Utilisation of artificial neural network for the analysis of interlayer shear properties/ Dirbtinio neuroninio tinklo naudojimas tarpsluoksniu slyties savyb?ms analizuoti/ Maksligo neiralo tiklu izmantosana starpslanu bides ipasibu analize/ Kunstlike narvivorkude kasutamine siduskihtide nihkeomaduste analuusil.
Raab, Christiane ; Halim, Abd El Halim Omar Abd El ; Partl, Manfred Norbert 等
1. Introduction
In order to organise data and to discover knowledge from data the
so called knowledge discovery techniques with artificial neuronal
networks (ANN) were introduced in the 1950s. According to Fayyad (Fayyad
et al. 1996; Miradi 2009) knowledge discovery is the nontrivial process
of identifying valid, novel, potentially useful, and ultimately
understandable patterns in data. ANN is a mathematical, computational
model that simulates the structure of biological neural networks. It
consists of an interconnected group of artificial neurons and process
information using a connectionist approach to computation (Haykin 1999).
The advantage of using ANN for modelling and data evaluation lies
in the fact that ANN is capable of processing large amounts of data
sets. ANN determines a model based on learning or training process, as
opposed to statistical analysis, when a model has to be developed by
regression. Furthermore, in most cases, it is unknown if the
relationship between the variables is linear or not. Therefore, ANN
being a non-linear statistical data modelling tool, has a clear
advantage over statistical linear regression analysis. Although ANN does
not deliver an equation it is utilised to determine most critical and
influencing variables. For many problems these influencing variables are
not known in detail or are not completely assessable. In case of multi
regression analysis (MRA), their knowledge is indispensable while ANN
has the potential to identify the most important ones. As opposed to
other areas in science and economy, where computational tools in the
field of artificial intelligence were used for discovering knowledge
from an increasing amount of data, this was rarely the case in pavement
engineering. Here, for a long period of time, data collection and
evaluation was rather based on empirical or statistical methods. In her
thesis, Miradi (Miradi 2009) performed an artificial intelligence based
knowledge discovery study of data on asphalt road pavement problems, in
particular, ravelling, cracking and rutting as well as stiffness of
cement treated bases. She showed that even without special knowledge in
asphalt pavement technology the correct use of artificial intelligence
tools leads to meaningful results and findings.
The aim of this paper is to apply ANN for knowledge discovery from
pavement interlayer bonding data covering a key issue in pavement
engineering. As opposed to Miradi's thesis (Miradi 2009) which
approached the problem of knowledge discovery for asphalt pavements from
a mathematical side, this paper deals with the practical application of
ANN. Hence, it focuses on the practical use of ANN and its application
for datasets on interlayer bonding for determining pattern within the
data and to predict certain interlayer bond properties.
2. Problem description
ANN is valuable empirical substitutes for conventional physical
models for analysing complex relationships involving multiple variables
provided that a sufficiently large database is available. The bond
between asphalt pavement layers is influenced by such a great variety of
different parameters or variables.
Clearly, the interlayer bond will depend on physical and mechanical
properties of the main constituents of the asphalt mixtures, the
geometrical, chemical and physical characteristics of the interface, the
mechanical properties of the pavement structure and the external factors
that affect the pavement structure itself, such as traffic and climate.
The characteristic values of the bond itself are also heavily dependent
on the way how they are determined, i.e. testing methods and conditions.
Table 1 presents a list of the variables which are expected to govern
the general behaviour of the bond. The list consists of 4 major variable
sets which includes more than 20 different main variables.
The number and complexity of parameters influencing interlayer
bonding makes it difficult to quantify the contribution of the different
parameters to the measured bonding properties and to find a physical
model predicting the interlayer shear bond properties such as max shear
force or max shear stiffness. Although the decrease of the interlayer
bond with increasing temperature is a well-known fact, the influence of
other factors (e.g. influence of tack coat, geometry of the interface
etc.) is either unknown to a full extent or intensely debated among
researchers and practitioners (Romanoschi, Metcalf 2002; Uzan et al.
1978; Ziari, Khabiri 2007).
Another reason for the fact that ANN has not yet been applied for
the evaluation of interlayer bonding is the lack of generally
acknowledged and openly accessible databases for interlayer bonding.
Furthermore, openly accessible databases are lacking interlayer bond
longterm performance data including information on traffic survey and
pavement condition data, since the evaluation of the shear bond between
asphalt layers is usually determined using cores, which are directly
taken after construction and before the road is opened to traffic.
