Data fusion methods for materials awareness

Recent advances in the development of artificial intelligence and machine learning (AI/ML) techniques have shown great potential for enhancing the modeling and characterization of materials science issues. AI/ML techniques revolutionize big data analytics through signals and imaging detection, segmentation, and characterization; data fusion processes of association, estimation, and prediction, and modeling of deformation, structural, and materials awareness. Unfortunately, the dominance of AI/ML applications may hinder fundamental understanding of driving parameters in complicated material properties, including the impact of local chemistry and energy influences on nucleation, phase evolution, and bonding. As mathematical complexities are modeled using AI/ML approaches the interaction of driving mechanisms and underlying physics-based and first-principles understanding is often omitted in the final modeling of material behavior. However, microscopy and advanced characterization techniques may help clarify the underlying physics by providing critical validation for mathematical assumptions used in AI/ML models and determining model inter-parameter relationships. Sensing-based characterization is critical for operations using deep learning and/or clustered neural networks where complex interactions between microstructural features strongly impact each other, and driving mechanisms that control material response. The paper addresses several considerations for applying machine learning techniques to fundamental material problems, and the role for parameter validation through characterization. The future of AI/ML materials awareness includes procedural potential applications, advanced analytical tools, and coordinated research discovery thrusts.

[1]  A. Choudhary,et al.  Deep materials informatics: Applications of deep learning in materials science , 2019, MRS Communications.

[2]  John C. Aldrin,et al.  A supervised learning approach for prediction of x-ray computed tomography data from ultrasonic testing data , 2019 .

[3]  Mehdi Salkhordeh Haghighi,et al.  Improving nondestructive characterization of dual phase steels using data fusion , 2018, Journal of Magnetism and Magnetic Materials.

[4]  E. L. Waltz.  Information understanding: integrating data fusion and data mining processes , 1998, ISCAS '98. Proceedings of the 1998 IEEE International Symposium on Circuits and Systems (Cat. No.98CH36187).

[5]  Jin,et al.  Information Fusion for Multi-Source Material Data: Progress and Challenges , 2019, Applied Sciences.

[6]  Ye Lu,et al.  Conjunctive and compromised data fusion schemes for identification of multiple notches in an aluminium plate using lamb wave signals , 2010, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[7]  Pierre Valin,et al.  Information fusion measures of effectiveness (MOE) for decision support , 2011, Defense + Commercial Sensing.

[8]  Sudipto Mandal,et al.  Generation of statistically representative synthetic three-dimensional microstructures , 2018 .

[9]  Jaimie Tiley,et al.  Strengthening mechanisms in an inertia friction welded nickel-base superalloy , 2016 .

[10]  Dierk Raabe,et al.  Identifying Structure–Property Relationships Through DREAM.3D Representative Volume Elements and DAMASK Crystal Plasticity Simulations: An Integrated Computational Materials Engineering Approach , 2017, JOM.

[11]  Ashley D. Spear,et al.  Predicting microstructure-dependent mechanical properties in additively manufactured metals with machine- and deep-learning methods , 2020, Computational Materials Science.

[12]  Parisa Shokouhi,et al.  Application of data fusion in nondestructive testing (NDT) , 2013, Proceedings of the 16th International Conference on Information Fusion.

[13]  Erik Blasch,et al.  Context-Enhanced Information Fusion: Boosting Real-World Performance with Domain Knowledge , 2016 .

[14]  Yan Zhang,et al.  SLADS-Net: Supervised Learning Approach for Dynamic Sampling using Deep Neural Networks , 2018, Computational Imaging.

[15]  Erik Blasch,et al.  DDDAS ADVANTAGES FROM HIGH-DIMENSIONAL SIMULATION , 2018, 2018 Winter Simulation Conference (WSC).

[16]  John C. Aldrin,et al.  Model-Assisted Probability of Detection Evaluation for Eddy Current Inspection of Fastener Sites , 2009 .

[17]  Rick S. Blum,et al.  Fusing synergistic information from multi-sensor images: An overview from implementation to performance assessment , 2018, Inf. Fusion.

[18]  Zheng Liu,et al.  Statistical comparison of image fusion algorithms: Recommendations , 2017, Inf. Fusion.

[19]  Jaimie Tiley,et al.  Modeling the tensile properties in β-processed α/β Ti alloys , 2006 .

[20]  A Preview of the U.S. Air Force Research Laboratory Additive Manufacturing Modeling Challenge Series , 2018 .

[21]  Joshua Shaffer,et al.  The Effect of Lath Orientations on Oxygen Ingress in Titanium Alloys , 2014, Metallurgical and Materials Transactions A.

[22]  Alexander C. S. Douglass,et al.  Segmentation of Hidden Delaminations with Pitch–Catch Ultrasonic Testing and Agglomerative Clustering , 2020, Journal of Nondestructive Evaluation.

[23]  Spandan Mishra.  Structural health monitoring with lamb-wave sensors: Problems in damage monitoring, prognostics and multisensory decision fusion , 2016 .

[24]  David Cebon,et al.  Materials Selection in Mechanical Design , 1992 .

[25]  H. R. Millwater,et al.  Probabilistic sensitivity analysis of dwell-fatigue crack initiation life for a two-grain microstructural model , 2013 .

[26]  Krishna Rajan,et al.  Information Science for Materials Discovery and Design , 2016 .

