Predicting mechanical properties of Carbon Nanotube (CNT) images Using Multi-Layer Synthetic Finite Element Model Simulations
This work addresses the problem of accelerating materials discovery for carbon nanotube forests, but it is incremental as it builds upon a previous neural network with a new data augmentation method.
The paper tackles predicting mechanical properties of carbon nanotube forest images by using a deep learning model with a novel data augmentation technique that blends 2D synthetic images to create multi-layer synthetic images, which reduces computational costs compared to 3D simulations or experiments. The result is a pipeline that is expected to outperform single synthetic image-based learning in predicting properties from real scanning electron microscopy images.
We present a pipeline for predicting mechanical properties of vertically-oriented carbon nanotube (CNT) forest images using a deep learning model for artificial intelligence (AI)-based materials discovery. Our approach incorporates an innovative data augmentation technique that involves the use of multi-layer synthetic (MLS) or quasi-2.5D images which are generated by blending 2D synthetic images. The MLS images more closely resemble 3D synthetic and real scanning electron microscopy (SEM) images of CNTs but without the computational cost of performing expensive 3D simulations or experiments. Mechanical properties such as stiffness and buckling load for the MLS images are estimated using a physics-based model. The proposed deep learning architecture, CNTNeXt, builds upon our previous CNTNet neural network, using a ResNeXt feature representation followed by random forest regression estimator. Our machine learning approach for predicting CNT physical properties by utilizing a blended set of synthetic images is expected to outperform single synthetic image-based learning when it comes to predicting mechanical properties of real scanning electron microscopy images. This has the potential to accelerate understanding and control of CNT forest self-assembly for diverse applications.