NLPAR: Non-local smoothing for enhanced EBSD pattern indexing

A Denoising Autoencoder for Improved Kikuchi Pattern Quality and Indexing in Electron Backscatter Diffraction

The rapid collection and indexing of electron diffraction patterns as produced via electron backscatter diffraction (EBSD) has enabled crystallographic orientation and structural determination, as well as additional property-determining strain and dislocation density information with increasing speed, resolution, and efficiency. Pattern indexing quality is reliant on the noise of the collected electron diffraction patterns, which is often convoluted by sample preparation and data collection parameters. EBSD acquisition is sensitive to many factors and thus can result in low confidence index (CI), poor image quality (IQ), and improper minimization of fit, which can result in noisy datasets and misrepresent the microstructure. In an attempt to enable both higher speed EBSD data collection and enable greater orientation fit accuracy with noisy datasets, an image denoising autoencoder was implemented to improve pattern quality. We show that EBSD data processed through the autoencoder results in a higher CI, IQ, and a more accurate degree of fit. In addition, using denoised datasets in HR-EBSD cross correlative strain analysis can result in reduced phantom strain from erroneous calculations due to the increased indexing accuracy and improved correspondence between collected and simulated patterns.

Machine learning based de-noising of electron back scatter patterns of various crystallographic metallic materials fabricated using laser directed energy deposition

A novel machine learning (ML) method of refining noisy Electron Back Scatter Patterns (EBSP) is proposed. For this, conditional generative adversarial networks (c-GAN) have been employed. The problem of de-noising the EBSPs was formulated as an image translation task conditioned on the input images to get refined/denoised output of EBSPs which can be indexed using conventional Hough transform based indexing algorithms. The ML model was trained using 10,000 EBSPs acquired under different settings for additively manufactured FCC, BCC and HCP alloy samples ensuring enough diversity and complexity in training data set. Pairs of noisy and corresponding optimal EBSPs were acquired by suitable tweaking of the EBSP acquisition parameters such as beam defocus, pattern binning and EBSD camera exposure duration. The trained model has brought out significant improvement in EBSD indexing success rate on test data, accompanied by betterment of indexing accuracy, quantified through 'pattern fit'. Complete automation of the EBSP refinement was demonstrated where in entire EBSD scan data can be fed to the model to get the refined EBSPs from which high quality EBSD data can be obtained.

Local Kikuchi band detection in electron backscatter diffraction patterns for enhanced pattern indexing

Partially missing bands in the preset region for Hough transform might strongly affect the accuracy of indexing Kikuchi patterns and reduce the quality of electron backscatter diffraction (EBSD) maps. This paper proposes a novel local band detection method for such kind of low-quality patterns. The approach involves rotating bands to vertical direction, detecting the local line segments through calculating the largest horizontal average grey gradient with a constant interval of 400 pixels in vertical direction, and applying Hough transform as well as weighted averaging to these line clusters to unify the edges of Kikuchi band. Therefore, even if only part of a Kikuchi band is visible, the entire band can also be accurately extracted. The average interplanar angle error obtained by the proposed method is approximately 29.0% less than those obtained by Hough transform-based technique. Moreover, the comparison of mean angular deviation (MAD) is also discussed. The average MAD of this method is about 38.5% lower than that of Hough transform-based technique. Consequently, the local Kikuchi band detection method is expected to be used for post-processing and re-indexing the EBSD low-quality patterns.

Electron backscattered diffraction using a new monolithic direct detector: High resolution and fast acquisition

A monolithic active pixel sensor based direct detector that is optimized for the primary beam energies in scanning electron microscopes is implemented for electron back-scattered diffraction (EBSD) applications. The high detection efficiency of the detector and its large array of pixels allow sensitive and accurate detection of Kikuchi bands arising from primary electron beam excitation energies of 4 keV to 28 keV, with the optimal contrast occurring in the range of 8-16 keV. The diffraction pattern acquisition speed is substantially improved via a sparse sampling mode, resulting from the acquisition of a reduced number of pixels on the detector. Standard inpainting algorithms are implemented to effectively estimate the information in the skipped regions in the acquired diffraction pattern. For EBSD mapping, an acquisition speed as high as 5988 scan points per second is demonstrated, with a tolerable fraction of indexed points and accuracy. The collective capabilities spanning from high angular resolution EBSD patterns to high speed pattern acquisition are achieved on the same detector, facilitating simultaneous detection modalities that enable a multitude of advanced EBSD applications, including lattice strain mapping, structural refinement, low-dose characterization, 3D-EBSD and dynamic in situ EBSD.

Spherical-angular dark field imaging and sensitive microstructural phase clustering with unsupervised machine learning

Electron backscatter diffraction is a widely used technique for nano- to micro-scale analysis of crystal structure and orientation. Backscatter patterns produced by an alloy solid solution matrix and its ordered superlattice exhibit only extremely subtle differences, due to the inelastic scattering that precedes coherent diffraction. We show that unsupervised machine learning (with principal component analysis, non-negative matrix factorisation, and an autoencoder neural network) is well suited to fine feature extraction and superlattice/matrix classification. Remapping cluster average patterns onto the diffraction sphere lets us compare Kikuchi band profiles to dynamical simulations, confirm the superlattice stoichiometry, and facilitate virtual imaging with a spherical solid angle aperture. This pipeline now enables unparalleled mapping of exquisite crystallographic detail from a wide range of materials within the scanning electron microscope.

Advancing characterisation with statistics from correlative electron diffraction and X-ray spectroscopy, in the scanning electron microscope

The routine and unique determination of minor phases in microstructures is critical to materials science. In metallurgy alone, applications include alloy and process development and the understanding of degradation in service. We develop a correlative method, exploring superalloy microstructures, which are examined in the scanning electron microscope (SEM) using simultaneous energy dispersive X-ray spectroscopy (EDS) and electron backscatter diffraction (EBSD). This is performed at an appropriate length scale for characterisation of carbide phases' shape, size, location, and distribution. EDS and EBSD data are generated using two different physical processes, but each provide a signature of the material interacting with the incoming electron beam. Recent advances in post-processing, driven by 'big data' approaches, include use of principal component analysis (PCA). Components are subsequently characterised to assign labels to a mapped region. To provide physically meaningful signals, the principal components may be rotated to control the distribution of variance. In this work, we develop this method further through a weighted PCA approach. We use the EDS and EBSD signals concurrently, thereby labelling each region using both EDS (chemistry) and EBSD (crystal structure) information. This provides a new method of amplifying signal-to-noise for very small phases in mapped regions, especially where the EDS or EBSD signal is not unique enough alone for classification.