Automated particle recognition for engine soot nanoparticles

Haffner-Staton, E.; Avanzini, L.; La Rocca, A.; Pfau, S. A.; Cairns, A.

Abstract

A pre-trained convolution neural network based on residual error functions (ResNet) was applied to the classification of soot and non-soot carbon nanoparticles in TEM images. Two depths of ResNet, one 18 layers deep and the other 50 layers deep, were trained using training-validation sets of increasing size (containing 100, 400 and 1400 images) and were assessed using an independent test set of 200 images. Network training was optimised in terms of mini-batch size, learning rate and training length. In all tests, ResNet18 and ResNet50 had statistically similar performances, though ResNet18 required only 25–35% of the training time of ResNet50. Training using the 100-, 400- and 1400-image training-validation sets led to classification accuracies of 84%, 88% and 95%, respectively. ResNet18 and ResNet50 were also compared for their ability to categorise soot and non-soot nanoparticles via a fivefold cross-validation experiment using the entire set of 800 images of soot and 800 images of non-soot. Cross-validation was repeated 3 times with different training durations. For all cross-validation experiments, classification accuracy exceeded 91%, with no statistical differences between any of the network trainings. The most efficient network was ResNet18 trained for 5 epochs, which reached 91.2% classification after only 84 s of training on 1600 images. Use of ResNet for classification of 1000 images, the amount suggested for reliable characterisation of soot sample, requires <4 s, compared with >30 min for a skilled operator classifying images manually. Use of convolution neural networks for classification of soot and non-soot nanoparticles in TEM images is highly promising, particularly when manually classified data sets have already been established.

Citation

Haffner-Staton, E., Avanzini, L., La Rocca, A., Pfau, S. A., & Cairns, A. (2022). Automated particle recognition for engine soot nanoparticles. Journal of Microscopy, 288(1), 28-39. https://doi.org/10.1111/jmi.13140

• Journal Article Type: Article
• Acceptance Date: Aug 31, 2022
• Online Publication Date: Sep 16, 2022
• Publication Date: Oct 1, 2022
• Deposit Date: Feb 20, 2025
• Publicly Available Date: Feb 20, 2025
• Journal: Journal of Microscopy
• Print ISSN: 0022-2720
• Electronic ISSN: 1365-2818
• Publisher: Wiley
• Peer Reviewed: Peer Reviewed
• Volume: 288
• Issue: 1
• Pages: 28-39
• DOI: https://doi.org/10.1111/jmi.13140
• Keywords: automotive, nanoparticles, neural networks, soot, TEM, vision learning
• Public URL: https://nottingham-repository.worktribe.com/output/11200852
• Publisher URL: https://onlinelibrary.wiley.com/doi/10.1111/jmi.13140