3. Shear testing
Shear testing was done using the Layer-Parallel Direct Shear (LPDS)
test device (Fig. 1). LPDS is an Empa modified version of equipment
developed in Germany by Leutner being more versatile in geometry and
more defined in the clamping mechanism (Raab, Partl 2008).
The specimens were conditioned in a climate chamber for 8 h and all
tests were conducted at a temperature of 20 [degrees]C. From the LPDS
test the shear force F as a function of the vertical shear deformation w
is obtained.
Nominal maximal shear stress, i.e. the average shear stress in the
cross section, is obtained by dividing the max shear force by the cross
section area of the specimen.
[[tau].sub.max] = [[F.sub.max]/A] = [4[F.sub.max]/[d.sup.2][pi]],
(1)
where [F.sub.max] - maximal force, kN; A - nominal cross section
area, [mm.sub.2]; d - specimen diameter, mm.
In addition to the max shear force, the max slope is used to define
the max shear "stiffness" value [S.sub.max] as follows (Raab,
Partl 2008):
[S.sub.max] = [dF/[dw](F)] at [[d.sup.2]F/[dw.sup.3]] = 0 and
[[d.sup.3]F/[dw.sup.3]] < 0, (2)
where dF - differential shear force; dw - differential shear
deformation.
[FIGURE 1 OMITTED]
In order to compare "stiffness" for different specimen
diameters, the shear reaction modulus [K.sub.max] (Goodman et al. 1968)
is used:
[K.sub.max] = [d[tau]/dw([tau])] at [[d.sup.2][tau]/[dw.sup.2]] = 0
and [[d.sup.3][tau]/[dw.sup.3]] < 0, (3)
where d[tau] - differential shear stress; dw - differential shear
deformation.
4. Artificial neuronal networks in general
An ANN is a biologically inspired computational model consisting of
several single units, artificial neurons, connected with weighting
coefficients (Ghaffari et al. 2006). This system is capable of
recognizing, capturing and mapping patterns in a set of data due to the
high interconnections of neurons processing information in parallel. A
basic network is composed by three or more layers (Fig. 2). The first
layer contains the input data while the last layer contains the output
data. One or more layers known as hidden layers are placed between the
input and output layers. The arriving signals, called inputs, multiplied
by the connection weights are 1st summed and then passed through a
transfer function to produce the output for that neuron. The activation
function acts on the weighted sum of the neuron's inputs and the
most commonly used function are sigmoid and hyperbolic tangent function.
The way that the neurons are connected to each other has a significant
impact on the operation of the ANN (Martinez, Angelone 2010). The most
commonly used ANN is a feed forward ANN. In this type of ANN each
artificial neuron is only connected to the artificial neuron in the next
layer and its output is fed forward to the next layer in the direction
from input to output (Miradi 2009).
There are many different learning algorithms but the most common
one is the back propagation (Ghaffari et al. 2006). For back
propagation, two other parameters, the learning rate and the momentum
coefficient need to be defined. The learning rate is an adjustable
factor that controls the speed of the learning process. The momentum
coefficient determines the proportion of the last weight change that is
added to the new weight change. The following simplified relationship
presented by Erb (1993) points out the effects of these two parameters
on the weight adjustment:
new weight change = [eta] error + [beta] (last weight change), (4)
where [eta] - learning rate; [beta] - momentum coefficient.
An ANN is trained to map a set of input data by iterative
adjustment of the weights. There are two main approaches for weight
adjustment: online and batch. The online method modifies and updates the
weights for each input data, while the batch method computes the weight
update for each input data, but stores these values during one
repetition through the training set. At the end, after all input data
samples have been presented, all the contributions are added, and only
then the weights will be updated (Abraham 2005).
[FIGURE 2 OMITTED]
Information from input data is fed forward through the network to
optimize the weights between neurons. Optimization of the weights is
made by backward propagation of the error during training or learning
phase. The ANN reads the input and output values in the training data
set and changes the value of the weighted links to reduce the difference
between the predicted and target (observed) values. The error in
prediction is minimized across many training cycles until network
reaches specified level of accuracy (Ghaffari et al. 2006).
A basic architecture of an ANN with four neurons in the input
layer, three neurons in the hidden layer and one neuron in the output
layer is presented in Fig. 2.
5. Datasets
As explained earlier, no standard databases were available. The
datasets used for this research were gathered over the years by the
authors of this paper from two different research projects on in situ
data (Raab, Partl 1999, 2008). Data can be divided into those from new
pavements ("New Road") and performance data from old
pavements. "LTPP Road" is a dataset combination of data from
new pavements and performance data from the same roads after 10 years.
