Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Tailoring Frictional Properties of Surfaces Using Diffusion Models

Even Marius Nordhagen, Henrik Andersen Sveinsson, Anders Malthe-Sørenssen

TL;DR

This work tackles inverse design of surface friction by replacing trial-and-error with a conditional diffusion model. A DDPM is trained on a dataset of synthetic surfaces labeled with friction values from molecular dynamics simulations of carved α-quartz interfaces. The model directly generates surface designs that meet specified friction criteria, and validation via re-labeling confirms alignment with targets, achieving a mean-squared error of $0.50 μN^2$ and good class-accuracy. The approach reduces design iterations and has potential to generalize to other surface properties and material-science problems.

Abstract

This Letter introduces an approach for precisely designing surface friction properties using a conditional generative machine learning model, specifically a diffusion denoising probabilistic model (DDPM). We created a dataset of synthetic surfaces with frictional properties determined by molecular dynamics simulations, which trained the DDPM to predict surface structures from desired frictional outcomes. Unlike traditional trial-and-error and numerical optimization methods, our approach directly yields surface designs meeting specified frictional criteria with high accuracy and efficiency. This advancement in material surface engineering demonstrates the potential of machine learning in reducing the iterative nature of surface design processes. Our findings not only provide a new pathway for precise surface property tailoring but also suggest broader applications in material science where surface characteristics are critical.

Tailoring Frictional Properties of Surfaces Using Diffusion Models

TL;DR

This work tackles inverse design of surface friction by replacing trial-and-error with a conditional diffusion model. A DDPM is trained on a dataset of synthetic surfaces labeled with friction values from molecular dynamics simulations of carved α-quartz interfaces. The model directly generates surface designs that meet specified friction criteria, and validation via re-labeling confirms alignment with targets, achieving a mean-squared error of and good class-accuracy. The approach reduces design iterations and has potential to generalize to other surface properties and material-science problems.

Abstract

This Letter introduces an approach for precisely designing surface friction properties using a conditional generative machine learning model, specifically a diffusion denoising probabilistic model (DDPM). We created a dataset of synthetic surfaces with frictional properties determined by molecular dynamics simulations, which trained the DDPM to predict surface structures from desired frictional outcomes. Unlike traditional trial-and-error and numerical optimization methods, our approach directly yields surface designs meeting specified frictional criteria with high accuracy and efficiency. This advancement in material surface engineering demonstrates the potential of machine learning in reducing the iterative nature of surface design processes. Our findings not only provide a new pathway for precise surface property tailoring but also suggest broader applications in material science where surface characteristics are critical.
Paper Structure (6 sections, 5 equations, 5 figures, 1 table)

This paper contains 6 sections, 5 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methodology
  3. Results
  4. Conclusions and Perspectives
  5. Model Architecture
  6. Conditioning and Embedding

Figures (5)

  • Figure 1: Molecular dynamics simulation. (a) We keep the uppermost and lowermost layers of the system rigid, and apply a Langevin thermostat to the atoms close to the layers. Here, the upper system surface is partly transparent to show the structure. (b) The lateral force is measured while the system is sheared, and the static friction is taken as the largest lateral force. (c) Cross-sectional view of the system initially (1), just before failure (2) and after failure (3).
  • Figure 2: Training and validation of DDPM. (a) Binary structures are generated using simplex noise. (b) To label the structures by friction we carve out the structure in an $\alpha$-quartz crystal. The static friction is measured by shearing the system in molecular dynamics simulations. (c) Diffusion and denoising process. A DDPM is trained to gradually denoise an image. (d) Fake samples are generated by denoising noise using the DDPM. The quality of the generated images is evaluated by comparing to the real samples using the FID score. (e) Conditioning is validated by labeling fake samples generated for a given label and comparing the two labels. Illustrations of carved surfaces are rendered with Ovito stukowski2010.
  • Figure 3: Performance of model. (a) The expected static friction of fake samples as a function of the measured friction. (b) Average number of clusters (blue lines) and average cluster sizes, given in peecentage of the total surface area (green lines) across classes. (c) Average porosity across all classes. (d) Mean-squared error loss as a function of epochs, log y-axis.
  • Figure 4: Example samples. (a) Real samples generated with simplex noise across the 10 classes. (b) Fake samples generated by the DDPM across the 10 classes.
  • Figure 5: Architecture and conditioning of denoising model. (a) The denoising model takes a U-Net architecture, consisting of an input block (input), six standard downsampling blocks, one special downsampling block (spec-down), one special upsampling block (spec-up), six standard upsampling blocks and an output block (output). The information flow is shown by solid arrows: Information is passed linearly between the blocks, but skip-connections transport additional information directly to the standard upsampling blocks. (b) Each of the blocks consist of other blocks and layers. Both upsampling and downsampling blocks rely heavily on residual blocks (res), where the downsampling blocks also depend on deconvolutions. (c) Each residual block consists two stacked blocks of a convolutional layer and $3\times3$ kernel, batch normalization and GELU activation. (d) Embedding networks are used to input conditions and time step into upsampling blocks. (e) Embedding networks consist of a linear layer, GELU activation and then another linear layer.