Journal ArticleDOI
Improved density peak clustering-based adaptive Gaussian mixture model for damage monitoring in aircraft structures under time-varying conditions
Lei Qiu,Fang Fang,Shenfang Yuan +2 more
TLDR
An Improved Density Peaks Clustering (IDPC)-based Expectation Maximization (EM) algorithm is proposed to improve the constructing algorithm of the Gaussian Mixture Model (GMM) to enhance the performance of the GMM-based damage monitoring method.About:
This article is published in Mechanical Systems and Signal Processing.The article was published on 2019-07-01. It has received 31 citations till now. The article focuses on the topics: Mixture model & Expectation–maximization algorithm.read more
Citations
More filters
Journal ArticleDOI
Structural health monitoring by a novel probabilistic machine learning method based on extreme value theory and mixture quantile modeling
Hassan Sarmadi,Ka-Veng Yuen +1 more
TL;DR: In this paper , a probabilistic machine learning method based on unsupervised novelty detection for health monitoring of civil structures is proposed, which is based on extreme value theory (EVT) and mixture quantile modeling.
Journal ArticleDOI
Effects of high-amplitude low-frequency structural vibrations and machinery sound waves on ultrasonic guided wave propagation for health monitoring of composite aircraft primary structures
TL;DR: In this article, the effects of high-amplitude low-frequency structural vibrations (HA-LFV) and audible sound waves (SW) on ultrasonic GW propagation were investigated.
Journal ArticleDOI
Deep learning-based planar crack damage evaluation using convolutional neural networks
TL;DR: A deep convolutional neural network (DCNN) for predicting the stress intensity factor (SIF) at the crack tip is designed based on the proposed DCNN, and the SIF can be automatically predicted through computational vision.
Journal ArticleDOI
Nonlinear ultrasonic testing and data analytics for damage characterization: A review
TL;DR: A comprehensive review of the state-of-the-art ML-enriched NUT for damage characterization is provided, including modeling of wave-damage interaction, different NUT techniques for data acquisition, signal pre-processing methods, and damage index-based parameter analysis strategies forDamage characterization.
Journal ArticleDOI
Towards Interpretable Machine Learning for Automated Damage Detection Based on Ultrasonic Guided Waves
Christopher Schnur,Payman Goodarzi,Yevgeniya Lugovtsova,Jannis Bulling,Jens Prager,Kilian Tschöke,Jochen Moll,Andreas Schütze,Tizian Schneider +8 more
TL;DR: This contribution proposes a machine learning approach for automated damage detection, based on an ML toolbox for industrial condition monitoring, applied to a guided wave-based SHM dataset for varying temperatures and damage locations, which is freely available on the Open Guided Waves platform.
References
More filters
Book
The EM algorithm and extensions
TL;DR: The EM Algorithm and Extensions describes the formulation of the EM algorithm, details its methodology, discusses its implementation, and illustrates applications in many statistical contexts, opening the door to the tremendous potential of this remarkably versatile statistical tool.
Journal ArticleDOI
Clustering by fast search and find of density peaks
Alex Rodriguez,Alessandro Laio +1 more
TL;DR: A method in which the cluster centers are recognized as local density maxima that are far away from any points of higher density, and the algorithm depends only on the relative densities rather than their absolute values.
Journal ArticleDOI
Model-based Gaussian and non-Gaussian clustering
TL;DR: The classification maximum likelihood approach is sufficiently general to encompass many current clustering algorithms, including those based on the sum of squares criterion and on the criterion of Friedman and Rubin (1967), but it is restricted to Gaussian distributions and it does not allow for noise.
Journal ArticleDOI
Unsupervised learning of finite mixture models
TL;DR: The novelty of the approach is that it does not use a model selection criterion to choose one among a set of preestimated candidate models; instead, it seamlessly integrate estimation and model selection in a single algorithm.
Journal ArticleDOI
Background and foreground modeling using nonparametric kernel density estimation for visual surveillance
TL;DR: This paper constructs a statistical representation of the scene background that supports sensitive detection of moving objects in the scene, but is robust to clutter arising out of natural scene variations.
Related Papers (5)
Crack Monitoring for Hot-Spot Areas Under Time-Varying Load Condition Based on FCM Clustering Algorithm
Structural health monitoring under environmental and operational variations using MCD prediction error
Mohsen Mousavi,Amir H. Gandomi +1 more