Automation in Construction 45 (2014) 50–65

Contents lists available at ScienceDirect

Automation in Construction
journal homepage: www.elsevier.com/locate/autcon

Artificial neural network models for predicting condition of offshore oil

and gas pipelines
Mohammed S. El-Abbasy a,⁎, Ahmed Senouci b, Tarek Zayed a, Farid Mirahadi a, Laya Parvizsedghy a
a
Dept. of Building, Civil and Environmental Engineering, Concordia University, Montreal, Quebec, Canada
b
Dept. of Civil and Environmental Engineering, Qatar University, Doha, Qatar

a r t i c l e i n f o a b s t r a c t

Article history: Pipelines daily transport and distribute huge amounts of oil and gas across the world. They are considered the
Received 10 August 2013 safest method of transporting oil and gas because of their limited number of failures. However, pipelines are
Revised 17 March 2014 subject to deterioration and degradation. It is therefore important that pipelines be effectively monitored to
Accepted 3 May 2014
optimize their operation and to reduce their failures to an acceptable safety limit. Numerous models have been
Available online 22 May 2014
developed recently to predict pipeline conditions. Nevertheless, most of these models have used corrosion
Keywords:
features alone to assess the condition of pipelines. Hence, this paper presents the development of models that
Offshore oil and gas pipelines evaluate and predict the condition of offshore oil and gas pipelines based on several factors besides corrosion.
Condition prediction The models were developed using artificial neural network (ANN) technique based on historical inspection
Artificial neural network data collected from three existing offshore oil and gas pipelines in Qatar. The models were able to successfully
predict pipeline conditions with an average percent validity above 97% when applied to the validation data set.
The models are expected to help pipeline operators to assess and predict the condition of existing oil and gas
pipelines and hence prioritize the planning of their inspection and rehabilitation.
© 2014 Elsevier B.V. All rights reserved.

1. Introduction pressure or system malfunction; and 5) natural events such as land-

Pipelines remain a reliable means of transporting products vital to the
sustenance of national economies in the world such as water, oil, and gas
[11]. The first oil pipeline, which was built in 1879 in Pennsylvania, was
109 miles long and 6 in. in diameter [21]. Nowadays more than 60
countries have pipeline networks exceeding 2000 km in length. The
United States has the longest pipeline network followed by Russia [17].
Gas and oil pipelines are subject to deterioration and degradation.
Pipeline accidents can cause catastrophic environmental damage due
to oil spillage as well as economic losses due to production interruption
[12]. Several types of accidents of oil and gas pipelines have been
recorded in the CONCAWE (CONservation of Clean Air and Water in
Europe) report [9]. They are most frequently classified in five cause cat-
egories: 1) third party, which represents a damage caused by operations
carried out by others in the pipeline vicinity and not related to its man-
agement; 2) corrosion, which consists of an inside corrosion related to
the product being transported and an outside corrosion related to the
pipeline coating and cathodic protection; 3) mechanical, which consists
of fractures or cracks occurring when efforts go beyond the efforts of the
system permits; 4) operational error, which is caused by excessive
⁎ Corresponding author.
E-mail addresses: msksia@yahoo.com (M.S. El-Abbasy), a.senouci@qu.edu.qa
(A. Senouci), zayed@encs.concordia.ca (T. Zayed), faridmirahadi@gmail.com (F. Mirahadi),
l.sedghy@yahoo.com (L. Parvizsedghy).
slides, floods, erosion in general, subsidence, earthquakes, frost or light-
ning. It is therefore important that the condition of pipelines is
effectively monitored to optimize their operation and reduce their fail-
ures to an acceptable safety limit.
Most of the developed condition assessment models are either sub-
jective (i.e., depending only on expert opinion considering no historical
data), or not comprehensive (i.e., dealing with only one failure cause).
Therefore, the objective of this research is to develop a more compre-
hensive condition assessment model that allows pipeline operators to
take the necessary actions to prevent future catastrophic failures.
2. Research objectives
The main objectives of the present study are to design a condition as-
sessment and prediction models and develop expected deterioration
curves for offshore oil and gas pipelines.
3. Background
Various attempts have been carried out in the last two decades for oil
and gas pipelines' leakage, defect type, corrosion rate, failure type, and
failure probability predictions. Ren et al. [30] applied back propagation
neural network to predict the corrosion rate of natural gas pipelines.
Particle swarm optimization (PSO) technique was employed by Liao
et al. [23] to develop a model that predicts internal corrosion rate for

http://dx.doi.org/10.1016/j.autcon.2014.05.003
0926-5805/© 2014 Elsevier B.V. All rights reserved.
 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65
wet gas gathering pipelines. The model was also developed using genet-
ic algorithm (GA) and ANN techniques which outperformed the PSO.
Dawotola et al. [10] developed a rupture risk management model for
crude oil pipelines using a methodology that incorporates structured
expert judgment and analytic hierarchy process (AHP). Noor et al. [27]
used semi-probabilistic and deterministic methodologies to predict
the remaining strength of submarine pipelines subjected to internal
corrosion. Bersani et al. [4] developed a risk assessment model using
historical data from the United States Department of Transportation
(DOT) to predict the failure caused by third party activity. Historical fail-
ure data was also used to develop a tool to predict the class of each spill-
age in oil pipelines using statistical analysis classification and regression
tree [5]. Li et al. [22] presented a method to predict the corrosion and the
remaining life of underground pipelines using a mechanically-based
probabilistic model that considers the effect of randomness in pipeline
corrosion using Monte Carlo simulation technique. Singh and Markeset
[33] presented a proposed methodology, based on fuzzy logic frame-
work, for the establishment of a risk-based inspection program for pipe-
lines according to the estimation of its corrosion rate. Peng et al. [28]
developed a fuzzy neural network model, which is based on failure
tree and fuzzy computing, to predict the rate of failure for oil and gas
pipelines. Dawotola (2009) [41] proposed a combined AHP and Fault
Tree Analysis to support the design, the construction, and the inspection
and maintenance of oil and gas pipelines by proposing an optimal selec-
tion strategy based on the probability and consequence of failure. Jinhai
et al. [19] proposed a leak fault-detection method based on the combi-
nation of Rough Set (RS) and ANN, called hybrid fault-detection method
based on RS and ANN (HFDMRSNN). Carvalho et al. [7] used the ANN
technique for pattern recognition of magnetic flux leakage (MFL) sig-
nals in weld joints of pipelines obtained by intelligent pig to distinguish
the presence of defects and their type. AHP was used by Dey [12] to de-
velop a model to help decision makers select a suitable type of inspec-
tion or monitoring technique for pipelines. Hallen et al. [18] presented
a probabilistic analysis framework to evaluate the condition of a corrod-
ing pipeline and the evolution of its probability of failure with time.
Sinha and Pandey [34] developed a simulation-based probabilistic
fuzzy neural network model to estimate the failure probability of
aging oil and gas pipelines due to corrosion. Ahammed [1] presented a
methodology to assess the remaining service life of a pressurized pipe-
line containing active corrosion defects. Belsito et al. [3] developed a
leakage detection system for liquefied gas pipelines using ANN for
leak sizing and location.
Most of the previously-mentioned models were either subjective
[10,12] or did not cover all the failure causes of oil and gas pipelines
[1,4,18,22,23,26,27,30,33,34]. In other words, they lack the objectivity
in predicting the different failure types of pipelines. As a result, Senouci
et al. [31] developed a regression and artificial neural network (ANN)
models to predict possible failure types for oil and gas pipelines. The
model took into consideration the prediction of failure types beside cor-
rosion, such as mechanical, third party, natural hazard, and operational
failures. The model was built based on a historical data collected from a
report that was prepared by CONCAWE [9]. Later, [32] developed
another model for the same purpose using fuzzy logic technique and
compared the results with those obtained using the regression and
ANN models developed by Senouci et al. [31]. The results comparison
showed that the developed fuzzy-based model outperformed the
regression and ANN models with respect to model validity.
Despite the attempts made to predict the failure type of oil pipelines
considering causes other than corrosion, still none of the previously-
mentioned models can be used to assess the condition of pipelines.
Actually, such models were intended to either predict the corrosion
rate, pipe leakage, or failure/defect type focusing mostly on corrosion
related factors. In addition to that, the important issues of “interdepen-
dency” between different factors' relations and “uncertainty” of factors'
severity weights were not addressed simultaneously. Furthermore,
none of the previous studies developed models that can forecast the
51
deterioration rate of oil and gas pipelines and hence can build up their
respective deterioration curve. Consequently, El-Abbasy et al. [14] de-
veloped a model that assesses the condition of oil and gas pipelines
based on several factors including corrosion using both Analytic Net-
work Process (ANP) and Monte-Carlo simulation. The model considered
factors' interdependency (using ANP), made decisions under uncertain-
ty (using simulation), and handled decisions involving large number of
variables (using integrated simulation/ANP). It was successfully tested
on an existing offshore gas pipeline in Qatar by comparing the results
obtained using the model with the actual pipeline condition.
The simulation model built by El-Abbasy et al. [14] is considered as a
first phase to evaluate or assess the condition of offshore oil and gas
pipelines. Two major limitations were found in the study conducted
by El-Abbasy et al. [14]. First, the factors that were used to predict the
pipeline condition were not sufficient due to the lack of collected data.
The factors related to the pipeline structural condition were also not
considered. Second, the model was developed and tested using inspec-
tion data for a single 12-inch gas pipeline. The limited historical inspec-
tion data did not allow the examination of the effect of changing
the pipe diameter or the type of the transported product on the devel-
oped model. Moreover, the limited inspection data did not allow the
development of sound deterioration curves for oil and gas pipelines.
To overcome the above limitations, an extensive data collection was
performed in a study conducted by El-Abbasy et al. [15] where seven
historical inspection data seta were collected for three different
pipelines with several sizes (i.e. diameters), materials, and types of the
carried product. Four factors were considered in addition to those
presented in the previous study [14]. The additional factors included
the “anode wastage” and three factors related to the pipeline structural
condition namely, “support condition”, “joint condition”, and “free
spans”. The regression analysis technique was used to correlate be-
tween all these factors using the gathered data. The developed models
were validated yielding an average validity percentage above 96%. In
addition, the study proposed a standard condition assessment scale
or rating system for oil and gas pipelines. This rating system can be
used as a guideline to decide and plan the maintenance of pipelines
(i.e., lining, cathodic protection, replacement, etc.) and to prioritize
rehabilitation/upgrading projects within the approved budget.
Although the study conducted by El-Abbasy et al. [15] provided
sound results, the use of the regression analysis technique as a machine
learning algorithm has still some limitations. Several other machine
learning algorithms can be used to predict pipeline condition including
ANN, Support Vector Machine (SVM), Naïve Bayes (NB), Decision Trees
(DT), Random Forest (RF), and K-Nearest Neighbor (K-NN). Although
ANN is considered one of the oldest methods, it is still found to be a
competitive algorithm among the new ones. For instance, Tahyudin
et al. [36] compared the performance of SVM, DT, ANN, NB, and Logistic
Regression (LR) to predict the graduation students on time. The results
showed that ANN and SVM were the best predictors with an accuracy
rate almost 100%. Caruana and Niculescu-Mizil [6] carried out a compar-
ison between ten supervised learning algorithms being applied on
eleven binary classification problems using eight performance metrics.
It was found that the ANN was among the top five best algorithms.
Other studies showed the outperformance of the ANN technique.
Mohana and Thangaraj [24] showed that ANN is better than SVM for
modelling resource state prediction. Prabhakar [29] also showed the
better performance of ANN over SVM in predicting software effort.
Mollazade et al. [25] compared four different learning algorithms,
namely, ANN, SVM, DT, and Bayesian Network (BN) for grading raisins
based on visual features. Results of validation stage showed ANN had
the highest classification accuracy, 96.33%. After ANN, SVM with poly-
nomial kernel function (95.67%), DT with J48 algorithm (94.67%) and
BN with simulated annealing learning (94.33%) had higher accuracy,
respectively. On the contrary, Folorunsho [16] used medical dataset to
predict the diabetes probability of any patient using ANN and DT. It
was found that DT outperformed ANN with a lower error metrics and
52 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65

