scholarly journals Gaussian Mixture Model Based Damage Evaluation for Aircraft Structures

2021 ◽  
Keyword(s):  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Probability Model ◽  
High Sensitivity ◽  
Gaussian Mixture ◽  
Guided Wave ◽  
Time Varying ◽  
Damage Evaluation ◽  
Significant Research ◽  
Structural Boundary

Abstract. The Guided Wave (GW) based Structural Health Monitoring (SHM) method is of significant research interest because of its wide monitoring range and high sensitivity. However, there are still many challenges in real engineering applications due to complex time-varying conditions, such as changes in temperature and humidity, random dynamic loads, and structural boundary conditions. In this paper, a Gaussian Mixture Model (GMM) is adopted to deal with these problems. Multi-dimensional GMM (MDGMM) is proposed to model the probability distribution of GW features under time-varying conditions. Furthermore, to measure the migration degree of MDGMM to reveal the crack propagation, research on migration indexes of the probability model is carried out. Finally, the validation in an aircraft fatigue test shows a good performance of the MDGMM.

Gaussian mixture model–based path-synthesis accumulation imaging of guided wave for damage monitoring of aircraft composite structures under temperature variation

2018 ◽  
Vol 18 (1) ◽  
pp. 284-302 ◽  
Author(s):  
Yuanqiang Ren ◽  
Lei Qiu ◽  
Shenfang Yuan ◽  
Fang Fang
Keyword(s):  
Temperature Variation ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Composite Structures ◽  
Gaussian Mixture ◽  
Guided Wave ◽  
Time Varying ◽  
Damage Imaging ◽  
Wave Path ◽  
Path Synthesis

With the capabilities of achieving large-scale monitoring, improving signal-to-noise ratio, and obtaining a high localization accuracy and strong fault tolerance, guided wave and piezoelectric sensor network–based damage imaging technique seems to be the key technique to realize damage localization of complex aircraft composite structures. However, aircraft structures usually work under random and complicated time-varying conditions, which may introduce nonnegligible uncertainties in the acquired guided wave signals and mask the subtle changes caused by damage. The current damage imaging methods barely consider this time-varying issue and are unable to reliably locate damage. To increase reliability, a Gaussian mixture model–based guided wave path-synthesis accumulation imaging method is proposed for damage imaging of complex aircraft composite structures under time-varying conditions. The Gaussian mixture model is used to suppress time-varying influence and achieve time-varying-independent damage characterization, based on which the guided wave path-synthesis imaging is conducted to perform the fusion of sensor network information and generate an image. During the monitoring process, a series of images will be generated with damage information accumulated, and the damage will gradually emerge in these images and can be located eventually. The typical time-varying condition, temperature variation, is chosen to verify the feasibility and effectiveness of the proposed method on a stiffened carbon fiber composite plate; the results show good performance of reliable damage imaging and localization within a temperature range from 0°C to 60°C.

scholarly journals scHiCSRS: A Self-Representation Smoothing Method with Gaussian Mixture Model for Imputing single-cell Hi-C Data

2021 ◽  
Author(s):  
Shili Lin ◽  
Qing Xie
Keyword(s):  
Single Cell ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Single Cells ◽  
High Sensitivity ◽  
Gaussian Mixture ◽  
Smoothing Method ◽  
Intermediate Step ◽  
Downstream Analysis ◽  
Structural Zeros

Motivation: Single-cell Hi-C techniques make it possible to study cell-to-cell variability in genomic features. However, excess zeros are commonly seen in single-cell Hi-C (scHi-C) data, making scHi-C matrices extremely sparse and bringing extra difficulties in downstream analysis. The observed zeros are a combination of two events: structural zeros for which the loci never inter- act due to underlying biological mechanisms, and dropouts or sampling zeros where the two loci interact but are not captured due to insufficient sequencing depth. Although quality improvement approaches have been proposed as an intermediate step for analyzing scHi-C data, little has been done to address these two types of zeros. We believe that differentiating between structural zeros and dropouts would benefit downstream analysis such as clustering. Results: We propose scHiCSRS, a self-representation smoothing method that improves the data quality, and a Gaussian mixture model that identifies structural zeros among observed zeros. scHiCSRS not only takes spatial dependencies of a scHi-C 2D data structure into account but also borrows information from similar single cells. Through an extensive set of simulation studies, we demonstrate the ability of scHiCSRS for identifying structural zeros with high sensitivity and for accurate imputation of dropout values in sampling zeros. Downstream analysis for three real datasets show that data improved from scHiCSRS yield more accurate clustering of cells than simply using observed data or improved data from several comparison methods.