For both datasets the single results for max shear force, max shear
stress, shear deformation at max shear force and max shear stiffness
were determined.
5.1. New Road dataset
In the mid 1990s, the Swiss Federal Laboratories for materials
testing and research, Empa, was appointed by the Swiss Federal Road
Office (ASTRA) to evaluate a simple, practice oriented and standard able
test method for assessing the interlayer bond between the layers of
asphalt pavements (Raab, Partl 1999). The test method was intended as a
quality assurance (QA) tool for inspection immediately after pavement
construction. In the course of this research project, a number of Swiss
pavements, constructed between 1993 and 1997 were investigated,
providing a representative selection of materials for heavy vehicle
traffic roads during that period of time. In the course of the project
only the bond between the surface (layer 1) and the binder or base layer
(layer 2) should be evaluated.
Since the construction took place before the European Standards
became effective, all surface courses had been constructed according the
old Swiss Standard SN 640431a Asphalt Concrete, Conception and
Requirements (1988). Fig. 3 shows the location of all test sites in
Switzerland and Table 2 gives an overview of structures, mixtures and
LPDS testing temperature for all test sites.
The investigated asphalt pavements were either new constructions or
rehabilitations of layer 1 and layer 2. Therefore, all surface (layer 1)
and second layers (layer 2) apart from three binder courses and one
upper base layer were totally new.
[FIGURE 3 OMITTED]
Most pavement surface courses consisted either of mastic asphalt
(SMA) or asphalt concrete (AC): 9 road sections had SMA and 7 road
sections had AC surface courses (layer 1). In addition, three coring
sites with special surface courses, i.e. mastic asphalt (MA), hot-rolled
asphalt (HRA) and porous asphalt (PA) were included. The surface courses
were placed either on AC layers with a nominal max aggregate size of 10,
16, 22 or 32 mm or on MA with a max aggregate size of 16 mm each (layer
2).
The investigated asphalt pavements were either new constructions or
rehabilitations of layer 1 and layer 2. Therefore, all surface (layer 1)
and second layers (layer 2) apart from 3 binder courses and 1 upper base
layer were totally new. In two cases, pavements with new surface courses
on unknown old base and binder courses were investigated. According to a
binder extraction analysis in the lab, the mixture type of these unknown
layers was evaluated to be most probably AC 10 according to the Swiss
standard SN 640431 Asphalt Concrete, Conception and Requirements (1976).
It is important to note, that the composition of binder courses was
equal to the composition of base courses since at that time the Swiss
construction practise did not distinguish between binder and base
courses. In order to avoid confusion, all notations in Table 1 are
according to the new Swiss standard, SN EN 640430 Mastic Asphalt,
Conception and Requirements, 2008 for asphalt concrete and SN EN 640441
Mastic Asphalt, Conception and Requirements, 2008, for MA.
All new asphalt pavement mixes of layer 1 and layer 2 were analysed
in the laboratory determining aggregate size distribution, binder
content, Marshall values (stability, flow, air void content) and
standard binder properties (penetration, softening point ring and ball).
Furthermore, the air void content of the pavement layers (mean value)
and the tack coat type were determined. For this investigation, at each
test site, 40 cores were taken directly after construction of the
pavement or pavement rehabilitation. From these cores, interlayer shear
tests between the first and second layer were performed at 20 [degrees]C
and 40 [degrees]C using the LPDS shear device. In addition to the max
shear force, max shear stress, shear deformation at max shear stress and
max shear stiffness S were determined for all cores.
5.2. LTPP Road dataset
For a long time, apart from two preliminary investigations in 1999
and 2001 on a limited database (Raab, Partl 1999; Stockert 2001), little
performance data concerning interlayer bonding were available, until in
2003 Empa conducted a long term pavement performance study on the
evaluation of interlayer bonding over time.
Based on the research project from 1999 (Raab, Partl 1999) and the
results obtained from more than 1000 cores from 20 different pavements,
a decade later the long term bonding properties of remaining 14
pavements could be determined again. The bonding properties determined
at 20 [degrees]C with the LPDS of 14 remaining high volume road
pavements for the years 1993 to 1997 were compared to the values for the
same road pavements in 2006.
From the remaining pavements, seven had SMA and four AC surface
courses. All three coring sites with special surface courses, i.e. MA,
HRA and PA could also be included.
For most road sections the average daily traffic (ADT, vpd) and the
percentage of heavy vehicles (> 3.5 t) data were also available from
Swiss Traffic Survey of 2005 and from Swiss Federal Office of Statistics
of 2006.