higher correlation coefficient. Such learning algorithms were also ap- START

plied in fields that are relevant to our study, i.e. pipe condition monitor-
ing. Kalanaki and Soltani [20] developed a break rate prediction models
for water pipes using SVM. Performance results were compared with LITERATURE REVIEW
continuous genetic algorithm-based support vector regression (SVR-
GA), continuous ant colony algorithm-based SVR (SVR-ACO), PSO- DATA COLLECTION
based SVR (SVR-PSO), ANN, and adaptive neuro-fuzzy inference sys-
tems (ANFIS). The results revealed the outperformance of using SVM
as a machine learning algorithm. On the other hand, Tabesh et al. [35]
assessed pipe failure rate and mechanical reliability of water distribu- Identify Factors Collect Historical
tion networks using ANN, ANFIS, and Nonlinear Regression (NLR) Affecting Oil and Gas Inspection Data for
where the results indicated the robustness of using ANN over the Pipeline Condition Oil/Gas Pipelines
other methods.
Select
Based on the above, it is quite clear that there is no a specific ma- Compatible
Factors
chine learning algorithm have an absolute outperformance over the
other. In other words, some algorithms may perform clearly better or
worse than the others depending on the problem nature as well as the MODEL DEVELOPMENT
data format. While a given machine learning approach may be easier
to implement for a given problem, or more suited to a particular data
format, to tackle difficult problems what matters in the end is the exper-
Three models with respect to Two models with respect to
tise a scientist has in a particular machine learning technology. What

Modify Models
diameter & product type product type only
can be obtained with a general-purpose machine learning method can
be achieved using another general-purpose machine learning method,
provided the learning architecture and algorithms are properly crafted
[8]. As a result, it was decided in this study to use ANN to develop con- MODEL TESTING & VALIDATION
dition prediction models for oil and gas pipelines. The main advantage
of ANN is related to the capability for learning from specific predefined
patterns. The learning capacity may include classification, prediction, Models No
and controlling of any specific task. Besides that, ANN provides two Successful?

major advantages over the regression analysis technique which have

been used by El-Abbasy et al. [15] to predict oil and gas pipeline condi- Yes

tion. First, ANN has the ability to detect implicitly any complex nonlin- DETERIORATION CURVES
ear relationships between independent and dependent variables [38].
If a significant amount of nonlinearity between the predictor variables
and the corresponding outcomes is present in a training data set, the END

network will adjust the connection weights to reflect these nonlinear-

ities. The predictor variables in a neural network usually undergo a non-
Fig. 1. Research methodology.
linear transformation at each hidden node and output node. Therefore, a
neural network can potentially model much more complex nonlinear
relationships than a logistic regression model can. Empirical observa-
dataset were not available in the factors identified previously. As a re-
tions suggest that when complex nonlinear relationships are present
sult, the compatible factors as well as the additional factors in the in-
in data sets, neural network models may provide a tighter model fit
spections dataset were selected to develop the condition prediction
than conventional regression techniques [37]. Second, the hidden
models.
layer of a neural network gives it the power to detect interactions or
Five condition prediction models were developed, namely, three
interrelationships between all of the input variables. When important
models with respect to the pipeline size (i.e. diameter) and the
interactions exist and are not modeled explicitly in a logistic regression
transported product type (i.e., oil or gas) and two models with respect
model, then a neural network model may be expected to predict a
to the type of the transported product only. The details and framework
particular outcome better than a logistic regression model.
of the model development using the ANN technique will be explained
Hence, in an attempt to enhance pipeline condition prediction pro-
later. The models were then tested, validated, and compared with previ-
cess, this paper presents new condition prediction models using the
ously developed models. Finally, a sensitivity analysis was carried out to
ANN technique. The performance of the models are then compared
develop different deterioration curves by examining the degree of the
with those developed using the regression analysis technique [15].
individual impact of each factor on the pipeline condition.

4. Research methodology
The developed methodology, which is shown in Fig. 1, started by
performing a brief literature review to search for the different tech-
niques and studies used by researchers for the condition assessment
of oil and gas pipelines. After that, a comprehensive data collection
was performed to in two different stages. The first stage was concerned
with the identification of the factors needed to increase the efficiency of
the condition prediction process. The second stage included gathering
historical data for different pipeline sizes and types in Qatar based on
previous inspections' records. The provided inspection dataset did not
include all the factors identified in the first stage of the data collection
process. Furthermore, few parameters or factors in the inspections'
5. Data collection
5.1. Factors affecting oil and gas pipeline condition assessment
The factors related to corrosion or third party features are insuffi-
cient to build an accurate condition assessment model. Therefore, it
is essential to identify other factors affecting pipeline condition. The
identification process was carried out in three main steps: (1) experts
prepared the most important factors that need to be considered in a
pipeline condition assessment, (2) another list was subsequently pre-
pared from the literature, and (3) a comparison was made between
the two lists to determine the overlapping criteria. The most important
 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65 53

Table 1
Collected pipelines' main characteristics.

