Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Data-driven discovery of roughness descriptors for surface characterization and intimate contact modeling of unidirectional composite tapes

Sebastian Rodriguez, Mikhael Tannous, Jad Mounayer, Camilo Cruz, Anais Barasinski, Francisco Chinesta

Abstract

Unidirectional tapes surface roughness determines the evolution of the degree of intimate contact required for ensuring the thermoplastic molecular diffusion and the associated inter-tapes consolidation during manufacturing of composite structures. However, usual characterization of rough surfaces relies on statistical descriptors that even if they are able to represent the surface topology, they are not necessarily connected with the physics occurring at the interface during inter-tape consolidation. Thus, a key research question could be formulated as follows: Which roughness descriptors simultaneously enable tape classification-crucial for process control-and consolidation modeling via the inference of the evolution of the degree of intimate contact, itself governed by the process parameters?. For providing a valuable response, we propose a novel strategy based on the use of Rank Reduction Autoencoders (RRAEs), autoencoders with a linear latent vector space enforced by applying a truncated Singular Value Decomposition (SVD) to the latent matrix during the encoder-decoder training. In this work, we extract useful roughness descriptors by enforcing the latent SVD modes to (i) accurately represent the roughness after decoding, and (ii) allow the extraction of existing a priori knowledge such as classification or modelling properties.

Data-driven discovery of roughness descriptors for surface characterization and intimate contact modeling of unidirectional composite tapes

Abstract

Unidirectional tapes surface roughness determines the evolution of the degree of intimate contact required for ensuring the thermoplastic molecular diffusion and the associated inter-tapes consolidation during manufacturing of composite structures. However, usual characterization of rough surfaces relies on statistical descriptors that even if they are able to represent the surface topology, they are not necessarily connected with the physics occurring at the interface during inter-tape consolidation. Thus, a key research question could be formulated as follows: Which roughness descriptors simultaneously enable tape classification-crucial for process control-and consolidation modeling via the inference of the evolution of the degree of intimate contact, itself governed by the process parameters?. For providing a valuable response, we propose a novel strategy based on the use of Rank Reduction Autoencoders (RRAEs), autoencoders with a linear latent vector space enforced by applying a truncated Singular Value Decomposition (SVD) to the latent matrix during the encoder-decoder training. In this work, we extract useful roughness descriptors by enforcing the latent SVD modes to (i) accurately represent the roughness after decoding, and (ii) allow the extraction of existing a priori knowledge such as classification or modelling properties.
Paper Structure (15 sections, 9 equations, 26 figures)

This paper contains 15 sections, 9 equations, 26 figures.

Table of Contents

  1. Introduction
  2. Compaction simulation
  3. Database of roughness profiles
  4. Rough surface classification
  5. Data-reduction and Rank Reduction Autoencoder --RRAE
  6. Results
  7. Rough interfaces consolidation
  8. Data generation
  9. Modeling approach
  10. Results
  11. Decoupled Feature Learning: An Extended RRAE Architecture
  12. Comparison with Standard Learning Architectures
  13. Supervised Encoder--Decoder Network
  14. Classical Auto-Encoder with Linear Latent Compression
  15. Conclusions and Perspectives

Figures (26)

  • Figure 1: Illustration of macro- and micro-roughness measured on a unidirectional composite tape.
  • Figure 2: Cellular automaton discretization of the 2D composite tape rough surface before compaction. Black cells represents composite tape while white represents air.
  • Figure 3: Cellular automaton states of the 2D composite tape rough surface compaction: Intermediate step (left) and final (right) step.
  • Figure 4: Different roughness profiles extracted from 12 tapes associated with different providers, here refereed as classes
  • Figure 5: Classification accuracy obtained using Topological Data Analysis (TDA) based on persistence images.
  • ...and 21 more figures