[27]  Bianca Maria Colosimo,et al.  Data fusion methods for statistical process monitoring and quality characterization in metal additive manufacturing , 2018 .

[28]  Ernst Niederleithinger,et al.  Image Fusion for Improved Detection of Near-Surface Defects in NDT-CE Using Unsupervised Clustering Methods , 2014 .

[29]  D. Dimiduk,et al.  Perspectives on the Impact of Machine Learning, Deep Learning, and Artificial Intelligence on Materials, Processes, and Structures Engineering , 2018, Integrating Materials and Manufacturing Innovation.

[30]  Chiho Kim,et al.  Machine learning in materials informatics: recent applications and prospects , 2017, npj Computational Materials.

[31]  M. Degraef,et al.  Managing the Mosaic of Microstructure , 2019 .

[32]  Xinyi Gong,et al.  Process-Structure Linkages Using a Data Science Approach: Application to Simulated Additive Manufacturing Data , 2017, Integrating Materials and Manufacturing Innovation.

[33]  Ashok Kumar,et al.  A Markov random field approach for microstructure synthesis , 2016 .

[34]  Joel B. Harley,et al.  Machine learning and NDE: Past, present, and future , 2019 .

[35]  Chiwoo Park,et al.  Sequential adaptive design for jump regression estimation , 2019, IISE Transactions.

[36]  Peter C. Collins,et al.  Neural Networks Relating Alloy Composition, Microstructure, and Tensile Properties of α/β-Processed TIMETAL 6-4 , 2013, Metallurgical and Materials Transactions A.

[37]  Edwin J. Schwalbach,et al.  A discrete source model of powder bed fusion additive manufacturing thermal history , 2019, Additive Manufacturing.

[38]  Alok Choudhary,et al.  Extracting Grain Orientations from EBSD Patterns of Polycrystalline Materials Using Convolutional Neural Networks , 2018, Microscopy and Microanalysis.

[39]  Erik Blasch,et al.  Situation, impact, and user refinement , 2003, SPIE Defense + Commercial Sensing.

[40]  Erik Blasch,et al.  Dynamic Data Driven Applications Systems (DDDAS) for Structural Awareness , 2019 .

[41]  Erik Blasch,et al.  Covert photo classification by deep convolutional neural networks , 2017, Machine Vision and Applications.

[42]  Daniel W. Davies,et al.  Machine learning for molecular and materials science , 2018, Nature.

[43]  Ming Yang,et al.  Data fusion of distributed AE sensors for the detection of friction sources during press forming , 2003 .

[44]  Jian Wang,et al.  Review of the mathematical foundations of data fusion techniques in surface metrology , 2015 .

[45]  Edward R. Dougherty,et al.  Optimal experimental design for materials discovery , 2017 .

[46]  David L. McDowell,et al.  Multiscale Computational Strategies for Heterogeneous Materials with Defects: Coupling Modeling with Experiments and Uncertainty Quantification , 2019, JOM.

[47]  Gianluigi Ferrari,et al.  Multisensor Data Fusion : From Algorithm and Architecture Design to Applications , 2014 .

[48]  J. Aldrin,et al.  The need and approach for characterization - U.S. air force perspectives on materials state awareness , 2018 .

[49]  David L. McDowell,et al.  Vision for Data and Informatics in the Future Materials Innovation Ecosystem , 2016, JOM.

[50]  R. Ramprasad,et al.  Machine Learning in Materials Science , 2016 .

[51]  Zheng Liu,et al.  Enhanced situation awareness through CNN-based deep multimodal image fusion , 2020, Optical Engineering.

[52]  Genshe Chen,et al.  Image quality assessment for performance evaluation of image fusion , 2008, 2008 11th International Conference on Information Fusion.

[53]  V. M. Karbhari.  Introduction: the future of non-destructive evaluation (NDE) and structural health monitoring (SHM) , 2013 .

[54]  Zheng Liu,et al.  Multispectral Image Fusion and Colorization , 2018 .

[55]  Zheng Liu,et al.  Survey: State of the Art in NDE Data Fusion Techniques , 2007, IEEE Transactions on Instrumentation and Measurement.

[56]  Xavier Gros Dut BSc.  NDT Data Fusion , 1996 .

[57]  Erik Blasch,et al.  Combining Convolutional and Recurrent Neural Networks for Human Skin Detection , 2017, IEEE Signal Processing Letters.

[58]  M. Groeber,et al.  DREAM.3D: A Digital Representation Environment for the Analysis of Microstructure in 3D , 2014, Integrating Materials and Manufacturing Innovation.

[59]  Andrzej Katunin,et al.  Evaluation of Impact Damages in Composites Based on Fusion of Ultrasonic and Optical Images with Optimized Parameters , 2014 .

[60]  Yufeng Zheng,et al.  Qualitative and quantitative comparisons of multispectral night vision colorization techniques , 2012, Optical Engineering.

[61]  Michael D. Sangid,et al.  Coupling in situ experiments and modeling – Opportunities for data fusion, machine learning, and discovery of emergent behavior , 2020 .

[62]  Alán Aspuru-Guzik,et al.  What Is High-Throughput Virtual Screening? A Perspective from Organic Materials Discovery , 2015 .

[63]  M. Groeber,et al.  3D reconstruction of prior β grains in friction stir–processed Ti–6Al–4V , 2014, Journal of microscopy.