Characteristics Pipeline (1) Pipeline (2) Pipeline (3)

Total length (km) 211 45 121

Inspected length (km) 77 45 85
Overall location 80 km (Offshore) + 131 km (Onshore) 45 km (Offshore) 89 km (Offshore) + 32 km (Onshore)
Inspected location Offshore Offshore Offshore
Diameter (inches) 12 20 24
Wall thickness (mm) 9.5 12.7 12.7
Steel pipe grade X65 B X52
SMYS (Mpa) 448 241 358
MAOP (bars) 125 48 50
Design pressure (bars) 139 50 107
Product type Gas Oil Gas
Construction year 1990 1972 1979
Inspection years 1996 and 2004 2001 and 2009 1996, 2001, and 2008

factors affecting pipeline condition were then identified. These factors
were divided into three main groups, namely, physical, external, and
operational. The physical factors comprise general pipeline characteris-
tics such as age, wall thickness, diameter, and applied coating condition.
The external factors deal with the surrounding environmental condition
of the pipeline while the operational factors deal with the adapted
operational strategies for the pipelines. The questionnaire that was
developed for the factors' identification was sent to 55 experts in oil
and gas pipelines integrity management. Out of the 55 questionnaires
sent, 28 completed questionnaires were received out of which only 25
were taken into consideration from the targeted sample, which repre-
sents 45.5% of the total sample. The respondents were asset, inspection,
and operation managers as well as onshore/offshore inspection engi-
neers with a technical experience of 6 to more than 20 years. It should
be noted that 22 of the respondents were inspection/operation man-
agers with a technical experience of more than 20 years. It should also
be noted that the surveys were mainly collected from the Middle-East
region, mostly from Qatar and Saudi Arabia.
5.2. Historical inspection data
Inspections data for three pipelines were collected from a large
state-owned oil and gas industry corporation in Qatar. The three pipe-
lines were located offshore and were of different sizes and different
steel grades. The main characteristics of the three pipelines are shown
in Table 1. Different inspection types were received whether they
were internal or external. The internal inspections included reports
and excel sheets obtained from the Magnetic Flux Leakage (MFL)
inspection method. On the other hand, the external inspections includ-
ed reports generated from Remotely Operated Vehicle (ROV) inspec-
tions and cathodic protection monitoring system. The inspection
reports were provided for two to three different inspection time inter-
vals covering the full length of the offshore pipelines. As mentioned ear-
lier, the provided inspection dataset did not include all the factors
identified in the first stage of the data collection process. Moreover,
few factors in the inspections' dataset were not available in the factors
identified previously. As a result, the compatible factors as well as the
additional factors in the inspections dataset were selected to develop
the condition prediction models. The factors selected to develop the
condition prediction models are shown in Fig. 2.
6. Model development
The model building procedure is shown in Fig. 3. The historical in-
spection datasets obtained from three pipelines in Qatar were used to
represent the factors affecting the pipeline condition. The 11 factors
shown in Fig. 2 were used to build the models. As mentioned before,
three models were developed based on the pipeline size (i.e. diameter)
and the transported product type (i.e., oil or gas). Moreover, two addi-
tional models were developed based only on the transported product
type making a total of five models as shown in Fig. 3.
After studying the inspection data of the three pipelines, it was
found that some factors were not constant across the whole pipeline
length. For example, the metal loss depth or the cathodic protection
can be high in a certain sector of the pipeline and low in another. As a
result, the pipelines were divided into several 100-meter-long

Coating
Metal Loss Condition
Crossings
Diameter
Cathodic
Protection

Age FACTORS AFFECTING

PIPELINE CONDITION

Operating
Pressure
Joint
Condition Anode
Free Spans Wastage
Support
Condition

Fig. 2. Factors included in model development.

54 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65

segments. For instance, the 24-inch gas pipeline with an inspected
length of 85 km was divided into 850 100-meter-long segments. As
shown in Table 1, inspections were carried for the 24-inch gas pipeline
in 1996, 2001, and 2008. Therefore, the total number of the data points
for developing the 24-inch gas pipeline model will be 850 × 3 = 2550
data points. Using the same concept; the number of data points used
for developing the 12-inch gas, 20-inch oil, gas, and oil models will be
1540, 900, 4990, and 4990, respectively.
The data for the “gas pipeline” model was generated by combining
the data of the 12-inch and 24-inch gas pipelines with the 20-inch oil
pipeline. The 20-inch oil pipeline was treated as a gas pipeline by calcu-
lating its actual condition using the “gas model” developed by El-Abbasy
et al. [14]. This will allow the prediction models to accommodate a
wider range of different pipelines' diameter and age. The same proce-
dure was followed again to obtain the data for the “oil pipeline”
model. In other words, the 20-inch oil pipeline data was combined
together with the 12-inch and 24-inch gas pipeline data into one set.
However, this time, the 12-inch and 24-inch gas pipelines were treated
as oil pipelines by calculating their actual condition using the “oil
model” developed by El-Abbasy et al. [14].
6.1. ANN model building
The ANN model is developed and analyzed using the Neuroshell
2V4.0® package [37], which is a commercially available neural network
analysis and modeling software. The ANN application framework of the
condition prediction problem is shown in Fig. 3. The inspection data for
selected factors are used to train the ANN in order to obtain ANN-based
condition prediction models. The inspection data points were divided
randomly into three sets: (1) 60% for training; (2) 20% for testing; and
(3) 20% for validation. The training set is used to train the network
whereas the testing set is used to test the network during the develop-
ment/training and also to continuously correct it by adjusting the
weights of network links. The validation data set, which is not presented

START

Define Models to be Developed

(1) 12-Inch Gas Pipes (2) 20-Inch Oil Pipes (3) 24-Inch Gas Pipes (4) Gas Pipes (5) Oil Pipes

Investigated variables

Condition Prediction Model Using

ANN Technique

Define Training, Testing, & Validation Datasets

Select Learning Algorithm

Define Design Parameters Define Training Criteria

Train Model

Recall Model for Testing

Test Model

NO
Testing Successful?

YES

Model Validation

Actual vs. Predicted Mathematical NO

Outputs Validation

YES

END

Fig. 3. Model development framework.

 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65 55

Table 2 6.1.2. Design parameters and training criteria

Factors' normalization method. The design parameters and training criteria defined for the ANN
Factor Unit Normalization method models are shown in Table 4. The selection of the input and output
variables greatly affects the ANN architecture and depends upon the
Age (AG) Years AG/70
Diameter (DI) Inches (DI − 2)/(52 − 2) nature of the problem. The input variables for the “gas” and “oil” pipe-
Metal loss (ML) % ML × 1 line models include the 11 factors shown in Fig. 2. However, the “diam-
Coating condition (CC) % CC × 1 eter” factor is excluded from the list for the “12-inch gas”, “20-inch oil”,
Crossings (CR) Number CR/20
and “24-inch gas” pipelines models since the diameter is constant for
Cathodic protecion (CP) mV (CP − 500)/(1300 − 500)
Operating pressure (OP) % of Design Pressure OP × 1 those models. Each variable is represented by one artificial neuron in
Anode wastage (AW) % AW × 1 the network's input and output layers. The input layer consists of 10
Support condition (SC) % SC × 1 neurons that represent the factors affecting the pipeline condition
Free spans (FS) meters FS/70 while the output layer has only one neuron that represents the pipeline
Joint condition (JC) % JC × 1
condition. The number of neurons in the hidden layers determines how
well a problem can be learned. If too many are used, the network will
to the network during training, is used to validate the model. To classify tend to memorize the problem, and thus not generalize well later. On
data into the abovementioned data sets, data patterns are randomly the other hand, if too few are used, the network will generalize well
selected from the entire data space, according to the set percentages. but may not have enough “power” to learn the patterns well [37]. In
It is worth noting that the factors' real numeric values were normalized other words, the hidden layers rely on the available model building
according to the normalization method shown in Table 2. dataset and the nature of outputs. Therefore, getting the right number
of hidden neurons is a matter of trial and error. Several iterations are
made to generate the optimum number of neurons in the hidden layer
6.1.1. Network architecture as shown in Table 4.
After dividing the datasets; the inputs and outputs were identified Different activation functions were applied to a hidden layer to
and selected. The inputs or predictors represent the factors affecting detect different features in a pattern, which is processed through a net-
the pipeline condition (Fig. 2) while the output represents the pipeline work. For example, a network design may use a Gaussian function on
condition. It should be noted that the pipeline condition is represented one hidden layer to detect features in the mid-range of the data and
by a numeric scale value from “0” to “10”, where “0” indicates that the use a Gaussian complement in another hidden layer to detect features
pipeline is at its worst condition and “10” at its best condition. Such from the upper and lower extremes of the data. Thus, the output layer
scale was adapted from the study conducted by El-Abbasy et al. [15] will get different views of the data. Combining the two feature sets in
which mainly depended on experts' opinions. Each pipeline's condition the output layer may lead to a better prediction.
numeric range and its corresponding linguistic description, most possi- The interaction among the network's layers is governed by the links
ble associated features, and suggested required action is shown in between them. Each link in the network has a learning rate, momen-
Table 3 [15]. A supervised ANN, using the back propagation algorithm, tum, and initial weights. Each time a pattern is presented to the
is used to develop the condition prediction models. The network archi- network, the weights leading to an output node are modified slightly
tecture has a total of five layers of neurons with one input, three hidden, during learning to produce a smaller error the next time the same pat-
and one output layers as shown in Fig. 4. tern is presented. The amount of weight modification is the learning

Table 3
Condition assessment scale [15].

