☆ 4.5 Article

Cluster-Based Joint Distribution Adaptation Method for Debonding Quantification in Composite Structures

AIAA JOURNAL (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Engineering, Aerospace

Feature Selection, Clustering, and Prototype Placement for Turbulence Datasets

Matthew Barone et al.

Summary: This paper explores automated approaches for analyzing and categorizing turbulent flow data to assess the quality of a turbulence dataset used for constructing data-driven turbulence closures. The study differentiates single-point statistics from multiple high-fidelity turbulent flow simulation datasets using a Gaussian mixture model clustering algorithm. The identified clusters provide insights into turbulence anisotropy and physical phenomena, and exemplars effectively summarize the dataset with reduced data points.

AIAA JOURNAL (2022)

添加到收藏夹

Article Engineering, Aerospace

Real-Time Prediction of Probabilistic Crack Growth with a Helicopter Component Digital Twin

Xuan Zhou et al.

Summary: In this paper, a reduced-order simulation approach is developed to achieve real-time prediction of crack growth in complex structures. By combining symmetric Galerkin boundary element method-finite element method (SGBEM-FEM) coupling method with machine learning methods, the proposed approach can automatically simulate hundreds of crack samples and establish the relation between crack sizes/shapes and crack-front stress intensity factors. This method provides a key simulation technology for realizing the digital twin of complex structures.

AIAA JOURNAL (2022)

添加到收藏夹

Article Engineering, Aerospace

Probabilistic REpresentatives Mining (PREM): A Clustering Method for Distributional Data Reduction

Zhenyu Gao et al.

Summary: This paper presents a data reduction method called Probabilistic Representatives Mining (PREM) which utilizes balanced clustering and multistage computing strategy to achieve better scalability and consistency. Numerical experiments demonstrate the superiority of PREM over baselines in reducing data sets and its effectiveness and accuracy in generating probabilistically representative samples for aviation environmental impact modeling.

AIAA JOURNAL (2022)

添加到收藏夹

Article Computer Science, Theory & Methods

Towards soft real-time fault diagnosis for edge devices in industrial IoT using deep domain adaptation training strategy

Dileep Kumar Soother et al.

Summary: Artificial intelligence and IIoT are rejuvenating fault diagnosis systems in Industry 4.0, proposing a soft real-time fault diagnosis system using domain adaptation training strategy for edge devices.

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING (2022)

添加到收藏夹

Article Engineering, Aerospace

Fatigue Damage Diagnostics-Prognostics Framework for Remaining Life Estimation in Adhesive Joints

Karthik Reddy Lyathakula et al.

Summary: This work presents an integrated damage diagnostics-prognostics framework for remaining useful life (RUL) estimation in adhesively bonded joints under fatigue loading. A matching pursuit algorithm is used for damage diagnostics, and a fatigue damage growth simulator is used for predictive modeling of fatigue degradation. The framework calibrates the simulator by quantifying uncertainties in fatigue model parameters. Bayesian inference via the Markov chain Monte Carlo method is used to estimate the probabilistic RUL based on the quantified uncertainties. The proposed diagnostic technique uses ultrasonic guided waves to quantify the damage extent.

AIAA JOURNAL (2022)

添加到收藏夹

Article Engineering, Biomedical

Domain Adaptation for Medical Image Analysis: A Survey

Hao Guan et al.

Summary: This paper surveys the recent advances of domain adaptation methods in medical image analysis, presents the motivation of introducing domain adaptation techniques to tackle domain heterogeneity issues in medical image analysis, and reviews the recent domain adaptation models in various medical image analysis tasks.

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING (2022)

添加到收藏夹

Article Engineering, Mechanical

Shape sensing and damage identification with iFEM on a composite structure subjected to impact damage and non-trivial boundary conditions

Luca Colombo et al.

Summary: The inverse Finite Element Method (iFEM) is a valuable tool for shape sensing and damage identification in structural health monitoring frameworks. This method calculates displacement fields and strain fields based on discrete strain measurements in the structure without prior knowledge of material properties or loading conditions.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2021)

添加到收藏夹

Article Engineering, Mechanical

Foundations of Population-based SHM, Part II: Heterogeneous populations - Graphs, networks, and communities

J. Gosliga et al.

Summary: This paper introduces a new technology PBSHM, which can transfer diagnostic information among a population of structures, enhancing SHM capability. By introducing IE models and AGs forming a network, assessing structural similarity, achieving knowledge transfer between structures, and discussing transfer using machine learning methods. These theories can be used to define precise terminology for PBSHM.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2021)

添加到收藏夹

Article Engineering, Mechanical

Foundations of population-based SHM, Part III: Heterogeneous populations - Mapping and transfer

P. Gardner et al.

Summary: This paper discusses the central ideas of knowledge transfer and mapping in Population-Based Structural Health Monitoring (PBSHM), as well as the importance of domain adaptation in a structural dynamics context.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2021)

添加到收藏夹

Article Robotics

Bi-Directional Domain Adaptation for Sim2Real Transfer of Embodied Navigation Agents

Joanne Truong et al.