Table 3 shows the remaining road sections with information on the
material and the traffic data.
Coring for the investigation of the long-term pavement performance
study was conducted a few meters away from the original coring site. For
every road section, 5 cores were taken inside and another 5 outside the
wheel track. From these cores interlayer shear tests between the first
and second layer were performed at 20 [degrees]C using the LPDS shear
device. In addition to the max shear force, shear stress and shear
deformation as well as shear stiffness and shear reaction modulus were
determined for all cores.
6. Data preparation
Before ANN calculations can be conducted, the available data have
to be prepared in terms of variable selection, data cleaning and data
scaling. In order to prepare the available datasets the input and output
variables have to be selected.
The following output variables were chosen:
- max shear force [F.sub.max], kN, which is converted into the max
nominal shear stress [[tau].sub.max], MPa;
- shear deformation at max shear stress w, mm;
- max shear stiffness [S.sub.max], kN/mm, which is converted into
the reaction modulus [K.sub.max], MPa/[mm.sup.2].
Input variable selection is a key step since the choice of the
variables influences the quality of the ANN model prediction. Sometimes
it is possible that a variable seems to be important for the ANN
software, while this importance can physically not be explained and is
opposed to findings in reality. Therefore, it is important to rely not
only on machine-aided search mechanisms, but also on experimental
knowledge and engineering judgement. Since the interlayer bond generally
depends on two different layers, all variables of the mixture and binder
characteristics and some variables of the pavement characteristics have
to be multiplied by a factor of two.
The input variable selection for ANN modelling of the databases was
conducted using a feature selection mode inbuilt in the applied ANN
software. When executing an exhaustive search, temperature, aggregates
passing through 2 mm and through 0.09 mm sieve of the second layer were
detected to be the most important variables for the New Road dataset
with a fitness of 56.1%, while the combination of all input variables
gained a fitness of 55.6%. It was therefore decided to take all 11 input
variables, since in this way more information could be retrieved using
the response graph feature.
The following additional input variables have to be taken into
account for the LTPP dataset:
- age, year;
- ADT, vpd;
- percentage of heavy vehicles > 3.5 t, %.
As opposed to the input variables for the New Road dataset the test
temperature had to be excluded, since all performance data for the LTPP
dataset were only determined for a temperature of 20 [degrees]C. The
binder contents for the layers were not included because their range was
very small and, therefore, their evaluation did not give valuable
information. The air void content was also neglected because the values
for the LTPP Road were not comparable to the values of New Road. In the
LTPP investigation air voids had been determined for every single core,
while for New Road the air void content represents a global value for
the whole pavement. Table 4 depicts all input variables for the New Road
and the LTPP Road dataset.
Another step in data preparation is data cleaning. Therefore the
datasets are not allowed to contain missing data and outliers. In cases
of missing output data, the whole row of data was eliminated in this
research. In some cases, output data were only missing for one output
parameter (such as shear stiffness). In this case, the data line was
eliminated for the evaluation of shear stiffness while it was used for
the evaluation of shear force and shear deformation. In case of missing
input data (variables) it depended whether it was possible to insert
data using values known from standards or guidelines, such as, mixture
characteristics or traffic data, or whether the whole line of data was
eliminated. Wrong type values resulting from human error were either
corrected or eliminated. Outliers are extreme cases such as, measurement
errors or other anomalies. Hence, each single outlier was examined and
it was decided to use or to eliminate the data. The applied software
often detected values for extreme cases and characterised them as
outliers. Here, it was decided to accept these data (e.g. high binder
and low air void content in case of mastic asphalt) when the given data
were consistent with reality and then included in the evaluation. In
other cases, unreasonably high or low data were either corrected when
the correct value was available or eliminated when this was not the
case.
After data cleaning data scaling is done. This is a procedure which
allows eliminating any incompatibility of data caused by the different
measurement units, which affects the accuracy of the model. Data scaling
was done within a range of [-1, 1] using Eqs (4-5):
SF = [(S[R.sub.max] - S[R.sub.min])/([x.sub.max] - [x.sub.min])]
(4)
[x.sub.s] = S[R.sub.min] + (x - [x.sub.min])SF, (5)
where SF - scaling factor; S[R.sub.max] - upper scaling range
limit; S[R.sub.min] - lower scaling range limit; x - actual numerical
value; [x.sub.max] - max actual value; [x.sub.min] - min actual value;
[x.sub.S] - scaled value.