Overall pipeline Linguistic Description Action(s) required

condition scale

Fit for purpose

9–10 Excellent • Internal & external corrosion: almost no signs ➢ Reassess in 10 years
• Corrosion rate: highly below expected average rate (≪0.08 mm/year). ➢ Regular annual maintenance.
• Cathodic protection: very good and within acceptable limits (N950 mV).
• Coating: very well maintained (b15% coat loss).
• Inhibitor's efficiency: N95%
7–9 Very good • Internal & external corrosion: few signs ➢ Reassess in 8 years
• Corrosion rate: below expected average rate (b0.08 mm/year). ➢ Regular annual maintenance.
• Cathodic protection: good and within acceptable limits (850–950 mV).
• Coating: well maintained (15–30% coat loss).
• Inhibitor's efficiency: 90–95%.
5–7 Good • Internal & external corrosion: average signs ➢ Reassess in 5 years
• Corrosion rate: nearly equal to the expected average rate (≈0.08 mm/year). ➢ Regular annual maintenance.
• Cathodic protection: adequate (750–850 mV). ➢ Schedule for CP & recoating within the next 2 years.
• Coating: still intact (30–40% coat loss)
• Inhibitor's efficiency: 80–90%.
3–5 Moderate • Internal & external corrosion: significant signs ➢ Reassess in 2 years
• Corrosion rate: above expected average rate (N0.08 mm/year). ➢ Regular annual maintenance.
• Cathodic protection: inadequate (675–750 mV). ➢ Schedule for minor rehabilitation within the next 1 year.
• Coating: partially damaged (40–60% coat loss) ➢ Schedule for CP & recoating within the next 1 year.
• Inhibitor's efficiency: 70–80%.

Close to failure
0–3 Critical • Internal & external corrosion: severe signs ➢ Schedule for major rehabilitation &/or replacement immediately.
• Corrosion rate: highly above expected average rate (≫0.08 mm/year).
• Cathodic protection: poor (b675 mV).
• Coating: almost damaged (N60% coat loss)
• Inhibitor's efficiency: b70%.
56 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65

Input Layer Hidden Layers Output Layer

Link 2

SLAB 2

Link 1

Link 4
SLAB 1 Link 3 SLAB 4 SLAB 5

Link 5

SLAB 3

Link 6

Fig. 4. ANN models' architecture.

rate times the error. For example, if the learning rate is 0.5, the weight
change is one half the error. Large learning rates often lead to oscillation
of weight changes and learning never completes, or to a convergence to
a non-optimum solution. One way to allow faster learning without os-
cillation is to make the weight change as a function of the previous
weight change to provide a smoothing effect. The momentum factor
determines the proportion of the last weight change that is added into
the new weight change. As neurons pass values from one layer of the
network to the next layer in back propagation networks, the values
are modified by a weight value in the link that represents connection
strengths between the neurons.
Finally, the training criteria include fixing the maximum and mini-
mum absolute error and the number of training cycles without improve-
ments. When the given training criteria are met, the model training is
stopped. If the training criteria are not met, it is suggested to either
change the activation functions or retrain using different architecture.

Table 4
Models' design parameters and training criteria.

Slab no. No. of neurons Activation function Link

Link no. Learning rate Momentum Initial weight

Design parameters 1 10a/11b Linear (0,1) 1 0.05 0.1 0.3

2 12 Gaussian 2 0.05 0.1 0.3
3 12 Tanh 3 0.05 0.1 0.3
4 12 Gaussian Complement 4 0.05 0.1 0.3
5 1 Logistics 5 0.05 0.1 0.3
6 0.05 0.1 0.3
Training criteria Stop training when one of these is true about the training set –Average Error b 0.0002
–Epochs since minimum average error N 1000
Stop training when one of these is true about the test set –Calibration Interval (events) 200
–Events since minimum average error N 20,000
a
For: 12-inch gas, 20-inch oil, and 24-inch gas pipes models.
b
For: gas and oil pipes models.

Table 5
Summary of the models' results.

Model R2 (%) r2 (%) Mean Squared Error Mean Absolute Error Min. Absolute Error Max. Absolute Error Correlation
(MSE) (MAE) Coeff., r (%)

12-Inch gas pipes 99.04 99.04 0.011 0.083 0.000 0.502 99.52
20-Inch oil pipes 99.59 99.59 0.007 0.060 0.000 0.565 99.80
24-Inch gas pipes 99.29 99.31 0.009 0.070 0.000 0.507 99.65
Gas pipes 99.23 99.25 0.011 0.079 0.000 0.548 99.63
Oil pipes 99.28 99.29 0.011 0.081 0.000 0.566 99.64
 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65 57

6.1.3. Model training and testing

Contribution factor
Consequently, the model is trained until the training criteria are met.
The training process uses “supervised learning” where the inputs and
outputs are known within the context of the problem. After the ANN

0.16674

0.07867
0.08241
0.12364

0.08406

0.07492

0.05204
0.11634

0.08173

0.07575

0.0637
is trained, it can be recalled to predict the pipeline condition for any
given testing input values. The testing input data sets are introduced
to the trained model in order to generate the predicted output, which

Cathodic protection

Operating pressure
Support condition
Coating condition
is then compared to the actual one. If they are close, the model testing

Anode wastage

Joint condition
is successful and vice versa. The training and testing processes were per-

Free spans
formed successfully for all the models with reasonable results as shown

Metal loss

Crossings
Diameter
Oil pipes

Variable
in Table 5. The ANN model values of R2 were close to 1.0 while the MSE

Age
and MAE were close to 0.0. The results confirm the robustness of the
developed models.

Contribution factor
6.1.4. Significance ranking of variable
Quantitative estimates of the relative contribution factor for

0.07222
0.15307
0.12572

0.10525

0.06006
0.08967
0.11175

0.07003

0.05992
0.08723

0.06507
the input variables affecting the pipeline condition are made. The con-
tribution factor for a certain variable is considered as a rough measure
of the importance of that variable in predicting the network's output.
Therefore, the contribution factor, which is derived from the contribu-

Cathodic protection

Operating pressure

Support condition
Coating condition
tion factor module of the referred software, determines the variable sig-

Anode wastage
Joint condition
nificance ranking. These contribution factors are developed through an

Free spans
Metal loss
Gas pipes

Crossings
Diameter
analysis of the link weights of the trained neural network. The higher

Variable
the number, the more that variable contributes toward prediction or

Age
classification of the output. Table 6 shows the factors' ranking and
their corresponding contribution factor.

Contribution factor
The relative significance ranking of the considered parameters,
obtained from the above analysis, can be generalized. As shown in
Table 6, it can be observed that the “cathodic protection” factor can be

0.09094
0.12901

0.09451

0.07232
0.14446

0.11631
0.09748

0.09407

0.08498
0.07593
considered as the most important variable affecting the pipe condition.
The “metal loss” and “coating condition” factors are also relatively im-

–
portant in determining the pipeline condition. This shows that minimiz-

Cathodic protection

Operating pressure
ing the corrosion rate by applying adequate coating and cathodic

Support condition
Coating condition
24-Inch gas pipes
protection for offshore pipelines is essential to improve their conditions.

Anode wastage
Joint condition
It can also be observed that the “operating pressure” factor has signifi-

Free spans
Metal loss

Crossings
Variable

cantly more impact in gas than in oil pipelines. On the other hand,
“crossings” and “diameter” are considered as the least important factor

Age

–
affecting the pipe condition. The rest of the factors, namely, “age”,
“anode wastage”, “support condition”, “joint condition”, and “free
Contribution factor

spans”, contributes moderately to the pipeline prediction process.