Summary: Deep reinforcement learning models require a large amount of data, but obtaining real-world data is costly and time-consuming. Many researchers have opted to use simulation for training before deploying robots in real environments. Although simulation allows for training many robots in parallel and provides ample data, robots trained solely in simulation often struggle to transfer to the real world, leading to a sim-vs-real gap. The proposed Bi-directional Domain Adaptation (BDA) aims to bridge this gap by addressing both the visual and dynamics domain gaps, showing significant improvements in performance with minimal real-world data samples.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

添加到收藏夹

Article Engineering, Aerospace

Fatigue Damage Monitoring of Wind Turbine Blades by Using the Kalman Filter

Nobuo Namura et al.

Summary: The paper proposes a monitoring system to track fatigue damage accumulation in order to extend the lifetime of horizontal axis wind turbines. The system utilizes physics models and a Kalman filter to estimate bending moment distribution along the blade using data collected by a SCADA system and strain sensors.

AIAA JOURNAL (2021)

添加到收藏夹

Article Engineering, Aerospace

Black-Box Function Aerodynamic Topology Optimization Algorithm via Machine Learning Technologies

Naohiko Ban et al.

Summary: The research aims to construct an efficient global topology optimization method using machine learning technologies, developing the FANTOM approach to overcome the difficulty in obtaining innovative and high-quality concepts in traditional mechanical design processes.

AIAA JOURNAL (2021)

添加到收藏夹

Article Geochemistry & Geophysics

A MultiKernel Domain Adaptation Method for Unsupervised Transfer Learning on Cross-Source and Cross-Region Remote Sensing Data Classification

Wei Liu et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2020)

添加到收藏夹

Article Construction & Building Technology

Particle filtering-based adaptive training of neural networks for real-time structural damage diagnosis and prognosis

Francesco Cadini et al.

STRUCTURAL CONTROL & HEALTH MONITORING (2019)

添加到收藏夹

Article Chemistry, Analytical

Application of Crack Identification Techniques for an Aging Concrete Bridge Inspection Using an Unmanned Aerial Vehicle

In-Ho Kim et al.

SENSORS (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Driver Drowsiness Estimation From EEG Signals Using Online Weighted Adaptation Regularization for Regression (OwARR)

Dongrui Wu et al.

IEEE TRANSACTIONS ON FUZZY SYSTEMS (2017)

添加到收藏夹

Review Physics, Multidisciplinary

Adhesive bonding of composite aircraft structures: Challenges and recent developments

Sp Pantelakis et al.

SCIENCE CHINA-PHYSICS MECHANICS & ASTRONOMY (2014)

添加到收藏夹

Article Construction & Building Technology

Application of sensor technologies for local and distributed structural health monitoring

C. Sbarufatti et al.

STRUCTURAL CONTROL & HEALTH MONITORING (2014)

添加到收藏夹

Article Engineering, Mechanical

Performance optimization of a diagnostic system based upon a simulated strain field for fatigue damage characterization

C. Sbarufatti et al.

MECHANICAL SYSTEMS AND SIGNAL PROCESSING (2013)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Domain Adaptation via Transfer Component Analysis

Sinno Jialin Pan et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS (2011)

添加到收藏夹

Article Engineering, Aerospace

Reengineering Aircraft Structural Life Prediction Using a Digital Twin

Eric J. Tuegel et al.

International Journal of Aerospace Engineering (2011)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A Survey on Transfer Learning

Sinno Jialin Pan et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2010)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Data clustering: 50 years beyond K-means

Anil K. Jain

PATTERN RECOGNITION LETTERS (2010)

添加到收藏夹

Article Computer Science, Theory & Methods

A tutorial on spectral clustering

Ulrike von Luxburg

STATISTICS AND COMPUTING (2007)

添加到收藏夹

Article Engineering, Aerospace

Damage identification of plate structures using a hybrid genetic-sensitivity approach

SM Bland et al.

AIAA JOURNAL (2005)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.