Detection of low-velocity impact-induced delaminations in composite laminates using Auto-Regressive models

Nardi, Davide; Lampani, Luca; Pasquali, Michele; Gaudenzi, Paolo

doi:10.1016/j.compstruct.2016.02.005

Cited by 41 publications

(22 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some relevant examples of AR models for damage detection are fault diagnostic and condition monitoring of rolling bearing [71], damage detection in wind turbine [72], damage detection in frame structures [73], and structural health monitoring of civil infrastructure [74,75]. Nardi et al [76] studied the detection of low-velocity impact-induced delamination in smart composite laminates via auto-regressive (AR) models. An optimal order was identified for the AR model to fit the undamaged/damaged data, and the corresponding AR parameters were transformed into a new sub-space via linear discriminant analysis (LDA).…”

Section: Auto Regressive Models (Ar Models)mentioning

confidence: 99%

“…Vamvoudakis-Stefanou et al [77] compared the performance of two non-parametric methods [i.e., power spectral . AR model order p = 25 [76] density (PSA) and transmittance function (TF)] and one parametric method [autoregressive model (AR)], for the detection of impact damage in composite beams. All the three methods were trained with random vibration response signals of a healthy beam.…”

Section: Auto Regressive Models (Ar Models)mentioning

confidence: 99%

See 1 more Smart Citation

Damage assessment of smart composite structures via machine learning: a review

et al. 2019

View full text Add to dashboard Cite

Composite materials are heterogeneous in nature and suffer from complex non-linear modes of failure, such as delamination, matrix crack, fiber-breakage, and voids, among others. The early detection of damage in composite structures, such as airplanes, is imperative to avoid catastrophic failure and tragic consequences. This paper reports on the use of machine learning techniques for the damage assessment (i.e., detection, quantification, and localization) of smart composite structures. The success of the machine learning paradigm for damage assessment depends on the representational capability of the discriminative features for the problems of interest. However, from a practical standpoint, it is not possible to define a global or superset of discriminative features that could discriminate between damaged and undamaged states of the structures, and simultaneously make a distinction between various modes of failures. In addition, one machine learning algorithm may show optimum performance for the discriminative features of a particular problem but fails for others. This article focuses on a review of discriminative features and the corresponding machine learning algorithms (both supervised and unsupervised), for various types of damage in smart composite structures.

show abstract

Section: Auto Regressive Models (Ar Models)mentioning

confidence: 99%

Section: Auto Regressive Models (Ar Models)mentioning

confidence: 99%

Damage assessment of smart composite structures via machine learning: a review

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Discriminant Analysis is a common technique for multivariate analysis, based on finding the linear and quadratic combination of variables, optimising the classification of different classes by means of a discriminant function [64,65].…”

Section: Introductionmentioning

confidence: 99%

Linear and nonlinear features and machine learning for wind turbine blade ice detection and diagnosis

et al. 2019

View full text Add to dashboard Cite

The mass of ice on wind turbines blades is one of the main problems that energy companies have in cold climates. This paper presents a novel approach to detect and classify ice thickness based on pattern recognition through guided ultrasonic waves and Machine Learning. To successfully achieve a supervised classification, it is necessary to employ a method that allows the correct extraction and selection of features of the ultrasonic signal. The main novelty in this work is that the approach considers four feature extraction methods to validate the results, grouped by linear (AutoRegressive (AR) and Principal Component Analysis) and nonlinear (nonlinear-AR eXogenous and Hierarchical Non-Linear Principal Component Analysis), and feature selection is done by Neighbourhood Component Analysis. A supervised classification was performed through Machine Learning with twenty classifiers such as Decision tree, Discriminant Analysis, Support Vector Machines, K-Nearest Neighbours, and Ensemble Classifiers. Finally, an evaluation of the classifiers was done in single frequency and multi-frequency modes, obtaining accurate results.

show abstract

“…The identification of matrix model parameters may be realized by the statistical processing of natural observations [23,24]. At absence of the representative sample of observations for the statistical analysis or absence of other information that allows to assess transformation model parameters, the calculation is realized simplistically: the full transformation of one substances to another ones is provided (p i =k i ), and reference values are chosen for transformation coefficients [20].…”

Section: The Solution Of the Problem Of Drainage Regulation For Nimentioning

confidence: 99%

Improvement of the Model of Transformation of Nitrogen-Containing Substances in a Water Body for the Solution of Nature Management Problem

Proskurnin

Berezenko

Kyrpychova

et al. 2017

EUREKA: Life Sciences

View full text Add to dashboard Cite

In the article is considered the one of aspects of nature management regulation – an account of successive transformation of pollutants in a water body, that come with waste waters of industrial, municipal and agricultural enterprises. It is necessary at the determination of permissible pollutants emission with waste waters that doesn’t allow the excess of the permissible level of substances content in the control point of a water body. This problem is considered on the example of successive transformation of nitrogen-containing substances in the following transformation order: organic nitrogen – ammonium nitrogen - nitrite nitrogen – nitrate nitrogen. The topicality of the modeling of nitrogen-containing substances is conditioned by their role in water ecosystems functioning. At that existent mathematical models of natural water quality formation that take into account substances transformation contain the large number of unknown parameters. So, the use of such models in problems of nature management regulation is problematic, because identification of model parameters is a separate very complicated scientific problem. And existent models with relatively small number of parameters don’t take into account the natural pollution of water bodies, caused by the life activity of organisms; substance losses in the transformational chain are also possible. The improved matrix mathematical model of nitrogen-containing substances transformation without the indicated shortcomings is offered.

show abstract

Detection of low-velocity impact-induced delaminations in composite laminates using Auto-Regressive models

Cited by 41 publications

References 13 publications

Damage assessment of smart composite structures via machine learning: a review

Damage assessment of smart composite structures via machine learning: a review

Linear and nonlinear features and machine learning for wind turbine blade ice detection and diagnosis

Improvement of the Model of Transformation of Nitrogen-Containing Substances in a Water Body for the Solution of Nature Management Problem

Contact Info

Product

Resources

About