It should be noted that ranking the variables throughout the contri-
bution factors is useful in refining the variables by excluding the least
0.07997
0.09446
0.11382

0.07232
0.11304

0.09625
0.09705

0.09619
0.16253

0.07437
important ones. However, in the current study, no variables were ex-
cluded since the difference between each variable's contribution factor –

is not significant.
Cathodic protection

Operating pressure
Support condition
Coating condition
20-Inch oil pipes

Anode wastage

Joint condition

7. Model validation
Free spans
Metal loss

Crossings
Variable

The performances of the developed five models are validated using

Age

the 20% validation dataset. The performance of each model is validated

–

with respect to certain mathematical validation diagnostics as recom-

Contribution factor

mended in literature [2,40]. Eqs. (1) and (2) show the average validi-
Relative variables' contribution factors and ranking.

ty/invalidity percentages (i.e., AVP and AIP) in order to predict the

error. The model is sound for an AIP value closer to 0.0 and not robust
0.06697
0.16607
0.13936
0.12299

0.06716

0.05893
0.09615

0.06396

for an AIP value closer to 100. Similarly, the Root Mean Square Error
0.1071
0.1113

(RMSE) is estimated using Eq. (3). If the value of the RMSE is close to
–

0, the model is sound and vice versa. The Mean Absolute Error (MAE)
is also defined in Eq. (4). The MAE value varies from 0 to infinity and
Cathodic protection

Operating pressure

Support condition
Coating condition
12-Inch gas pipes

it should be close to zero for sound results [13]. Finally, the MAE value
Anode wastage

Joint condition

is also used to define the fitness function fi of a model [13] as shown

Free spans
Metal loss

in Eq. (5). The equation for the fitness function indicates that a model
Crossings
Variable
Model

is valid when its fi value is close to 1000 and invalid when its fi value
Age

is close to 0.
–

X   
n  E 
Table 6

Rank

100
AIP ¼ 1− i   ð1Þ
10
11

i¼1 
1
2
3
4
5
6
7
8
9

Ci n
58 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65

Table 7
Regression and ANN models' validation comparison.

Model Regression technique ANN technique

R2 (%) AVP (%) AIP (%) RMSE MAE fi R2 (%) AVP (%) AIP (%) RMSE MAE fi

12-Inch gas pipes 98.80 97.9 2.1 0.008 0.098 911 99.04 98.1 1.9 0.007 0.093 915
20-Inch oil pipes 99.40 96.2 3.8 0.015 0.152 868 99.59 97.4 2.6 0.012 0.099 910
24-Inch gas pipes 99.20 98.3 1.7 0.005 0.079 927 99.29 98.4 1.6 0.005 0.078 928
Gas pipes 99.10 97.8 2.2 0.005 0.099 910 99.23 97.8 2.2 0.004 0.093 915
Oil pipes 99.00 97.9 2.1 0.004 0.094 914 99.28 98.0 2.0 0.004 0.089 918

9
(a) 12-INCH GAS PIPES
Pipe Condition

8
7
6
5
4
3
2
1
0
0 50 100 150 200 250 300 350
Event Number

(b) 20-INCH OIL PIPES

9
Pipe Condition

8
7
6
5
4
3
2
1
0
0 50 100 150 200
Event Number

9
(c) 24-INCH GAS PIPES
Pipe Condition

8
7
6
5
4
3
2
1
0
0 50 100 150 200 250 300 350 400 450 500 550
Event Number

(d) GAS PIPES

9
Pipe Condition

8
7
6
5
4
3
2
1
0
0 100 200 300 400 500 600 700 800 900 1000
Event Number

(e) OIL PIPES

10
9
Pipe Condition

8
7
6
5
4
3
2
1
0
0 100 200 300 400 500 600 700 800 900 1000
Event Number
ACTUAL CONDITION PREDICTED CONDITION

Fig. 5. Models' validation plots.

 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65 59

AVP ¼ 100−AIP ð2Þ Error; fi = fitness function; Ei = estimated value; Ci = actual value;
and n = number of events.
qX
ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi Table 7 summarizes the results of the developed ANN model valida-
n 2
RMSE ¼ i¼1
ðC i −Ei Þ =n ð3Þ tion parameters. These results were compared with those obtained
using the regression models of El-Abbasy et al. [15]. As shown in the
Xn table, both techniques provided five corresponding models with an
jCi −Ei j AVP close to 1, AIP, RMSE, and MAE close to 0 as well as fi close to
MAE ¼ i¼1
ð4Þ
n 1000. These results can be considered as good indicators to the robust
1000 performance of the models in predicting accurately the pipeline condi-
fi ¼ ð5Þ tion. Both techniques are almost similar to each other in terms of R2,
1 þ MAE
AVP, AIP, RMSE, MAE, and fi. However, the results in Table 7 show that
the ANN technique provides slightly better results than the regression
Where: AIP = Average Invalidity Percent; AVP = Average Validity technique with respect to all parameters. This is due to the fact that
Percent; RMSE = Root Mean Squared Error; MAE = Mean Absolute the ANN technique considers the nonlinear relation of the dependent

12-INCH GAS PIPES DETERIORATION CURVES - DIRECTLY PROPORTIONAL FACTORS

8.5
PIPE CONDITION

7.5

6.5

NORMALIZED VALUE 5.5

0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
FACTORS' REAL VALUES
CATHODIC PROTECTION (mv) 500 580 660 740 820 900 980 1060 1140 1220 1300
CORRESPONDING PIPE CONDITION
COATING CONDITION 5.79 6.09 6.40 6.71 6.99 7.24 7.45 7.62 7.7 4 7.81 7.83
CATHODIC PROTECTION 5.88 6.23 6.55 6.86 7.14 7.40 7.63 7.85 8.0 3 8.19 8.33
SUPPORT CONDITION 7.38 7.44 7.50 7.56 7.61 7.65 7.69 7.72 7.7 4 7.76 7.78
JOINT CONDITION 7.53 7.56 7.58 7.61 7.64 7.66 7.69 7.71 7.7 4 7.76 7.78

12-INCH GAS PIPES DETERIORATION CURVES - INVERSELY PROPORTIONAL FACTORS

9
PIPE CONDITION

NORMALIZED VALUE 6
0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
FACTORS' REAL VALUES
AGE (Years) 0 7 14 21 28 35 42 49 56 63 70
CROSSING (#) 0 2 4 6 8 10 12 14 16 18 20
FREE SPANS (m) 0 7 14 21 28 35 42 49 56 63 70
CORRESPONDING PIPE CONDITION

AGE 7.86 7.79 7.73 7.67 7.61 7.57 7.52 7.49 7.46 7.43 7.41
METAL LOSS 8.32 8.04 7.79 7.55 7.34 7.14 6.95 6.77 6.58 6.39 6.18
CROSSINGS 7.77 7.76 7.74 7.73 7.72 7.71 7.70 7.69 7.69 7.68 7.68
OPERATING PRESSURE 9.18 9.03 8.87 8.71 8.55 8.40 8.24 8.08 7.92 7.76 7.61
ANODE WASTAGE 7.85 7.80 7.75 7.71 7.66 7.61 7.56 7.52 7.47 7.42 7.38
FREE SPANS 7.85 7.71 7.58 7.47 7.36 7.27 7.18 7.11 7.05 7.01 6.97

Fig. 6. 12-Inch gas pipes deterioration curves.

