Recent Studies on Void Shrinkage in Metallic Materials Subjected to In Situ Heavy Ion Irradiations

Niu, Tongjun; Nasim, M.; Annadanam, Rayaprolu Goutham Sreekar; Fan, Cuncai; Li, Jin; Shang, Zhongxia; Xue, Yexiang; El–Azab, Anter; Wang, H.; Zhang, Xinghang

doi:10.1007/s11837-020-04358-3

Cited by 11 publications

(5 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Learning Physics Models from Data. Physics model learning from data have been explored in (Greydanus, Dzamba, and Yosinski 2019;Cranmer et al 2020a;Lutter, Ritter, and Peters 2018;Niu et al 2020). In regards to efficient methods for physics learning, (Xue et al 2021a), (Sima and Xue 2021), (Nasim et al 2022),(Bar-Sinai et al 2019, (Schaeffer 2017) are similar to our works in that these also aim to make the learning more computationally efficient, using locality sensitive hashing, random projection, approximate derivatives and compressed sensing.…”

Section: Related Workmentioning

confidence: 64%

Efficient Learning of PDEs via Taylor Expansion and Sparse Decomposition into Value and Fourier Domains

Nasim,

Xue

2024

AAAI

View full text Add to dashboard Cite

Accelerating the learning of Partial Differential Equations (PDEs) from experimental data will speed up the pace of scientific discovery. Previous randomized algorithms exploit sparsity in PDE updates for acceleration. However such methods are applicable to a limited class of decomposable PDEs, which have sparse features in the value domain. We propose Reel, which accelerates the learning of PDEs via random projection and has much broader applicability. Reel exploits the sparsity by decomposing dense updates into sparse ones in both the value and frequency domains. This decomposition enables efficient learning when the source of the updates consists of gradually changing terms across large areas (sparse in the frequency domain) in addition to a few rapid updates concentrated in a small set of “interfacial” regions (sparse in the value domain). Random projection is then applied to compress the sparse signals for learning. To expand the model applicability, Taylor series expansion is used in Reel to approximate the nonlinear PDE updates with polynomials in the decomposable form. Theoretically, we derive a constant factor approximation between the projected loss function and the original one with poly-logarithmic number of projected dimensions. Experimentally, we provide empirical evidence that our proposed Reel can lead to faster learning of PDE models (70-98% reduction in training time when the data is compressed to 1% of its original size) with comparable quality as the non-compressed models.

show abstract

Section: Related Workmentioning

confidence: 64%

Efficient Learning of PDEs via Taylor Expansion and Sparse Decomposition into Value and Fourier Domains

Nasim,

Xue

2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Scalable Analysis of in situ Experiment Video Data. Our PHASE-FIELD-LAB has been deployed in the real world to efficiently analyze high volume the experimental in situ video data (Nasim et al 2023;Niu et al 2020Niu et al , 2021. Manual annotation of a single 10-minute in situ video can take upto 3.75 months (Xue et al 2021).…”

Section: Impact Of Phase-field-lab In Scientific Discoverymentioning

confidence: 99%

“…The amount of data collected for this pipeline of related analysis tasks can be overwhelming. For example, in the application domains considered in this paper, in situ radiation experiments to study material properties under extreme conditions generate high resolution high frame rate videos in the scale of terabytes (Niu et al 2020). To automate the dis- datasets, scalable and reliable AI-driven data analysis methods are essential.…”

Section: Introductionmentioning

confidence: 99%

“…PHASE-FIELD-LAB is currently being used by material scientists for analyzing material defects evolution in metallic materials, such as the void defects shown in Figure 2. Using our tool provides the researchers the ability to scale up the analysis process (Niu et al 2020), which in turn has led to the discovery of new physics phenomena of the size fluctuations of the void defects in metal (Cu) under irradiation and high temperature (Nasim et al 2023).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

End-to-End Phase Field Model Discovery Combining Experimentation, Crowdsourcing, Simulation and Learning

Nasim,

Zhang,

El-Azab

et al. 2024

AAAI

View full text Add to dashboard Cite

The availability of tera-byte scale experiment data calls for AI driven approaches which automatically discover scientific models from data. Nonetheless, significant challenges present in AI-driven scientific discovery: (i) The annotation of large scale datasets requires fundamental re-thinking in developing scalable crowdsourcing tools. (ii) The learning of scientific models from data calls for innovations beyond black-box neural nets. (iii) Novel visualization & diagnosis tools are needed for the collaboration of experimental and theoretical physicists, and computer scientists. We present Phase-Field-Lab platform for end-to-end phase field model discovery, which automatically discovers phase field physics models from experiment data, integrating experimentation, crowdsourcing, simulation and learning. Phase-Field-Lab combines (i) a streamlined annotation tool which reduces the annotation time (by ~50-75%), while increasing annotation accuracy compared to baseline; (ii) an end-to-end neural model which automatically learns phase field models from data by embedding phase field simulation and existing domain knowledge into learning; and (iii) novel interfaces and visualizations to integrate our platform into the scientific discovery cycle of domain scientists. Our platform is deployed in the analysis of nano-structure evolution in materials under extreme conditions (high temperature and irradiation). Our approach reveals new properties of nano-void defects, which otherwise cannot be detected via manual analysis.

show abstract

“…Such significant microstructure damages can cause swelling, hardening, embrittlement, and other problems in materials which significantly shorten their service life [33,34]. The irradiation stability of a material can be strengthened through introducing defect sinks, such as grain boundaries (GBs) [35][36][37][38], twin boundaries (TBs) [39][40][41][42][43][44][45], and free surface [46][47][48][49][50][51][52], which facilitate the recombination of irradiation-induced defects and defect clusters. It is well known that interfaces may also act as effective defect sinks [53].…”

Section: Introductionmentioning

confidence: 99%

Recent Studies on the Fabrication of Multilayer Films by Magnetron Sputtering and Their Irradiation Behaviors

Jin

Jian

et al. 2021

Coatings

Self Cite

View full text Add to dashboard Cite

Multilayer films with high-density layer interfaces have been studied widely because of the unique mechanical and functional properties. Magnetron sputtering is widely chosen to fabricate multilayer films because of the convenience in controlling the microstructure. Essentially, the properties of multilayer films are decided by the microstructure, which could be adjusted by manipulating the deposition parameters, such as deposition temperature, rate, bias, and target–substrate distance, during the sputter process. In this review, the influences of the deposition parameters on the microstructure evolution of the multilayer films have been summarized. Additionally, the impacts of individual layer thickness on the microstructure evolution as well as the irradiation behavior of various multilayer films have been discussed.

show abstract

Recent Studies on Void Shrinkage in Metallic Materials Subjected to In Situ Heavy Ion Irradiations

Cited by 11 publications

References 65 publications

Efficient Learning of PDEs via Taylor Expansion and Sparse Decomposition into Value and Fourier Domains

Efficient Learning of PDEs via Taylor Expansion and Sparse Decomposition into Value and Fourier Domains

End-to-End Phase Field Model Discovery Combining Experimentation, Crowdsourcing, Simulation and Learning

Recent Studies on the Fabrication of Multilayer Films by Magnetron Sputtering and Their Irradiation Behaviors

Contact Info

Product

Resources

About