Before ANN modelling, the dataset is divided in two subsets, the
training and the test set. The training set, about 85% of the dataset,
is used for training and the test set, about 15% of the data, is used
for testing the evaluated model. The software used in this research
divides each dataset into three subsets: the training set, the
validation set and the test set. The training set is a part of the input
dataset used for neural network training, i.e. for the adjustment of
network weights. The validation set is a part of the data used to tune
network topology or network parameters other than weights. For example,
it is used to define the number of hidden units or to detect the moment
when the neural network performance started to deteriorate. The
validation set is used for calculating generalisation loss and retaining
the best network (the network with the lowest error on validation set).
The test set is a part of the dataset used only to test how well the
neural network will perform on new data. The test set is used after the
network is ready trained, to test what errors will occur during future
network application. The test set is not used during training and thus
was considered as new data entered by the user for the neural network
application. It was also decided to separate a part of the dataset
(about 10% of the data) to have an additional test set, the so called
query set, which was used to query and validate the determined network.
This was done prior to feeding the datasets into the ANN modelling
process, which means that several lines of data were excluded and put
together in the query set file.
7. Modelling using ANN
7.1. New Road
For all three output parameters the same number of hidden layers
was used. Since it was found that the result did not differ too much
when using different numbers of hidden neurons, the min number 5, which
gave a good prediction, was used. Batch back propagation learning
algorithms with a learning rate of [eta] = 0.2 and a momentum
coefficient of [beta] = 0.9 was found to give the best results for the
prediction of all three output parameters. The hyperbolic tangent was
chosen as the activation function for both, hidden layer and output
layer.
From Figs 4-6 it becomes clear that for the output variable max
shear force [F.sub.max] and max shear stiffness Smax a good prediction
is possible, while the ANN computation of the output variable, shear
deformation w at [F.sub.max], does not lead to a model, which is able to
predict its values in a sufficient way. In case of the output variables
force and stiffness the linear regression coefficients values [R.sup.2]
of 0.96 and 0.85 give a good prediction of [F.sub.max] and [S.sub.max]
and the slopes of the regression lines are close to 1.
Regarding the output variable shear deformation w at Fmax a linear
correlation in the form y = ax + b with b = 0 and therefore a prediction
of the values is not possible.
7.2. LTPP road
Again, for all three output parameters the same number of hidden
layers was used. Since it was found that the result did not differ too
much when using different numbers of hidden neurons, the min number 5,
which gave a good prediction, was used. Batch back propagation learning
algorithms with a learning rate of [eta] = 0.4 and a momentum
coefficient of [beta] = 0.9 was found to give the best results for the
prediction of all three output parameters. The hyperbolic tangent was
chosen as the activation function for both, hidden layer and output
layer.
Figs 7-9 give the result of ANN modelling and show the prediction
for the output variables using the query files for validating the
determined network.
[FIGURE 4 OMITTED]
[FIGURE 5 OMITTED]
[FIGURE 6 OMITTED]
The findings for the LTPP dataset are similar. For the output
variable [F.sub.max] and [S.sub.max] a prediction is possible with
[R.sup.2] values of 0.75 and 0.74. For this database even the prediction
for the output variable shear deformation w at [F.sub.max] is possible,
although the [R.sup.2] value with 0.52 is clearly not very high. This
finding can be contributed to the fact that with age the deformation at
[F.sub.max] becomes smaller and the distinction between the new and aged
values becomes clearer.
[FIGURE 7 OMITTED]
[FIGURE 8 OMITTED]
[FIGURE 9 OMITTED]
For the linear regression the findings are similar. For all
regression lines a slope very close to 1 is found, although the linear
regression coefficients [R.sup.2] are not high. For [F.sub.max] and
[S.sub.max] they receive values of 0.66 for training and 0.72 for
testing. In case of the shear deformation at [F.sub.max], [R.sup.2] is
very low (0.09 for training and 0.22 for testing).
It is interesting to note, that in the LTPP data, as opposed to the
New Road data, a weak correlation for the max shear deformation at
[F.sub.max] can be found. This correlation might be attributed to the
fact that in case of LTPP data, overall the shear deformation data are
lying within a less wide range and the amount of similar or comparable
data (new/old) increased.
Similar statements are made for LPTT dataset (Figs 8-10). However,
here [F.sub.max] and [S.sub.max] show only weak correlations with
[R.sup.2] values of 0.58 and 0.67, while the [R.sup.2] of the linear
correlation for the shear deformation is only 0.50, partly due to the
fact that, for physical reason again, the regression line was forced
through the origin of the axis. On the other hand, the slope of the
linear regression line was for all output variables close to 1. That the
prediction for LTPP Road is not so good compared to New Road is
explained by the fact that LTPP Road is a combination of two datasets
which differ regarding the time of testing.