60 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65

and independent variables as well as the correlation between the
factors affecting the pipeline condition.
Fig. 5 shows the “actual versus predicted output plot” results for the
five developed models. It is observed that the predicted values by the
developed models are within the acceptable limits and scattered around
the actual values of response variable. In other words, the majority of
the results obtained are matching with few instances of disagreement.
Therefore, the validation test results are satisfactory.
8. Deterioration curve building
A sensitivity analysis is executed in order to test the developed
models' sensitivity to changes in their inputs. For each model, the
input variables were varied one at a time to determine their respective
impact on the pipeline condition. For this purpose, the values of the
studied factor were varied whereas the values of the other factors
were kept constant at their average values. The data was presented to
the developed models to predict new outputs. The pipeline conditions
were obtained using the prediction models. Since there were no varia-
tions in any factor other than the one studied, the variations observed
in the predicted pipeline conditions were under the exclusive influence
of the studied factor. In other words, the effects of all other factors were
discounted and the impacts of the studied factor upon the pipeline con-
dition were determined.
It is also important to express graphically the impact of each fac-
tor on the pipeline condition. As a result, deterioration curves were
developed for each model as shown in Figs. 6 to 10. These deteriora-
tion curves give a clearer understanding of the interrelationships of

20-INCH OIL PIPES DETERIORATION CURVES - DIRECTLY PROPORTIONAL FACTORS

9
PIPE CONDITION

NORMALIZED VALUE
6
0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
FACTORS' REAL VALUES

CATHODIC PROTECTION (mv) 500 580 660 740 820 900 980 1060 1140 1220 1300
CORRESPONDING PIPE CONDITION

COATING CONDITION 6.52 6.72 6.93 7.13 7.33 7.52 7.72 7.91 8.10 8.28 8.47
CATHODIC PROTECTION 6.42 6.82 7.22 7.60 7.96 8.29 8.59 8.83 9.03 9.19 9.29
SUPPORT CONDITION 7.66 7.77 7.87 7.96 8.04 8.11 8.18 8.24 8.29 8.34 8.39
JOINT CONDITION 8.15 8.17 8.18 8.20 8.22 8.24 8.27 8.30 8.33 8.36 8.39

20-INCH OIL PIPES DETERIORATION CURVES - INVERSELY PROPORTIONAL FACTORS

9
PIPE CONDITION

NORMALIZED VALUE 6
0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
FACTORS' REAL VALUES

AGE (Years) 0 7 14 21 28 35 42 49 56 63 70
CROSSING (#) 0 2 4 6 8 10 12 14 16 18 20
FREE SPANS (m) 0 7 14 21 28 35 42 49 56 63 70
CORRESPONDING PIPE CONDITION

AGE 8.52 8.49 8.45 8.42 8.38 8.35 8.31 8.27 8.24 8.20 8.17
METAL LOSS 8.41 8.37 8.26 8.08 7.84 7.56 7.25 6.95 6.67 6.45 6.32
CROSSINGS 8.36 8.35 8.33 8.32 8.30 8.29 8.27 8.26 8.24 8.23 8.21
OPERATING PRESSURE 8.45 8.45 8.45 8.44 8.44 8.43 8.42 8.40 8.39 8.37 8.35
ANODE WASTAGE 8.42 8.37 8.31 8.26 8.20 8.15 8.09 8.04 7.98 7.92 7.87
FREE SPANS 8.46 8.21 8.00 7.83 7.70 7.59 7.50 7.43 7.38 7.35 7.32

Fig. 7. 20-Inch oil pipes deterioration curves.

 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65 61

24-INCH GAS PIPES DETERIORATION CURVES - DIRECTLY PROPORTIONAL FACTORS

PIPE CONDITION
8

NORMALIZED VALUE 6
0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
FACTORS' REAL VALUES

CATHODIC PROTECTION (mv) 500 580 660 740 820 900 980 1060 1140 1220 1300
CORRESPONDING PIPE CONDITION

COATING CONDITION 6.46 6.66 6.85 7.04 7.22 7.39 7.56 7.73 7.88 8.04 8.18
CATHODIC PROTECTION 6.29 6.54 6.84 7.16 7.48 7.80 8.08 8.33 8.53 8.66 8.73
SUPPORT CONDITION 7.82 7.87 7.91 7.95 7.98 8.01 8.04 8.07 8.09 8.11 8.13
JOINT CONDITION 7.63 7.67 7.72 7.77 7.82 7.88 7.94 8.00 8.06 8.12 8.19

24-INCH GAS PIPES DETERIORATION CURVES - INVERSELY PROPORTIONAL FACTORS

9
PIPE CONDITION

NORMALIZED VALUE 6
0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
FACTORS' REAL VALUES

AGE (Years) 0 7 14 21 28 35 42 49 56 63 70
CROSSING (#) 0 2 4 6 8 10 12 14 16 18 20
FREE SPANS (m) 0 7 14 21 28 35 42 49 56 63 70
CORRESPONDING PIPE CONDITION

AGE 8.31 8.25 8.19 8.13 8.07 8.01 7.95 7.89 7.83 7.77 7.71
METAL LOSS 8.91 8.66 8.41 8.16 7.91 7.66 7.42 7.17 6.92 6.67 6.42
CROSSINGS 8.13 8.10 8.07 8.04 8.02 7.99 7.96 7.94 7.91 7.88 7.86
OPERATING PRESSURE 8.86 8.69 8.53 8.37 8.22 8.07 7.92 7.77 7.62 7.46 7.30
ANODE WASTAGE 8.21 8.14 8.07 8.02 7.96 7.91 7.87 7.83 7.79 7.76 7.74
FREE SPANS 8.21 8.10 7.99 7.88 7.77 7.66 7.56 7.45 7.34 7.23 7.12

Fig. 8. 24-inch gas pipes deterioration curves.

pipeline future condition and the studied factors. As shown in the
mentioned figures, each deterioration curve set was separated into
two groups of factors, namely, directly proportional and inversely
proportional.
The first group shows only the factors that have a positive impact on
the pipeline condition. The factors in this group are the diameter, the
coating condition, the cathodic protection, the support condition, and
the joint condition. Smaller pipeline diameters have usually higher
probability of failure than those with larger ones [39]. This is possibly
because smaller standard dimension ratios (SDR) affect the structural
performance of pipelines and make them more vulnerable to external
impact and third party damage. In addition, smaller diameter pipelines,
which have thinner wall thicknesses, allow faster corrosion rate. Good
and well maintained coating and cathodic protection enhances the
pipeline condition by protecting it against corrosion. Finally, well main-
tained supports and joints condition achieves a better structural perfor-
mance of the pipeline.
On the other hand, the second group shows only the factors that
have a negative impact on the pipeline condition. The factors in this
group are the age, the metal loss, the anode wastage, the operating
pressure, the crossings, and the free spans. The impact of age on pipeline
condition is negative in nature. An increase of the metal loss depth as a
percentage of its pipeline wall thickness due to corrosion or mechanical
damage degrades pipeline condition. As galvanic anodes waste, their
sizes decrease; resulting in a decrease in their well-known sacrificial
action to protect the pipeline from corroding. Maximum allowable
operating pressure (MAOP) decreases the pipeline condition when it
gets close to the design pressure as it can induces more stresses on the
62 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65

GAS PIPES DETERIORATION CURVES - DIRECTLY PROPORTIONAL FACTORS

PIPE CONDITION
8.5

7.5

6.5

NORMALIZED VALUE 5.5

0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
FACTORS' REAL VALUES

DIAMETER (Inches) 2 7 12 17 22 27 32 37 42 47 52
CATHODIC PROTECTION (mv) 500 580 660 740 820 900 980 1060 1140 1220 1300
CORRESPONDING PIPE CONDITION

DIAMETER 7.84 7.88 7.92 7.96 8.00 8.05 8.09 8.13 8.17 8.21 8.26
COATING CONDITION 6.32 6.56 6.78 6.99 7.18 7.36 7.53 7.68 7.81 7.93 8.04
CATHODIC PROTECTION 5.95 6.25 6.61 6.98 7.35 7.68 7.96 8.18 8.31 8.37 8.40
SUPPORT CONDITION 7.56 7.59 7.62 7.66 7.70 7.75 7.80 7.85 7.92 7.98 8.05
JOINT CONDITION 7.36 7.46 7.54 7.62 7.70 7.77 7.83 7.89 7.95 7.99 8.03

GAS PIPES DETERIORATION CURVES - INVERSELY PROPORTIONAL FACTORS

9.5

8.5
PIPE CONDITION

7.5

6.5

NORMALIZED VALUE
5.5
0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
FACTORS' REAL VALUES

AGE (Years) 0 7 14 21 28 35 42 49 56 63 70
CROSSING (#) 0 2 4 6 8 10 12 14 16 18 20
FREE SPANS (m) 0 7 14 21 28 35 42 49 56 63 70
CORRESPONDING PIPE CONDITION

AGE 8.18 8.12 8.05 7.99 7.92 7.86 7.79 7.73 7.67 7.60 7.54
METAL LOSS 8.36 8.25 8.09 7.87 7.61 7.31 6.99 6.68 6.39 6.14 5.98
CROSSINGS 8.01 7.97 7.92 7.88 7.84 7.80 7.75 7.71 7.67 7.63 7.58
OPERATING PRESSURE 9.31 9.10 8.90 8.70 8.51 8.33 8.15 7.97 7.80 7.63 7.47
ANODE WASTAGE 8.07 8.02 7.96 7.90 7.85 7.79 7.73 7.68 7.62 7.57 7.51
FREE SPANS 8.58 8.51 8.43 8.34 8.25 8.15 8.05 7.93 7.82 7.69 7.56

Fig. 9. Gas pipes deterioration curves.

