Computer Vision Approaches for Segmentation of Nanoscale Precipitates in Nickel-Based Superalloy IN718

Extracting accurate volume fraction and size measurements of γ″ and γ′ precipitates in iron-based superalloys from micrographs is challenging and conventionally involves manual image processing due to their smaller size, and similar crystal structures and chemistries. The co-precipitation of composite particles further complicates automated segmentation. In this work, different types of traditional machine learning approaches and a convolutional neural network (CNN) were compared to a non-machine learning approach, for the segmentation of the composite particles of γ″ and γ′ precipitates. The objective was to optimize metrics of segmentation accuracy and the required computational resources. The data set contains 47 experimentally generated scanning electron micrographs of IN718 alloy samples, computationally increased to 188 images (900 × 900 px). All algorithms are containerized using singularity, publicly available, and can be modified without dependencies. The CNN and the random forest models achieve 95% and 94% accuracy, respectively, on the test images with better computational efficiency than the non-machine learning algorithm. The CNN tested accurately over a range of imaging conditions.

[1]  Guang Yang,et al.  Automatic Brain Tumor Detection and Segmentation Using U-Net Based Fully Convolutional Networks , 2017, MIUA.

[2]  Scott Krig,et al.  Computer Vision Metrics , 2014, Apress.

[3]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[4]  Jennifer L. W. Carter,et al.  High-Throughput Approaches to Establish Quantitative Process–Structure–Property Correlations in Ni-Base Superalloy , 2020 .

[5]  V. Rodriguez-Galiano,et al.  Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines , 2015 .

[6]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[7]  Jennifer L. W. Carter,et al.  Harnessing Legacy Data to Educate Data-Enabled Structural Materials Engineers , 2020 .

[8]  A. Czyrska-Filemonowicz,et al.  Imaging and characterization of γ' and γ"nanoparticles in Inconel 718 by EDX elemental mapping and FIB-SEM tomography , 2015 .

[9]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[10]  Scott Krig,et al.  Computer Vision Metrics: Survey, Taxonomy, and Analysis , 2014 .

[11]  Jaron J. R. Chong,et al.  Canadian Association of Radiologists White Paper on Artificial Intelligence in Radiology , 2018, Canadian Association of Radiologists journal = Journal l'Association canadienne des radiologistes.

[12]  J. Du,et al.  THE EFFECT OF NB, TI, AL ON PRECIPITATION AND STRENGTHENING BEHAVIOR OF 718 TYPE SUPERALLOYS , 2005 .

[13]  Thorsteinn S. Rögnvaldsson A Simple Trick for Estimating the Weight Decay Parameter , 1996, Neural Networks: Tricks of the Trade.

[14]  Gary R. Bradski,et al.  ORB: An efficient alternative to SIFT or SURF , 2011, 2011 International Conference on Computer Vision.

[15]  Leslie N. Smith,et al.  A disciplined approach to neural network hyper-parameters: Part 1 - learning rate, batch size, momentum, and weight decay , 2018, ArXiv.

[16]  Mert R. Sabuncu,et al.  Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels , 2018, NeurIPS.

[17]  Abien Fred Agarap Deep Learning using Rectified Linear Units (ReLU) , 2018, ArXiv.

[18]  D. Blavette,et al.  The role of the atom probe in the study of nickel-based superalloys , 2000 .

[19]  Wei Li,et al.  Data Augmentation for Hyperspectral Image Classification With Deep CNN , 2019, IEEE Geoscience and Remote Sensing Letters.

[20]  Kellie J. Archer,et al.  Empirical characterization of random forest variable importance measures , 2008, Comput. Stat. Data Anal..

[21]  LoyGareth,et al.  Fast Radial Symmetry for Detecting Points of Interest , 2003 .

[22]  Alexander Zelinsky,et al.  Fast Radial Symmetry for Detecting Points of Interest , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Jennifer L. W. Carter,et al.  Characterization of nanoscale precipitates in superalloy 718 using high resolution SEM imaging , 2019, Materials Characterization.

