Professional Documents
Culture Documents
discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/228907097
CITATIONS READS
78 446
4 authors, including:
Some of the authors of this publication are also working on these related projects:
All content following this page was uploaded by Gatan Kerschen on 19 July 2017.
E-mail: g.kerschen@ulg.ac.be
37
G Kerschen et al
Figure 2. Comparison of the principal angles of the current and reference data.
A numerical algorithm for the computation of the reference data set contains enough information to cover normal
angles involving a QR factorization and the singular value process operation. The most likely value for the errant
decomposition was proposed by Bjorck and Golub [20] and sensor is defined as the value which minimizes the magnitude
can also be found in [21]. It should be noted that the of the deviation between the response vector x(t) and its
angles have already found several applications in electrical reconstruction x(t). In the approach pioneered by Kramer [4]
engineering [22, 23] and in structural dynamics [3, 17, 24, 25]. and in [28], the reconstruction is performed using non-linear
In this study, our interest lies in the largest angle which allows PCA, but in this study, we restrict ourselves to the linear PCA
one to quantify how the subspaces are globally different. described in section 2. Replacement of a sensor value thus
In practice, due to the noise inherent in a measurement involves finding the value of x j (t) such that
process, the largest angle between the subspaces spanned by
the reference and current data will not be exactly zero even if all min J = x(t) x(t)2 . (4)
xj
sensors are functioning correctly. Before applying the sensor
validation process, the reference data are thus partitioned into Equation (4) is a univariate optimization problem. If
several sets. The principal angle between the subspace spanned there is more than one missing sensor at a time, it requires
by each of these sets and the subspace spanned by the whole a multivariate approach. It is however interesting to note that
data set is computed, which gives us a collection of different there is an analytical solution to this problem [8]. Suppose
angle values. When dealing with the current data set, an again that the j th sensor fails and that the value to be optimized
alarm is issued when the monitored angle exceeds the upper is labelled x . The objective function is
control limit (UCL) defined as the mean angle plus three
times its standard deviation (see outlier statistics [26, 27]). J = (x1 x1 )2 + + (x j x )2 + + (xn S xn S )2 (5)
This corresponds to a 99.7% confidence interval for a normal
distribution. This is illustrated in figure 2. with
When an alert is given, the faulty sensor is then isolated by x = PPT x = Ax (6)
removing one by one the sensors from both the reference and for zero-mean data (we recall that matrix P contains the
current data sets. The angle should then be minimum when principal directions). Now, defining A = A I or ai j =
the faulty sensor is discarded. ai j i j where I is the identity matrix, the objective function
A final remark concerns the normalization of the data. becomes
When using PCA, it is often advised to deal with equally
nS
2
important variables (e.g. with unit variance). In some cases J = ak1 x1 + + ak j x + + akn
x
S nS
. (7)
(e.g. sensor gain fault), it should be kept in mind that the k=1
normalization might mask the fault.
The minimum with respect to x is obtained by setting
J /x = 0. This gives
4. Sensor correction
nS
Let us suppose that n S sensors are available giving a response ak j ak1 x1 + + ak j x + + akn
x = 0.
S nS
(8)
vector x(t) and that for some reason the j th sensor fails. Let k=1
us also assume that the errant sensor has been identified. If the
After a little rearrangement this gives
response given by this sensor contains important information,
correction is then necessary. It is first assumed that the x1 {a j }T {a1 } + + x {a j }T {a j } + + xn S {a j }T {an S } = 0 (9)
38
Sensor validation using principal component analysis
where {ak } is the kth column of A . It follows that Table 1. Geometrical and mechanical properties of the set-up.
S Length (m) Width (m) Thickness (m) Material
{a j }T nk=
j =1 x k {ak }
x = . (10) Main beam 0.7 0.014 0.014 Steel
{a j }T {a j }
Thin beam part 0.04 0.014 0.0005 Steel
From a geometric point of view, this procedure amounts to
finding the intersection between a straight line and the subspace
An interesting feature is that, if the structure may be
spanned by the PCA modes. The straight line is parallel to the
assumed to be linear for low excitation levels, this is no longer
axis of the faulty sensor and is defined by the coordinates of
the case for higher levels. Indeed, if the excitation level is
the remaining sensors. This is pictured in figure 3 where the
increased, the thin part is excited in large deflection and a
first sensor is unavailable, i.e., x1 = 0.
geometrical non-linearity is activated.
Finally, it should be noted that, as in the previous section,
Two different kinds of sensor fault are simulated. Firstly,
the number of sensors must be greater than the number the acceleration measured at the third sensor is multiplied by
of structural modes involved in order to guarantee enough 1.2 (gain fault). Secondly, it is replaced by a white-noise
redundancy in the data. sequence of the same variance (sensor failure).
5.1. Description of the experimental structure 5.2.1. Reference data. The reference data set contains 70 000
points from each of the seven channels. It corresponds to
The benchmark is similar to the one proposed by the Ecole an excitation level equal to 1.4 N for which the structural
Centrale de Lyon (France) in the framework of COST behaviour is linear. An important thing to check is that there
Action F3 working group on Identification of non-linear are enough sensors in relation to the number of excited mode
systems [29]. This experimental application involves a shapes. Table 2 lists the normalized singular values and their
clamped beam with a thin beam part at the end of the main cumulative sum. Two singular values are zero which ensures
beam (cf figure 4). The geometrical and mechanical properties enough redundancy in the data set. It should be noted that
of the set-up are listed in table 1. a modal analysis has revealed the presence of three natural
Seven accelerometers which regularly span the beam are frequencies in the 0500 Hz range. This is relatively well
used to measure the response. The excitation force provided reflected by the cumulative sum of the singular values as
by an electrodynamic shaker is a white-noise sequence band- the first three singular values already account for 98.66% of
limited in the 0500 Hz range. Due to the thin beam part, the total energy. The remaining 1.34% may be attributed
the effect of gravity is not negligible. In order to reduce its to the (small) participation of the modes outside the excited
influence, a set-up in which the thin beam is vertical and the frequency range but also to the experimental noise.
shaker, located at position 3, excites the structure in a horizontal The next step is to estimate the UCL. To this end, the data
plane is considered. are partitioned into 28 different sets containing 2500 points
39
G Kerschen et al
Figure 6. The monitored angle. (a) Gain fault; (b) sensor failure.
40
Sensor validation using principal component analysis
Figure 7. Results of the isolation stage. (a) Gain fault; (b) sensor failure.
Figure 8. The monitored angle for a non-linear structural behaviour. (a) Gain fault; (b) sensor failure.
41
G Kerschen et al
42