pipeline. Finally, as the number of other crossing and free spans
increase, the pipelines become less stable.
As shown in Figs. 6 to 10, the vertical axis represents the predicted
pipeline conditions while the horizontal axis the impact factor. Since all
the factors do not have the same units, the horizontal axis of the
deterioration curves are plotted using a normalized scale from 0 to 1 as
explained in Table 2. However, for better visualization to the reader,
the real values of the factors (age, diameter, crossings, cathodic protec-
tion, and free spans) are listed below their corresponding normalized
values as shown in Figs. 6 to 10. The real values of the remaining factors
(metal loss, coating condition, operating pressure, anode wastage, sup-
port condition, and joint condition) are not listed since they are the
same as the normalized values. In addition, the corresponding predicted
pipeline condition values to each factor's different values are tabulated as
shown in each deterioration curve. For example, let us assume that the
effect of the “coating condition” factor on the pipeline condition is
studied for the “20-Inch Oil pipelines”. Let us also assume that the target
coating condition percentages are 20 and 60%. Therefore, simply by using
Fig. 7, the user will select the 0.2 and 0.6 normalized values on the hori-
zontal axis and read the corresponding predicted pipeline condition for
each case using the underneath table for the coating condition factor.
Alternatively, the user can just hit the “coating condition” curve for each
case and accordingly read the predicted pipeline condition from the
vertical axis. Based on that, the predicted pipeline conditions for coating
condition of 20 and 60% will be 6.93 and 7.72, respectively. As a reminder,
these results are based on the average values of factors other than the
“coating condition”. The same procedure can be followed to check or
predict the individual impact of other factors on the pipeline condition.
 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65 63

OIL PIPES DETERIORATION CURVES - DIRECTLY PROPORTIONAL FACTORS

PIPE CONDITION
9

NORMALIZED VALUE 6
0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
FACTORS' REAL VALUES

DIAMETER (Inches) 2 7 12 17 22 27 32 37 42 47 52
CATHODIC PROTECTION (mv) 500 580 660 740 820 900 980 1060 1140 1220 1300
CORRESPONDING PIPE CONDITION

DIAMETER 8.50 8.54 8.58 8.62 8.66 8.70 8.74 8.78 8.82 8.86 8.90
COATING CONDITION 6.66 6.90 7.14 7.36 7.58 7.79 7.99 8.19 8.37 8.56 8.73
CATHODIC PROTECTION 6.21 6.31 6.65 7.13 7.66 8.17 8.61 8.92 9.08 9.16 9.18
SUPPORT CONDITION 7.94 8.02 8.09 8.16 8.23 8.29 8.36 8.42 8.47 8.53 8.58
JOINT CONDITION 7.92 8.01 8.10 8.18 8.26 8.33 8.39 8.44 8.49 8.54 8.57

OIL PIPES DETERIORATION CURVES - INVERSELY PROPORTIONAL FACTORS

9
PIPE CONDITION

NORMALIZED VALUE 6
0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
FACTORS' REAL VALUES

AGE (Years) 0 7 14 21 28 35 42 49 56 63 70
CROSSING (#) 0 2 4 6 8 10 12 14 16 18 20
FREE SPANS (m) 0 7 14 21 28 35 42 49 56 63 70
CORRESPONDING PIPE CONDITION

AGE 8.86 8.79 8.72 8.64 8.57 8.50 8.42 8.35 8.27 8.20 8.12
METAL LOSS 9.21 9.02 8.78 8.50 8.19 7.86 7.51 7.15 6.82 6.51 6.25
CROSSINGS 8.66 8.63 8.59 8.56 8.54 8.51 8.49 8.47 8.45 8.44 8.43
OPERATING PRESSURE 8.83 8.80 8.77 8.75 8.72 8.69 8.67 8.64 8.61 8.59 8.56
ANODE WASTAGE 8.59 8.55 8.50 8.44 8.35 8.25 8.13 7.99 7.84 7.67 7.48
FREE SPANS 8.02 7.97 7.93 7.89 7.85 7.80 7.76 7.72 7.67 7.63 7.59

Fig. 10. Oil pipes deterioration curves.