[24]  M. Mills,et al.  Nano γ′/γ″ composite precipitates in Alloy 718 , 2012 .

[25]  M. Mills,et al.  Imaging and characterization of fine γ' precipitates in a commercial nickel-base superalloy , 2005 .

[26]  Michael J. Kulis,et al.  A quantifiable and automated volume fraction characterization technique for secondary and tertiary γ′ precipitates in Ni-based superalloys , 2018, Materials Characterization.

[27]  Diogo Almeida,et al.  Resnet in Resnet: Generalizing Residual Architectures , 2016, ArXiv.

[28]  David Paper,et al.  Scikit-Learn Classifier Tuning from Simple Training Sets , 2019, Hands-on Scikit-Learn for Machine Learning Applications.

[29]  Pinaki Pratim Acharjya,et al.  Study and Comparison of Different Edge Detectors for Image Segmentation , 2012 .

[30]  Joel H. Saltz,et al.  Comparison of Different Classifiers with Active Learning to Support Quality Control in Nucleus Segmentation in Pathology Images , 2018, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[31]  Jeremy Howard,et al.  fastai: A Layered API for Deep Learning , 2020, Inf..

[32]  J. W. Brooks,et al.  Metallurgical Stability of Inconel Alloy 718 , 1988 .

[33]  Joni-Kristian Kämäräinen Gabor features in image analysis , 2012, IPTA.

[34]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[35]  Vanessa Sochat,et al.  Singularity: Scientific containers for mobility of compute , 2017, PloS one.

[36]  Steffen Bickel,et al.  Discriminative learning for differing training and test distributions , 2007, ICML '07.

[37]  Mario Cifrek,et al.  A brief introduction to OpenCV , 2012, 2012 Proceedings of the 35th International Convention MIPRO.

[38]  Abdel-Aziz Binguitcha-Fare,et al.  Crops and weeds classification using Convolutional Neural Networks via optimization of transfer learning parameters , 2019 .

[39]  R. Choras Image Feature Extraction Techniques and Their Applications for CBIR and Biometrics Systems , 2008 .

[40]  G. Frommeyer,et al.  Microstructure and mechanical properties of nickel based superalloy IN718 produced by rapid prototyping with electron beam melting (EBM) , 2011 .

[41]  Robert P. Sheridan,et al.  Deep Neural Nets as a Method for Quantitative Structure-Activity Relationships , 2015, J. Chem. Inf. Model..

[42]  P. Midgley,et al.  TEM, HRTEM, electron holography and electron tomography studies of γ′ and γ″ nanoparticles in Inconel 718 superalloy , 2009, Journal of microscopy.

[43]  Kunle Olukotun,et al.  DeepFreak: Learning Crystallography Diffraction Patterns with Automated Machine Learning , 2019, ArXiv.

[44]  Mehryar Mohri,et al.  L2 Regularization for Learning Kernels , 2009, UAI.

[45]  S. Semiatin,et al.  An Investigation of High-Temperature Precipitation in Powder-Metallurgy, Gamma/Gamma-Prime Nickel-Base Superalloys , 2015, Metallurgical and Materials Transactions A.

[46]  D. S. Duvall,et al.  Coherency strengthening in Ni base alloys hardened by DO22 γ′ precipitates , 1974, Metallurgical and Materials Transactions B.

[47]  David Paper,et al.  Hands-on Scikit-Learn for Machine Learning Applications: Data Science Fundamentals with Python , 2019 .

[48]  Chao Yang,et al.  A Survey on Deep Transfer Learning , 2018, ICANN.

[49]  L. Murr,et al.  Microstructures and mechanical behavior of Inconel 718 fabricated by selective laser melting , 2012 .

[50]  Heikki Haario,et al.  Segmentation of Overlapping Elliptical Objects in Silhouette Images , 2015, IEEE Transactions on Image Processing.

[51]  A. Pineau,et al.  Morphology of y’ and y” precipitates and thermal stability of inconel 718 type alloys , 1973 .

[52]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[53]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[54]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[55]  Farzin Deravi,et al.  Candidate pruning for fast corner detection , 2004 .