8. Discussion
The applied software offers the possibility to analyse ANN results
by using the so-called response graphs. The response graph displays the
response of the model output by varying one of the variables, while
keeping the other input variables constant. The constant value for each
variable is the mean value of that variable in the dataset.
Fig. 10 gives the response graphs for New Road showing the input
variables "Temperature" and "Air void content of layer 1
and layer 2". It was decided to show the response graphs for
[F.sub.max] and [S.sub.max] since here physical dependencies are known
best.
[FIGURE 10 OMITTED]
[FIGURE 11 OMITTED]
As shown in Fig. 10a, the [F.sub.max] and [S.sub.max] decrease with
increasing temperature from 20 [degrees]C to 40 [degrees]C. The same
applies for the [F.sub.max] and [S.sub.max] with increasing air void
content of layer 1 (Fig. 10b).
The situation gets different, for the air void content of layer 2,
where an increase in air void content goes with an increase of
[F.sub.max] and [S.sub.max] (Fig. 10c). While the first two findings are
in agreement with practical experience, the finding that the shear force
increases with increasing air void content of layer 2 is debatable.
Here, the range of air void content is probably too small for
determining a clear dependency and one has to keep in mind that the
increase in shear force is also quite small. Regarding the air void
content (Fig. 10b), another explanation is found in the difference
between layer 1 and layer 2. The difference in air void content of the
layer 1 is mainly based on differences in the asphalt concept, with
mastic asphalt having very low air void content on the one hand and
porous asphalt having very high air void content on the other hand. The
air void content of the layer 2 lies within a clearly defined range
since these layers are all constructed according to the concept of
asphalt concrete. In case of the air void content of layer 2, other
effects of roughness and interlock could be dominant. Fig. 11 gives the
response graphs for LTPP Road showing the input variables ADT, vehicles
> 3.5 t and age.
As shown in Fig. 11a, the shear force decreases with increasing
ADT. The same applies for increasing percentage of heavy vehicles (Fig.
11b). The situation gets different, when looking at the age, where an
increase in operation time of 10 years leads to an increase of shear
force and shear stress (Fig. 11c). The findings for the ADT, the
percentage of heavy vehicles and the age are in agreement with practical
experience.
The results in a paper by Raab (Raab, Partl 2008) clearly states
that while the nominal [F.sub.max] of intact pavements increases with
age or operation time, very high levels of average daily traffic and
high percentages of heavy vehicles can lead to pavement deterioration
combined with a decrease in shear force and shear stress. In this
investigation it was found that very high levels of average daily
traffic and high percentages of heavy vehicles can cause damage to the
pavement, which results in a decrease of shear forces and stresses
mainly in the wheel path. In most cases pavement deterioration is
visible (ruts, cracks), but when the pavement is subjected to very high
levels of ADT over a long period of time, shear properties were found to
decrease without the pavement showing visible defects.
9. Conclusions
The results presented in this paper support the following
conclusions:
1. ANN techniques are a valuable tool to derive models from
datasets and to predict interlayer shear bond properties such as max
shear force, deformation at max shear stress, and max shear stiffness.
2. The prediction of quality and accuracy of various interlayer
bond properties is different. Max shear force and shear stress are
predicted best, followed by max shear stiffness, while shear deformation
at max shear stress is a less representative of the bond property.
3. Engineering judgement and practical knowledge are indispensable
when choosing the important variables for using the artificial neuronal
networks technique. Therefore, plausibility checks are necessary.
4. According to the findings of this research, it is recommended to
create additional independent query test files. In order to have the
most reliable output, the data for these query files must be chosen
randomly, but taking into account every investigated characteristic,
such as different materials, different temperatures or intermediate
layers etc.
5. Regarding New Road dataset the best predictions was found for
the output parameter "max shear force" followed by the
"max shear stiffness" with linear regression coefficient
values [R.sup.2] of 0.94 and 0.85 for the query test set. A prediction
for the max shear deformation was not possible, since the deformation
data seemed to be too diverse within the database.
6. The response graphs for "temperature" and "air
void layer 1" the predicted max shear forces are in good agreement
with practical experience, and findings from other research, while for
"air void layer 2" a connection with practical experience was
more difficult.
7. For LTPP Road dataset, a combination of New Road with its
performance data a prediction of max shear force and max shear stiffness
is not as accurate as for the New Road dataset. This results in linear
regression coefficient values [R.sup.2] of 0.58 and 0.62. The prediction
for the shear deformation even becomes better than for New Road dataset
([R.sup.2] = 0.42).
