1 February 2019 in Microscopy and Microanalysis
We apply a deep convolutional neural network segmentation model to enable novel automated microstructure segmentation applications for complex microstructures typically evaluated manually and subjectively. We explore two microstructure segmentation tasks in an openly available ultrahigh carbon steel microstructure dataset: segmenting cementite particles in the spheroidized matrix, and segmenting larger fields of view featuring grain boundary carbide, spheroidized particle matrix, particle-free grain boundary denuded zone, and Widmanstätten cementite. We also demonstrate how to combine these data-driven microstructure segmentation models to obtain empirical cementite particle size and denuded zone width distributions from more complex micrographs containing multiple microconstituents. The full annotated dataset is available on materialsdata.nist.gov.
1 November 2021 in Nature Communications
Automated, reliable, and objective microstructure inference from micrographs is essential for a comprehensive understanding of process-microstructure-property relations and tailored materials development. However, such inference, with the increasing complexity of microstructures, requires advanced segmentation methodologies. While deep learning offers new opportunities, an intuition about the required data quality/quantity and a methodological guideline for microstructure quantification is still missing. This, along with deep learning’s seemingly intransparent decision-making process, hampers its breakthrough in this field. We apply a multidisciplinary deep learning approach, devoting equal attention to specimen preparation and imaging, and train distinct U-Net architectures with 30–50 micrographs of different imaging modalities and electron backscatter diffraction-informed annotations. On the challenging task of lath-bainite segmentation in complex-phase steel, we achieve accuracies of 90% rivaling expert segmentations. Further, we discuss the impact of image context, pre-training with domain-extrinsic data, and data augmentation. Network visualization techniques demonstrate plausible model decisions based on grain boundary morphology.
12 April 2021 in Research Square
Automated, reliable, and objective microstructure inference from micrographs is an essential milestone towards a comprehensive understanding of process-microstructure-property relations and tailored materials development. However, such inference, with the increasing complexity of microstructures, requires advanced segmentation methodologies. While deep learning (DL), in principle, offers new opportunities for this task, an intuition about the required data quality and quantity and an extensive methodological DL guideline for microstructure quantification and classification are still missing. This, along with a lack of open-access data sets and the seemingly intransparent decision-making process of DL models, hampers its breakthrough in this field. We address all aforementioned obstacles by a multidisciplinary DL approach, devoting equal attention to specimen preparation, contrasting, and imaging. To this end, we train distinct U-Net architectures with 30–50 micrographs of different imaging modalities and corresponding EBSD-informed annotations. On the challenging task of lath-bainite segmentation in complex-phase steel, we achieve accuracies of 90% rivaling expert segmentations. Further, we discuss the impact of image context, pre-training with domain-extrinsic data, and data augmentation. Network visualization techniques demonstrate plausible model decisions based on grain boundary morphology and triple points. As a result, we resolve preconceptions about required data amounts and interpretability to pave the way for DL's day-to-day application for microstructure quantification.
29 November 2016 in Chinese Physics B
An acoustic vector sensor can measure the components of particle velocity and the acoustic pressure at the same point simultaneously, which provides a larger array gain against the ambient noise and a higher angular resolution than the omnidirectional pressure sensor. This paper presents an experimental study of array gain for a conformal acoustic vector sensor array in a practical environment. First, the manifold vector is calculated using the real measured data so that the effects of array mismatches can be minimized. Second, an optimal beamformer with a specific spatial response on the basis of the stable directivity of the ambient noise is designed, which can effectively suppress the ambient noise. Experimental results show that this beamformer for the conformal acoustic vector sensor array provides good signal-to-noise ratio enhancement and is more advantageous than the delay-and-sum and minimum variance distortionless response beamformers.