Novel techniques for characterising graphene nanoplatelets using Raman spectroscopy and machine learning

Abstract

A significant challenge for graphene nanoplatelet (GNP) suppliers is the characterisation of platelet morphology in industrial environments. This challenge is further exacerbated to platelet surface chemistry when scalable functionalisation processes, such as plasma treatment, are used to modify the GNPs to improve the filler-matrix interphase in nanocomposites. The costly and complex suite of analytical equipment necessary for a complete material description makes quality control and process optimisation difficult. Raman spectroscopy is a facile and accessible characterisation technique, with recent advancements unlocking fast mapping for rapid data collection. In this study, we develop novel techniques to better characterise GNP morphology and changes in surface chemistry using Raman maps of bulk powders. Providing a bespoke algorithmic framework for the analysis of these advanced materials. An unsupervised peak fitting and processing algorithm was used to extract crystallinity data and correlate it with laser-diffraction-derived lateral size values for a commercial set of GNPs rapidly and accurately. Classical machine learning was used to identify the most informative Raman features for classifying the plasma-functionalised GNPs. The initial material properties were found to affect the peak features that were the most useful for classification. In low defect density and low specific surface area GNPs, the D peak FWHM is found to be the most useful, whereas the I2D/IG ratio is the most useful in the opposite case. Finally, a convolutional neural network was trained to discern between different GNP grades with 86% accuracy. This work demonstrates how computer vision could be deployed for rapid and accurate quality control on the factory floor.

Navigating the frontiers of graphene quality control to enable product optimisation and market confidence

“…ISO/TS 21356-1:2021 describes the techniques and detailed methodologies for the characterisation of structural properties of graphitic particles. The current state of the art metrology in measurement of these structural properties includes a combination of microscopy and spectroscopy techniques such as Raman spectroscopy [5][6][7], scanning electron microscopy (SEM), atomic force microscopy (AFM), and transmission electron microscopy (TEM). Raman spectroscopy is generally used to assess the structural configuration and integrity of the carbon lattice, as well as chemistry [7,8].…”

Advancing the Industrial Circular Economy: The Integrative Role of Machine Learning in Resource Optimization

“…This approach revitalizes older equipment, reintegrating it into the production system and considerably reducing the opportunity costs of retaining such equipment in terms of both finances and resources. Additionally, Mercadillo et al [78] employed classic ML for product feature identification, showcasing how computer vision can be applied for rapid and accurate quality control on the factory floor. A critical future consideration is how manufacturers can effectively discern and cater to consumer preferences.…”

Automated statistical analysis of raman spectra of nanomaterials

“…58 Deep-learning techniques have been reported for automatic denoise of Raman spectra of graphene, 59 fit specific Raman bands and isolate the most informative Raman features to extract crystallinity or functionalization. 60 Similarly, the thickness of TMDCs and inhomogeneity can be automatically classified using neural networks 61 and k -means clustering analysis, 62 respectively. These tools have been developed to meet specific user requirements, mostly related to the automatic assessment of material quality for industrial applications.…”