Chapter 6
Data-Driven Methodologies for Structural Damage
Detection Based on Machine Learning Applications
Jaime Vitola, Maribel Anaya Vejar,
Diego Alexander Tibaduiza Burgos and
Francesc Pozo
Additional information is available at the end of the chapter
http://dx.doi.org/10.5772/65867
© 2016 The Author(s). Licensee InTech. This chapter is distributed under the terms of the Creative Commons
Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution,
and reproduction in any medium, provided the original work is properly cited.
Jaime Vitola, Maribel Anaya Vejar, Diego
Alexander Tibaduiza Burgos and Francesc
Pozo
Additional information is available at the end of the chapter
Abstract
Structural health monitoring (SHM) is an important research area, which interest is the
damage identication process. Dierent information about the state of the structure
can be obtained in the process, among them, detection, localization and classication
of damages are mainly studied in order to avoid unnecessary maintenance procedures
in civilian and military structures in several applications. To carry out SHM in prac-
tice, two dierent approaches are used, the rst is based on modelling which requires to
build a very detailed model of the structure, while the second is by means of data-driven
approaches which use information collected from the structure under dierent struc-
tural states and perform an analysis by means of data analysis . For the laer, statisti-
cal analysis and paern recognition have demonstrated its eectiveness in the damage
identication process because real information is obtained from the structure through
sensors installed permanently to the observed object allowing a real-time monitoring.
This chapter describes a damage detection and classication methodology, which makes
use of a piezoelectric active system which works in several actuation phases and that is
aached to the structure under evaluation, principal component analysis, and machine
learning algorithms working as a paern recognition methodology. In the chapter, the
description of the developed approach and the results when it is tested in one aluminum
plate are also included.
Keywords: SHM, PCA, machine learning, structural health monitoring
1. Introduction
Structural health monitoring (SHM) is a very interesting area, which main objective is the
damage identication using permanently installed sensors to the structure. In general, one
© 2016 The Author(s). Licensee InTech. This chapter is distributed under the terms of the Creative Commons
Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use,
distribution, and reproduction in any medium, provided the original work is properly cited.
of the aims is to monitor in real time a structure in order to know the current state starting
from the damage detection, from this point of view, damage detection is extremely important:
rst, for safety, because it helps manage the downside risk resulting in a reduction cost by
improving the visual inspection and maintenance processes [1, 2]. Currently, the new devel-
opments in several areas include the use of more complex structures. In many cases, the rela-
tion between the structure and the rest of the elements introduces interdependences which
can be non-linear increasing the diculty of the damage detection process. In these cases, a
multicomponent and systemic approach can be incorporated to result in a safe and optimal
maintenance model [3]. It is also important to note that there is infrastructure, which has been
in use for several years, some examples can be found in historical buildings, bridges, aero-
nautical and aerospace structures, among others. This aging process brings new challenges
[4] for SHM systems.
It is mandatory also to highlight the wide range of opportunities oered by the automation of
the structural health monitoring process which can be used in conjunction with other automa-
tion systems such as an integrated transport system (ITS - Intelligent Transportation Systems),
auto guided vehicles, among others. This symbiosis can oer benets and give news perspec-
tives about the use of the structures by providing additional information that the SHM sys-
tems can leverage to increase reliability, robustness and eciency, reducing the probability
of error, and providing tools for a beer decision-making [5]. Structural health systems have
a wide application in countless civilian infrastructures such as bridges [24] and buildings [6].
Similarly, SHM systems have been also applied to monitor mechanical components such as
fuselages helicopters [7], wind turbines installed on land [8, 9] and sea (oshore) [10], aero-
space equipment [11], aircraft [12], high-speed trains [13], aircraft turbines [14] and boats [15],
in the same way SHM systems have been applied to marine renewable energy equipment [16].
It is noteworthy that the environmental conditions need to be considered to ensure a robust
damage detection, in this sense, some works have been introduced to compensate the eects
of the temperature changes [17, 18].
Regardless of the infrastructure design or the technology used in the development of the
maintenance decision making, there are some factors to consider. Factors, such as informa-
tion about the physical infrastructure, administrative information, use, and many others
such as reliability, maintainability, operability, bearing capacity, and policy-adopted main-
tenance [19], need to be considered. Added to this it must be remembered drift probability
[20]. The theories and the denition about the best inspection process are really complex,
for instance in the machines which are working all time it is necessary to develop mainte-
nance methodologies to avoid the failure or breakdown maintenance, in this sense, preven-
tive maintenance and reliability-centered maintenance, among others need to be included
[21]. This chapter includes a description of a methodology for damage detection and clas-
sication and the experimental validation with data from an aluminum plate instrumented
with piezoelectric transducers permanently aached to its surface. In this sense, the chapter
is organized as follows: Chapter 2 presents general concepts about the methods and con-
cepts used in the methodology, Chapter 3 explains the methodology. Chapter 4 describes
the experimental setup, after Chapter 5 presents the results, nally the conclusions are
included.