8. The response graphs for LTPP Road dataset for the prediction of
the max shear force support findings that aging and trafficking has a
positive effect on the max shear force, while the pavement deteriorates,
leading to a decrease in shear force when the average daily traffic and
the percentage of heavy vehicles becomes very large.
Caption: Fig. 1. LPDS test device, schematic drawing (Raab, Partl
2008)
Caption: Fig. 2. Schematic of a three layer ANN with four neurons
in the input layer, three neurons in the hidden layer and one neuron in
the output layer (Miradi 2009)
Caption: Fig. 3. Location of Swiss test sites (Raab, Partl 1999)
Caption: Fig. 4. Prediction of [F.sub.max] for independent query
test dataset
Caption: Fig. 5. Prediction of w at [F.sub.max] for independent
query test dataset
Caption: Fig. 6. Prediction of [S.sub.max] for independent query
test dataset
Caption: Fig. 7. Prediction of [F.sub.max] for independent query
test dataset
Caption: Fig. 8. Prediction of w at [F.sub.max] for independent
query test dataset
Caption: Fig. 9. Prediction of [S.sub.max] for independent query
test dataset
Caption: Fig. 10. Response graphs of the input variables as a
function of [F.sub.max] and [T.sub.max]: a--temperature; b--air void
content layer 1; c--air void content layer 2
Caption: Fig. 11. Response graphs of the input variables as a
function of [F.sub.max] and [T.sub.max]: a - ADT; b - vehicles > 3.5
t; c--age
doi: 10.3846/bjrbe.2013.14
Received 3 May 2011; accepted 5 July 2011
References
Abraham, A. 2005. Artificial Neural Networks, in Handbook of
Measuring System Design. Ed. by Sydenham, P.; Thorn, R. John Wiley &
Sons, 1648 p. ISBN: 0470021438.
Erb, R. J. 1993. Introduction to Backpropagation Neural Network
Computation, Pharmaceutical Research 10(2): 165-170.
Fayyad, U.; Piatetsky-Shapiro, G.; Smyth, P. 1996. From Data Mining
to Knowledge Discovery in Databases, American Association for Artificial
Intelligence 17(3): 34-54.
Ghaffari, A.; Abdollahi, H.; Khoshayand, M. R.; Soltani Bozchalooi,
I.; Dadgar, A.; Rafiee-Therani, M. 2006. Performance Comparison of
Neural Network Training Algorithms in Modeling of Bimodal Drug Delivery,
International Journal of Pharmaceutics 327(1-2): 126-138.
http://dx.doi.org/10.1016/j.ijpharm.2006.07.056.
Goodman, R. E.; Taylor, R. L.; Brekke, T. L. 1968. A Model for the
Mechanics of Jointed Rock, Journal of the Soil Mechanics and Foundations
Division 94(3): 637-659.
Haykin, S. 1999. Neural Networks: a Comprehensive Foundation. 2nd
edition.
Prentice Hall. ISBN: 0139083855. 842 p.
Martinez, F.; Angelone, S. 2010. The Estimation of the Dynamic
Modulus of Asphalt Mixtures Using Artificial Neural Networks, in Proc.
of the 11th International Conference on Asphalt Pavements. August 1-6,
2010, Nagoya, Aichi, Japan.
Miradi, M. 2009. Knowledge Discovery and Pavement Performance. PhD
thesis. University of Technology, Delft.
Partl, M. N.; Raab, C. 1999. Shear Adhesion between Top Layers of
Fresh Asphalt Pavements in Switzerland, in Proc. of the 7th Conference
on Asphalt Pavements for Southern Africa (CAPSA'99). 29 August-2
September, 1999, Victory Falls, Zimbabwe, South Africa. 5.130-5.137.
Raab, C.; Partl, M. N. 2008. Investigation on Long-Term Interlayer
Bonding of Asphalt Pavements, The Baltic Journal of Road and Bridge
Engineering 3(2): 65-70.
http://dx.doi.org/10.3846/1822-427X.20083.65-70.
Raab, C.; Partl, M. N. 1999. Methoden zur Beurteilung des
Schichtenverbunds von Asphaltbelagen [Methods to Determine the Bond of
Asphalt Pavements]. Report No. 442. ASTRA, Switzerland. 118 p.
