A Damage Classification Approach for Structural Health Monitoring Using Machine Learning

Burgos, Diego Alexander Tibaduiza; Torres-Arredondo, Miguel Angel; Vitola, Jaime; Anaya, Maribel; Pozo, Francesc

doi:10.1155/2018/5081283

Cited by 49 publications

(31 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonlinear approaches, such as nonlinear PCA (NLPCA), have also been analyzed for damage detection and classification. Some examples include the combination of the hierarchical version of NLPCA (h-NLPLCA) and machine learning, in which the nonlinear components are used as the feature vector to train different models [185].…”

Section: Development Of Statistical Modelsmentioning

confidence: 99%

Damage Identification in Structural Health Monitoring: A Brief Review from its Implementation to the Use of Data-Driven Applications

Burgos

Vargas

Pedraza

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

The damage identification process provides relevant information about the current state of a structure under inspection, and it can be approached from two different points of view. The first approach uses data-driven algorithms, which are usually associated with the collection of data using sensors. Data are subsequently processed and analyzed. The second approach uses models to analyze information about the structure. In the latter case, the overall performance of the approach is associated with the accuracy of the model and the information that is used to define it. Although both approaches are widely used, data-driven algorithms are preferred in most cases because they afford the ability to analyze data acquired from sensors and to provide a real-time solution for decision making; however, these approaches involve high-performance processors due to the high computational cost. As a contribution to the researchers working with data-driven algorithms and applications, this work presents a brief review of data-driven algorithms for damage identification in structural health-monitoring applications. This review covers damage detection, localization, classification, extension, and prognosis, as well as the development of smart structures. The literature is systematically reviewed according to the natural steps of a structural health-monitoring system. This review also includes information on the types of sensors used as well as on the development of data-driven algorithms for damage identification.

show abstract

Section: Development Of Statistical Modelsmentioning

confidence: 99%

Damage Identification in Structural Health Monitoring: A Brief Review from its Implementation to the Use of Data-Driven Applications

Burgos

Vargas

Pedraza

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Five different supervised machine learning algorithms were compared in the classification stage, among them were: KNN, SVM, MLP ANN, Adaboost, and Gaussian process classifier. Because of these classifiers being well known, the authors suggest the reading of the following works, for more details [ 59 , 60 , 61 ].…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Nonlinear Feature Extraction Through Manifold Learning in an Electronic Tongue Classification Task

Leon-Medina

Anaya

Pozo

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

A nonlinear feature extraction-based approach using manifold learning algorithms is developed in order to improve the classification accuracy in an electronic tongue sensor array. The developed signal processing methodology is composed of four stages: data unfolding, scaling, feature extraction, and classification. This study aims to compare seven manifold learning algorithms: Isomap, Laplacian Eigenmaps, Locally Linear Embedding (LLE), modified LLE, Hessian LLE, Local Tangent Space Alignment (LTSA), and t-Distributed Stochastic Neighbor Embedding (t-SNE) to find the best classification accuracy in a multifrequency large-amplitude pulse voltammetry electronic tongue. A sensitivity study of the parameters of each manifold learning algorithm is also included. A data set of seven different aqueous matrices is used to validate the proposed data processing methodology. A leave-one-out cross validation was employed in 63 samples. The best accuracy (96.83%) was obtained when the methodology uses Mean-Centered Group Scaling (MCGS) for data normalization, the t-SNE algorithm for feature extraction, and k-nearest neighbors (kNN) as classifier.

show abstract

“…Unsupervised approaches do not make use of prior information and can be considered as 'blind'. They make use of patterns and similarities in data features in order to find labels [13].…”

Section: Machine Learning As a Tool For Structural Health Monitoringmentioning

confidence: 99%

Damage Detection in Composites By Artificial Neural Networks Trained By Using in Situ Distributed Strains

et al. 2020

View full text Add to dashboard Cite

In this paper, a passive structural health monitoring (SHM) method capable of detecting the presence of damage in carbon fibre/epoxy composite plates is developed. The method requires the measurement of strains from the considered structure, which are used to set up, train, and test artificial neural networks (ANNs). At the end of the training phase, the networks find correlations between the given strains, which represent the ‘fingerprint’ of the structure under investigation. Changes in the distribution of these strains is captured by assessing differences in the previously identified strain correlations. If any cause generates damage that alters the strain distribution, this is considered as a reason for further detailed structural inspection. The novelty of the strain algorithm comes from its independence from both the choice of material and the loading condition. It does not require the prior knowledge of material properties based on stress-strain relationships and, as the strain correlations represent the structure and its mechanical behaviour, they are valid for the full range of operating loads. An implementation of such approach is herein presented based on the usage of a distributed optical fibre sensor that allows to obtain strain measurement with an incredibly high resolution.

show abstract

A Damage Classification Approach for Structural Health Monitoring Using Machine Learning

Cited by 49 publications

References 45 publications

Damage Identification in Structural Health Monitoring: A Brief Review from its Implementation to the Use of Data-Driven Applications

Damage Identification in Structural Health Monitoring: A Brief Review from its Implementation to the Use of Data-Driven Applications

Nonlinear Feature Extraction Through Manifold Learning in an Electronic Tongue Classification Task

Damage Detection in Composites By Artificial Neural Networks Trained By Using in Situ Distributed Strains

Contact Info

Product

Resources

About