Besides examining the impact of changing each factor on the pipe-
line condition, additional deterioration curves were developed—for oil
and gas pipelines—to show the effect of changing all the factors togeth-
er. These curves were developed by changing simultaneously all the
factors normalized values starting from their best possible to their
worst effects on the pipeline condition as shown in Fig. 11. For more
clarification, the curves were built by first increasing the age factor by
one year starting from zero. Simultaneously, the metal loss, coating con-
dition, cathodic protection, crossings, anode wastage, free spans, joint
and support condition factors were changed proportionally according
to their rate of increase or decrease based on the received historical
inspection data. However, both the factors of diameter and operating
pressure were kept constant. The effect of such periodical change in
the factors' values was determined by calculating the pipeline condition
each year using the developed model. It should be noted that the
deterioration profiles shown in Fig. 11 does not take into account any
kind of rehabilitation action that may take place during the pipeline op-
eration. Also, due to the lack of inspections data received, the accuracy
of the deterioration profiles can be enhanced throughout receiving
more additional inspections data.
According to the developed deterioration curves, it can be observed
that the “cathodic protection” and “coating condition” factors have the
highest positive impacts on the pipeline condition while the “diameter”
factor has the lowest positive impact. On the other hand, the “metal loss”
and “crossings” factors have the highest and lowest negative impacts on
the pipeline condition, respectively. This indicates that the corrosion re-
lated factors (cathodic protection, metal loss, and coating condition) are
the most important contributors to the pipeline condition prediction.
However, other factors including age, support condition, joint condition,
anode wastage, and free spans, are still essential for pipeline condition
64 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65
GAS & OIL PIPELINES DETERIORATION PROFILES
10
9 pipelines by artificial neural networks, Am. Inst. Chem. Eng. J. 44 (12) (1998)
8
PIE CONDITION
7 evaluation in the pipeline transport dangerous goods, Chem. Eng. Trans. 19
6 (2010) 249–254.
5
4 [6] R. Caruana, A. Niculescu-Mizil, An empirical comparison of supervised learning
3 algorithms, Proceedings of the 23rd international conference on Machine Learning,
2 ACM, Pittsburgh, PA, USA, 2006.
1 and artificial neural networks applied to detection and classification of pipe weld
0 defects, NDT E Int. 39 (8) (2006) 661–667.
0 10 20 30 40 50 60
AGE (Years)
GAS PIPES OIL PIPES
Fig. 11. Deterioration profiles.
prediction as they together represent around 40% of their contribution
strength. Also, operating pressure has a significantly higher effect on
“gas” pipeline condition than on “oil” pipelines.
9. Conclusions
A study on the condition prediction of oil and gas pipelines was con-
ducted. Twenty quantitative and qualitative factors having a major im-
pact on the condition of oil and gas pipeline were identified of which 11
were used in this study. The ANN technique was used to develop five
condition prediction models with respect to pipeline size and type of
transported product. The developed models are based on historical
inspection data collected from three different offshore pipelines in
Qatar. The collected data were prepared, organized, and subsequently
used to train, test, and validate the models. The coefficient of determina-
tion (R2) results for the developed models were between 99.04 and
99.59%. In addition, all other necessary statistical diagnosis have been
checked showing sound results for the developed models. The models
have been validated and the results showed their robustness with an
average validity percentage between 97.40 and 98.40%. The developed
ANN models were compared with previously developed regression
models that serve the same purpose of this study. It was found that the
performance of both techniques were close to each other, however, the
ANN technique provided better results. Finally, a sensitivity analysis
was carried out in order to build deterioration curves for the models de-
veloped. The deterioration curves show the degree of the individual effect
of each factor on the pipeline condition. Cathodic protection and coating
condition were found to have the highest positive effect on the pipeline
condition while metal loss have the highest negative effect. On the
other hand, diameter and crossings were found to have the lowest posi-
tive and negative effects on the pipeline condition, respectively. The
models are expected to help pipeline operators to assess and predict
the condition of existing oil and gas pipelines and hence prioritize their
inspections and rehabilitation planning.
Acknowledgments
The authors gratefully acknowledge the support provided by
Qatar National Research Fund (QNRF) for this research project under
award No. QNRF-NPRP 09-901-2-343. The authors would also like to
acknowledge the operational pipeline engineers of Qatar Petroleum
for their invaluable suggestions and recommendations.
References
[1] M. Ahammed, Probabilistic estimation of remaining life of a pipeline in the presence
of active corrosion defects, Int. J. Press. Vessel. Pip. 75 (4) (1998) 321–329.
[2] H. Al-Barqawi, T. Zayed, Condition rating model for underground infrastructure
sustainable water mains, ASCE J. Perform. Constr. Facil. 20 (2) (2006) 126–135.
[3] S. Belsito, P. Lombardi, P. Andreussi, S. Banerjee, Leak detection in liquefied gas
2675–2688.
[4] C. Bersani, L. Citro, R.V. Gagliardi, R. Sacile, A.M. Tomasoni, Accident occurence
[5] M. Bertolini, N. Bevilacqua, Methodology and theory oil pipeline cause analysis a
classification tree approach, J. Qual. Maint. Eng. 12 (2) (2006) 186–198.
[7] A.A. Carvalho, J.M.A. Rebello, L.V.S. Sagrilo, C.S. Camerini, I.V.J. Miranda, MFL signals
70 [8] J. Cheng, A.N. Tegge, P. Baldi, Machine learning methods for protein structure
prediction, IEEE Rev. Biomed. Eng. 1 (2008) 41–49.
[9] P.M. Davis, J. Dubois, F. Gambardella, F. Uhlig, Performance of European Cross-
country Oil Pipelines: Statistical Summary of Reported Spillages in 2008 and Since
1971, CONCAWE, Brussels, June 2010.
[10] A.W. Dawotola, P.H.A.J.M. VanGelder, J.K. Vrijling, Decision analysis framework for
risk management of crude oil pipeline system, Adv. Decis. Sci. 2011 (2011).
[11] A.W. Dawotola, P.H.A.J.M. VanGelder, J.K. Vrijling, Risk Assessment of Petroleum
Pipelines using a combined Analytical Hierarchy Process—Fault Tree Analysis
(AHP-FTA), Proceedings of the 7th International Probabilistic Workshop, Delft,
Netherlands, 2009.
[12] P.K. Dey, A risk based model for inspection and maintenance of cross country
petroleum pipelines, J. Qual. Maint. Eng. 7 (1) (2001) 25–43.
[13] I. Dikmen, M. Birgonul, S. Kiziltas, Prediction of organizational effectiveness in
construction companies, ASCE J. Constr. Eng. Manag. 131 (2) (2005) 252–261.
[14] M.S. El-Abbasy, A. Senouci, T. Zayed, F. Mosleh, A condition assessment model for oil
and gas pipelines using integrated simulation and analytic network process, Journal
of Structure and Infrastructure EngineeringTaylor and Francis Group, 2014, (in-press).
[15] M.S. El-Abbasy, A. Senouci, T. Zayed, F. Mirahadi, L. Parvizedghy, Condition predic-
tion models for oil and gas pipelines using regression analysis, ASCE J. Constr. Eng.
Manag. 140 (6) (2014).
[16] O. Folorunsho, Comparative study of different data mining techniques performance
in knowledge discovery from medical database, Int. J. Adv. Res. Comput. Sci. Softw.
Eng. 3 (3) (2013) 11–15.
[17] R. Goodland, Oil and Gas Pipelines Social and Environmental Impact Assessment:
State of the Art, IAIA 2005 Conference, Fargo, ND, USA, 2005.
[18] J.M. Hallen, F. Caleyo, J.L. Gonzalez, Probabilistic Condition Assessment of Corroding
Pipelines in Mexico, Proceedings of the 3rd Pan American Conference for Nonde-
structive Testing (PANNDT), Rio de Janeiro, Brazil, 2003.
[19] L. Jinhai, Z. Huaguang, F. Jian, Y. Heng, A new fault detection and diagnosis method
for oil pipeline based on rough set and neural network, Advances in Neural
Networks, Lecture Notes in Computer Science (LNCS), vol. 4493, 2007, pp. 561–569.
[20] M. Kalanaki, J. Soltani, Performance assessment among hybrid algorithms in tuning
SVR parameters to predict pipe failure rates, Adv. Comput. Int. J. 2 (5) (2013) 40–46.
[21] J.L. Kennedy, Oil and Gas Pipeline Fundamentals, 2nd edition PennWell Publishing
Company, Oklahoma, 1993.
[22] S.X. Li, S.R. Yu, H.L. Zeng, J.H. Li, R. Liang, Predicting corrosion remaining life of
underground pipelines with a mechanically-based probabilistic model, J. Pet. Sci.
Eng. 65 (3–4) (2009) 162–166.
[23] K. Liao, Q. Yao, X. Wu, W. Jia, A numerical corrosion rate prediction method for direct
assessment of wet gas gathering pipelines internal corrosion, Energies 5 (10) (2012)
3892–3907.
[24] R.S. Mohana, P. Thangaraj, Machine learning approaches in improving service level
agreement-based admission control for a software-as-a-service provider in cloud,
J. Comput. Sci. 9 (10) (2013) 1283–1294.
[25] K. Mollazade, M. Omid, A. Arefi, Comparing data mining classifiers for grading
raisins based on visual features, Comput. Electron. Agric. 84 (2012) (2012)
124–131.
[26] N.M. Noor, N.A.N. Ozman, N. Yahaya, Deterministic prediction of corroding pipeline
remaining strength in marine environment using DNV RP—F101 (Part A), J. Sustain.
Sci. Manag. 6 (1) (2011) 69–78.
[27] N.M. Noor, N. Yahaya, N.A.N. Ozman, S.R. Othman, The forecasting residual life of
corroding pipeline based on semi-probabilistic method, UNIMAS E J. Civ. Eng. 1
(2010) 246–263.
[28] X.Y. Peng, P. Zhang, L.Q. Chen, Long-Distance Oil/Gas Pipeline Failure Rate Prediction
Based On Fuzzy Neural Network Model, CSIE 2009 Proceedings, World Congress on
Computer Science and Information Engineering, vol. 5, Wilshire Grand, Los Angeles,
LA, USA, 2009.
[29] M.D. Prabhakar, Prediction of software effort using artificial neural network and
support vector machine, Int. J. Adv. Res. Comput. Sci. Softw. Eng. 3 (3) (2013)
40–46.
[30] C.Y. Ren, W. Qiao, X. Tian, Natural gas pipeline corrosion rate prediction model
based on bp neural network, Adv. Intell. Soft Comput. 147 (2012) 449–455.
[31] A. Senouci, M.S. El-Abbasy, E. Elwakil, B. Abdrabou, T. Zayed, A model for predicting
failure of oil pipelines, Journal of Structure and Infrastructure Engineering, vol. 10,
No. 3, Taylor and Francis Group, 2014, pp. 375–387.
[32] A. Senouci, M.S. El-Abbasy, T. Zayed, A fuzzy-based model for predicting failure of oil
pipelines, ASCE J. Infrastruct. Syst. (2014) (in-press).
[33] M. Singh, T. Markeset, A methodology for risk-based inspection planning of oil and
gas pipes based on fuzzy logic framework, Eng. Fail. Anal. 16 (7) (2009) 2098–2113.
 M.S. El-Abbasy et al. / Automation in Construction 45 (2014) 50–65
[34] S.K. Sinha, M.D. Pandey, Probabilistic neural network for reliability assessment
of oil and gas pipelines, Comput. Aided Civ. Infrastruct. Eng. 17 (5) (2002)
320–329.
[35] M. Tabesh, J. Soltani, R. Farmani, D. Savic, Assessing pipe failure rate and mechanical
reliability of water distribution networks using data-driven modeling, J. Hydroinf. 11
(1) (2009) 1–17.
[36] I. Tahyudin, E. Utami, A. Amborowati, Comparing Classification Algorithm of Data
Mining to Predict the Graduation Students on Time, Information Systems Interna-
tional Conference (ISICO), Bali, Indonesia, 2013.
[37] Ward Systems Group Inc., Neuroshell 2V4.0, Computer Software http://www.
wardsystems.com/neuroshell2.asp 1996 surfed at 5 July 2013.
65
[38] H. White, Learning in artificial neural networks: a statistical perspective, Neural
Comput. 1 (4) (1989) 425–464.
[39] P. Wilson, D. Wheeler, R. Wilson, R. Coleman, N. Wolfe, An Assessment of Low
Pressure Crude Oil Pipelines and Crude Oil Gathering Lines in California, California
State Fire Marshal (CSFM), Sacramento, April 1997.
[40] T. Zayed, D. Halpin, Deterministic models for assessing prod. and cost of bored piles,
Constr. Manag. Econ. 23 (5) (2005) 531–543.
[41] A.W. Dawotola, P.H.A.J.M. VanGelder, J.K. Vrijling, “Risk Assessment of Petroleum
Pipelines using a combined Analytical Hierarchy Process: Fault Tree Analysis
(AHP-FTA)”, Proceedings of the 7th International Probabilistic Workshop, Delft,
The Netherlands, 2009.