ActivationNet: Representation learning to predict contact quality of interacting 3-D surfaces in engineering designs

TL;DR

ActivationNet is a novel machine learning method that predicts contact quality between interacting 3-D surfaces in engineering designs using point cloud representations and deep neural networks.

Contribution

It introduces ActivationNet, a new approach that learns from point clouds or meshes to accurately predict contact quality in complex geometries.

Findings

High accuracy in contact quality prediction across multiple experiments.

Effective handling of point cloud and mesh data for contact analysis.

Agreement of predictions with expected contact behaviors.

Abstract

Engineering simulations for analysis of structural and fluid systems require information of contacts between various 3-D surfaces of the geometry to accurately model the physics between them. In machine learning applications, 3-D surfaces are most suitably represented with point clouds or meshes and learning representations of interacting geometries form point-based representations is challenging. The objective of this work is to introduce a machine learning algorithm, ActivationNet, that can learn from point clouds or meshes of interacting 3-D surfaces and predict the quality of contact between these surfaces. The ActivationNet generates activation states from point-based representation of surfaces using a multi-dimensional binning approach. The activation states are further used to contact quality between surfaces using deep neural networks. The performance of our model is demonstrated using several experiments, including tests on interacting surfaces extracted from engineering geometries. In all the experiments presented in this paper, the contact quality predictions of ActivationNet agree well with the expectations.