Romanoschi, S. A.; Metcalf, J. B. 2002. The Characterization of
Pavement Layer Interfaces [CD-ROM], in Proc. of the 9th International
Conference on Asphalt Pavements (ISAP). August 17-22, 2002, Copenhagen,
Denmark.
Stockert, U. 2001. Schichtenverbund--Prufung und
Bewertungshintergrund [Interlayer Bonding -Testing and Assessment
Background], Strafie+Autobahn [Road and Motorway] 11: 624-631.
Uzan, J.; Livneh, M.; Eshed, Y. 1978. Investigation of Adhesion
Properties between Asphaltic Concrete Layers, Journal of the Association
of Asphalt Paving Technologist 47: 495-521.
Ziari, H.; Khabiri, M. M. 2007. Interface Condition Influence on
Prediction of Flexible Pavement Life, Journal of Civil Engineering and
Management 13(1): 71-76.
http://dx.doi.org/10.1080/13923730.2007.9636421.
Christiane Raab (1) ([mail]), Abd El Halim Omar Abd El Halim (2),
Manfred Norbert Parti (3)
(1,3) Empa Swiss Federal Laboratories for Materials Testing and
Research, CH-8600 Dubendorf, Switzerland
(2) Dept of Civil and Environmental Engineering, Carleton
University, 1125 Colonel by Drive, K1S 5B6 Ottawa, ON, Canada
E-mails: (1) christiane.raab@empa.ch; (2) a.halim@carleton.ca; (3)
manfred.partl@empa.ch
Table 1. List of general variables influencing the interlayer bond
of asphalt pavements
Characteristics Shear testing
Mixture Binder Pavement condition
Mixture type Binder type Type of pavement Temperature
Nominal max Penetration Layer thickness Deformation rate
aggregate
size
Aggregate Softening Air void content Specimen size
gradation Point
R + B
Binder content SHRP values Tack coat Test configuration
Stiffness Age
Air void Location in the
content pavement
Traffic
Environmental
conditions
Construction
conditions
Table 2. New road pavements
Site Material LPDS testing temperature
No. layer 1 layer 2 20[degrees]C 10[degrees]C
1 SMA 11 AC 22 X X
2 SMA 11 AC 32 X X
3 SMA 11 AC 32 X X
4 SMA 11 AC 22 X X
5 SMA 11 AC 22 X X
6 SMA 11 AC 16 X X
7 SMA 11 AC 22 X X
8 SMA 11 AC 32 X -9
SMA 11 AC 16 X X
10 AC 11 AC 32 X X
11 HRA 11 AC 22 X X
12 MA 11 MA 16 X X
13 PA 11 AC 16 X X
14 SMA 11 AC 22 X -15
AC 11 AC 32 X X
16 AC 11 AC 22 X -17
AC 11 AC 22 X -18
AC 16 AC 10 X -19
AC 16 AC 10 X -20
AC 11 AC 16 X -
Table 3. Remaining road pavements in 2006 and traffic data
Site Material Traffic
No. layer 1 layer 2 ADT, vpd > 3.5 t, %
2 SMA 11 AC 32 not available buses
3 SMA 11 AC 32 18 300 9.8
5 SMA 11 AC 22 32 700 7.6
6 SMA 11 AC 16 94 990 4.4
7 SMA 11 AC 22 19 800 4.4
8 SMA 11 AC 32 31 500 5.5
10 AC 11 AC 32 77 890 11.1
11 HRA 11 AC 22 9800 2.6
12 MA 11 MA 16 32 700 7.6
13 PA 11 AC 16 31 500 4.6
14 SMA 11 AC 22 28 050 5.8
15 AC 11 AC 32 64 230 8.2
18 AC 16 AC 10 not available not available
19 AC 16 AC 10 not available not available
Table 4. Input variables for New Road and LTPP Road datasets
Input variables New Road Input variables LTPP Road
Temperature, T
Void 1, void content of layer 1
Void 2, void content of layer 2 Age
Binder 1, binder content of ADT
layer 1
Binder 2, binder content of Percentage of heavy vehicles
layer 2 > 3.5 t
Aggregate passing through Aggregate passing through
sieve 8 mm, layer 1 sieve 8 mm, layer 1
Aggregate passing through Aggregate passing through
sieve 8 mm, layer 2 sieve 8 mm, layer 2
Aggregate passing through Aggregate passing through
sieve 2 mm, layer 1 sieve 2 mm, layer 1
Aggregate passing through Aggregate passing through
sieve 2 mm, layer 2 sieve 2 mm, layer 2
Aggregate passing through Aggregate passing through
sieve 0.09 mm, layer 1 sieve 0.09 mm, layer 1