Pattern Recognition - Analysis and Applications110
2. General concepts
The methodology described in this work uses some well-known methods for data driven,
however in this section some of this concepts will be introduced.
2.1. Principal components analysis
One of the greatest diculties in data analysis occurs when the amount of data is very large
and there is no apparent relationship between all the information or if it is very dicult to
nd. As solution, principal component analysis (PCA) was born as a very useful tool to reduce
and analyze a big quantity of information. The principal component analysis technique was
described by Pearson in 1901, as a Mechanism of Multivariate analysis and was also used
by Hotelling in 1933 [22]. This method allows to nd the principal components, which are a
reduced version of the original dataset and include relevant information that identies the
reason for the variation between them. To nd these variables, the analysis includes the trans-
formation of the current coordinate space to a new space in order to re-express the original
data trying to lter the noise and redundancies. These redundancies are measured by means
of the correlation between the variables [23].
There are two mechanisms to implement the analysis of main components: rst method is
based on correlations and second is based on covariance. It is necessary to highlight that PCA
is not invariant to scale, so the data under study must be normalized. Many methods can be
used to do this as is shown in [23, 24]. In many applications, PCA is used as a tool to reduce the
dimensionality of the data to be applied in a subsequent process to work with a reduced num-
ber of data. Currently, there are many useful toolboxes to apply PCA and analyze the reduced
data provided by the technique [25], this is one of the reasons about PCA still being used. More
information about PCA and the normalization process can be consulted in Refs. [24, 26–28].
2.2. Machine learning
Since Alan Turing showed interest in learning by machines, this area has remained at the fore-
front of the research by increasing his popularity and expanding its eld of performance [29].
This has revolutionized the way in which complex problems has been tackled. In the relent-
less pursuit of best tools for data analysis, machine learning has been highlighted by nding
a set of strategies for paern recognition, which are able to nd the relationship between data
that at rst glance have no correlation and are very dicult to dene a deterministic math-
ematical model. Machine learning strategies and bio-inspired algorithms allow to avoid this
diculty through mechanisms designed to nd the answer by themselves. In SHM or related
areas, it is possible to nd some applications about how machine learning has been used to
detect problems, such as breaks, corrosion, cracks, impact damage, delamination, disunity,
breaking bers (some pertinent to metals and the others to composite materials [30]), in addi-
tion it has been used to provide information about the future behavior of a structure under
extreme events such as earthquakes [31].
Depending on how the algorithms work, machine learning can be classied into two main
approaches: unsupervised and supervised learning. First, the information is grouped and
Data-Driven Methodologies for Structural Damage Detection Based on Machine Learning Applications
http://dx.doi.org/10.5772/65867
111
interpreted only using the input data, however, the second, requires information about the
output data to perform the learning task. Figure 1 shows this classication and includes infor-
mation about the works that each one of these learning can be used.
Since this work is aimed to classify damages, supervised learning is used. In practice, this task
is performed through the classication learner toolbox of MATLAB®, and Table 1 includes
the methods used in the development of this work.
Figure 1. Machine learning approaches according to the learning.
Decision trees Nearest neighbor classiers Support vector machines Ensemble classiers
Simple tree Fine KNN Linear SVM Boosted trees
Medium tree Cubic SVM Fine Gaussian SVM Bagged trees
Complex Tree Medium KNN Medium Gaussian SVM Subspace KNN
Coarse KNN Coarse Gaussian SVM Subspace discriminant
Cosine KNN Quadratic SVM RUSBoosted
Weighted KNN Cubic SVM Trees
Table 1. Methods included in the classication learner toolbox of MATLAB®.
Pattern Recognition - Analysis and Applications112
3. Damage classication methodology
The methodology used in this work is aimed to the damage detection and classication. To per-
form this task, it is necessary to highlight that paern recognition point of view is used, in this
sense, the methodology works rst with the denition of a healthy paern which is obtained
from dierent states of the structure. In this work, data from healthy and dierent damages are
used as inputs to the machines. This stage is dened as training and is developed as in Figure 2.
In general terms, the process includes a pre-processing step, where all the experiments are
organized in a matrix per each actuation phase as in Figure 3, and normalization is applied
before to create PCA models.
Figure 2. Training process.
Figure 3. Organization and normalization data.
Data-Driven Methodologies for Structural Damage Detection Based on Machine Learning Applications
http://dx.doi.org/10.5772/65867
113