Deep learning-assisted microstructural analysis of Ni/YSZ anode composites for solid oxide fuel cells

Hwang, Heesu; Ahn, Junsung; Lee, Hyunbae; Oh, Jungkeun; Kim, Jaehwan; Ahn, Jae Pyung; Kim, Hong‐Kyu; Lee, Jong‐Ho; Yoon, Young; Hwang, Jin‐Ha

doi:10.1016/j.matchar.2021.110906

Cited by 18 publications

(6 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, deep learning techniques have seen significant advancements in various fields, as evidenced by numerous studies [32][33][34]. For network threat detection, in [35], anomalous traffic was detected using spatio-temporal information modeling based on the C-LSTM method.…”

Section: The Usage Of Machine Learningmentioning

confidence: 99%

An Ensemble of Text Convolutional Neural Networks and Multi-Head Attention Layers for Classifying Threats in Network Packets

Kim,

Yoon

2023

Electronics

Self Cite

View full text Add to dashboard Cite

Using traditional methods based on detection rules written by human security experts presents significant challenges for the accurate detection of network threats, which are becoming increasingly sophisticated. In order to deal with the limitations of traditional methods, network threat detection techniques utilizing artificial intelligence technologies such as machine learning are being extensively studied. Research has also been conducted on analyzing various string patterns in network packet payloads through natural language processing techniques to detect attack intent. However, due to the nature of packet payloads that contain binary and text data, a new approach is needed that goes beyond typical natural language processing techniques. In this paper, we study a token extraction method optimized for payloads using n-gram and byte-pair encoding techniques. Furthermore, we generate embedding vectors that can understand the context of the packet payload using algorithms such as Word2Vec and FastText. We also compute the embedding of various header data associated with packets such as IP addresses and ports. Given these features, we combine a text 1D CNN and a multi-head attention network in a novel fashion. We validated the effectiveness of our classification technique on the CICIDS2017 open dataset and over half a million data collected by The Education Cyber Security Center (ECSC), currently operating in South Korea. The proposed model showed remarkable performance compared to previous studies, achieving highly accurate classification with an F1-score of 0.998. Our model can also preprocess and classify 150,000 network threats per minute, helping security agents in the field maximize their time and analyze more complex attack patterns.

show abstract

Section: The Usage Of Machine Learningmentioning

confidence: 99%

An Ensemble of Text Convolutional Neural Networks and Multi-Head Attention Layers for Classifying Threats in Network Packets

Kim,

Yoon

2023

Electronics

Self Cite

View full text Add to dashboard Cite

show abstract

“…After the training, ViT-TA detects and highlights objects contributing to the critical conditions. Through object recognition [71], semantic segmentation, and image classification techniques [72,73], the types and geometry of the highlighted objects can be inferred. Upon detection of the first appearance of the critical objects, video frames up to the Post-collision point are iterated to compute the values of the situational variables, such as speed and direction of the vehicles and the distance between critical objects.…”

Section: Composition Of Vulnerable Traffic Accident Scenarios Based O...mentioning

confidence: 99%

Vision Transformer for Detecting Critical Situations and Extracting Functional Scenario for Automated Vehicle Safety Assessment

et al. 2022

Self Cite

View full text Add to dashboard Cite

Automated Vehicles (AVs) are attracting attention as a safer mobility option thanks to the recent advancement of various sensing technologies that realize a much quicker Perception–Reaction Time than Human-Driven Vehicles (HVs). However, AVs are not entirely free from the risk of accidents, and we currently lack a systematic and reliable method to improve AV safety functions. The manual composition of accident scenarios does not scale. Simulation-based methods do not fully cover the peculiar AV accident patterns that can occur in the real world. Artificial Intelligence (AI) techniques are employed to identify the moments of accidents from ego-vehicle videos. However, most AI-based approaches fall short in accounting for the probable causes of the accidents. Neither of these AI-driven methods offer details for authoring accident scenarios used for AV safety testing. In this paper, we present a customized Vision Transformer (named ViT-TA) that accurately classifies the critical situations around traffic accidents and automatically points out the objects as probable causes based on an Attention map. Using 24,740 frames from Dashcam Accident Dataset (DAD) as training data, ViT-TA detected critical moments at Time-To-Collision (TTC) ≤ 1 s with 34.92 higher accuracy than the state-of-the-art approach. ViT-TA’s Attention map highlighting the critical objects helped us understand how the situations unfold to put the hypothetical ego vehicles with AV functions at risk. Based on the ViT-TA-assisted interpretation, we systematized the composition of Functional scenarios conceptualized by the PEGASUS project for describing a high-level plan to improve AVs’ capability of evading critical situations. We propose a novel framework for automatically deriving Logical and Concrete scenarios specified with 6-Layer situational variables defined by the PEGASUS project. We believe our work is vital towards systematically generating highly reliable and trustworthy safety improvement plans for AVs in a scalable manner.

show abstract

“…All the above-mentioned models are based on various assumptions, which can only indirectly explain the real 3D microstructure. In this context, recent progress in high-resolution tomography utilizing a focused ion beam (FIB) has opened new analytical possibilities and, thus, initiated new potentials for the microstructure-performance relationship investigations in composite SOFC anodes [9,[20][21][22][23][24][25][26]. Through such real 3D measurements, essential microstructural parameters, such as three-phase boundary length (TPBL) and tortuosity, can be obtained.…”

Section: Introductionmentioning

confidence: 99%

The Microstructural Reconstruction of Variously Sintered Ni-SDC Cermets Using Focused Ion Beam Scanning Electron Microscopy Nanotomography

Kapun,

Majorovits,

Šturm

et al. 2024

Materials

View full text Add to dashboard Cite

This work focuses in-depth on the quantitative relationships between primary first-order microstructural parameters (i.e., volume fractions of various phases and particle size distribution) with the more complex second-order topological features (i.e., connectivity of phases, three-phase boundary length (TPBL), interfacial areas, or tortuosity). As a suitable model material, a cermet nickel/samaria-doped ceria (Ni-SDC) is used as an anode in a solid oxide fuel cell (SOFC). A microstructure description of nano-sized Ni-SDC cermets, fabricated at various sintering conditions from 1100 °C to 1400 °C, was performed using FIB-SEM nanotomography. The samples were serially sectioned employing a fully automated slicing procedure with active drift correction algorithms and an auto-focusing routine to obtain a series of low-loss BSE images. Advanced image processing algorithms were developed and applied directly to image data volume. The microstructural–topological relationships are crucial for the microstructure optimisation and, thus, the improvement of the corresponding electrode performance. Since all grains of individual phases (Ni, SDC, or pores) did not percolate, special attention was given to the visualisation of the so-called active TPBL. Based on the determined microstructure characteristics of the prepared Ni-SDC cermets, including simulations of gas flow and pressure drop, thermal treatment at 1200 °C was recognised as the most appropriate sintering temperature.

show abstract

Deep learning-assisted microstructural analysis of Ni/YSZ anode composites for solid oxide fuel cells

Cited by 18 publications

References 30 publications

An Ensemble of Text Convolutional Neural Networks and Multi-Head Attention Layers for Classifying Threats in Network Packets

An Ensemble of Text Convolutional Neural Networks and Multi-Head Attention Layers for Classifying Threats in Network Packets

Vision Transformer for Detecting Critical Situations and Extracting Functional Scenario for Automated Vehicle Safety Assessment

The Microstructural Reconstruction of Variously Sintered Ni-SDC Cermets Using Focused Ion Beam Scanning Electron Microscopy Nanotomography

Contact Info

Product

Resources

About