systems’ performance, effectively addressing a regression problem. Utilizing this trained model, we estimate the performance values for the remaining 70% of the data, which serves as the test set. In the third step, the predicted performance values are employed to rank the test data, facilitating prioritized evaluation of the design scenarios. Specifically, a small subset of the test data with the highest estimated ranks undergoes evaluation via the open-loop optimal control modeler. This targeted approach concentrates on evaluating higher-ranked designs identified by the GNN, replacing the exhaustive search (enumeration-based) of all design cases. The results demonstrate a significant average reduction of over 92\% in the number of system dynamic modeling and optimal control analyses required to identify optimal design scenarios.
Download publicationAssociated Researchers
Saeid Bayat
University of Illinois at Urbana-Champaign
Nastaran Shahmansouri
Former Autodesk
Satya RT Peddada
University of Illinois at Urbana-Champaign
James T. Allison
University of Illinois at Urbana-Champaign
Related Resources
2023
Amortizing Pragmatic Program Synthesis with RankingsA novel method of amortizing the RSA algorithm by leveraging a global…
2023
Neural Shape Diameter Function for Efficient Mesh SegmentationIntroducing a neural approximation of the Shape Diameter Function,…
2022
Leveraging Robotics for Cleaner Construction JobsitesThe value in Spot’s ability to execute repeatable, autonomous missions…
2023
Using AI to Optimize Construction DesignHow can we leverage AI to make construction design processes more…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Contact us