scholarly journals Automated segmentation of intraretinal cystoid macular edema based on Gaussian mixture model

2019 ◽  
Vol 13 (01) ◽  
pp. 1950020
Author(s):  
Jinghong Wu ◽  
Sijie Niu ◽  
Qiang Chen ◽  
Wen Fan ◽  
Songtao Yuan ◽  
...  
Keyword(s):  
Optical Coherence Tomography ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Level Set ◽  
Spatial Information ◽  
High Sensitivity ◽  
Gaussian Mixture ◽  
Automated Segmentation ◽  
Potential Fluid ◽  
Sd Oct

We introduce a method based on Gaussian mixture model (GMM) clustering and level-set to automatically detect intraretina fluid on diabetic retinopathy (DR) from spectral domain optical coherence tomography (SD-OCT) images in this paper. First, each B-scan is segmented using GMM clustering. The original clustering results are refined using location and thickness information. Then, the spatial information among every consecutive five B-scans is used to search potential fluid. Finally, the improved level-set method is used to obtain the accurate boundaries. The high sensitivity and accuracy demonstrated here show its potential for detection of fluid.

A uniform initialization Gaussian mixture model–based guided wave–hidden Markov model with stable damage evaluation performance

2018 ◽  
Vol 18 (3) ◽  
pp. 853-868 ◽  
Author(s):  
Shenfang Yuan ◽  
Jinjin Zhang ◽  
Jian Chen ◽  
Lei Qiu ◽  
Weibo Yang
Keyword(s):  
Fatigue Crack ◽  
Markov Model ◽  
Crack Propagation ◽  
Hidden Markov Model ◽  
Hidden Markov ◽  
Gaussian Mixture ◽  
Guided Wave ◽  
Time Varying ◽  
Damage Evaluation ◽  
Model Based

During practical applications, the time-varying service conditions usually lead to difficulties in properly interpreting structural health monitoring signals. The guided wave–hidden Markov model–based damage evaluation method is a promising approach to address the uncertainties caused by the time-varying service condition. However, researches that have been performed to date are not comprehensive. Most of these research studies did not introduce serious time-varying factors, such as those that exist in reality, and hidden Markov model was applied directly without deep consideration of the performance improvement of hidden Markov model itself. In this article, the training stability problem when constructing the guided wave–hidden Markov model initialized by usually adopted k-means clustering method and its influence to damage evaluation were researched first by applying it to fatigue crack propagation evaluation of an attachment lug. After illustrating the problem of stability induced by k-means clustering, a novel uniform initialization Gaussian mixture model–based guided wave–hidden Markov model was proposed that provides steady and reliable construction of the guided wave–hidden Markov model. The advantage of the proposed method is demonstrated by lug fatigue crack propagation evaluation experiments.

scholarly journals Multi-Dimensional Uniform Initialization Gaussian Mixture Model for Spar Crack Quantification under Uncertainty

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1283
Author(s):  
Qiuhui Xu ◽  
Shenfang Yuan ◽  
Tianxiang Huang
Keyword(s):  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Expectation Maximization Algorithm ◽  
Gaussian Mixture ◽  
Fatigue Tests ◽  
Guided Wave ◽  
Monitoring Method ◽  
Notched Specimen ◽  
Small Cracks ◽  
The Relationship

Guided Wave (GW)-based crack monitoring method as a promising method has been widely studied, as this method is sensitive to small cracks and can cover a wide monitoring range. Online crack quantification is difficult as the initiation and growth of crack are affected by various uncertainties. In addition, crack-sensitive GW features are influenced by time-varying conditions which further increase the difficulty in crack quantification. Considering these uncertainties, the Gaussian mixture model (GMM) is studied to model the probability distribution of GW features. To further improve the accuracy and stability of crack quantification under uncertainties, this paper proposes a multi-dimensional uniform initialization GMM. First, the multi-channel GW features are integrated to increase the accuracy of crack quantification, as GW features from different channels have different sensitivity to cracks. Then, the uniform initialization method is adopted to provide more stable initial parameters in the expectation-maximization algorithm. In addition, the relationship between the probability migration index of GMMs and crack length is calibrated with fatigue tests on prior specimens. Finally, the proposed method is applied for online crack quantification on the notched specimen of an aircraft spar with complex fan-shaped cracks under uncertainty.

Sign in / Sign up

Export Citation Format

Share Document