Академический Документы
Профессиональный Документы
Культура Документы
Automation in Construction
journal homepage: www.elsevier.com/locate/autcon
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.
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 51
wet gas gathering pipelines. The model was also developed using genet- deterioration rate of oil and gas pipelines and hence can build up their
ic algorithm (GA) and ANN techniques which outperformed the PSO. respective deterioration curve. Consequently, El-Abbasy et al. [14] de-
Dawotola et al. [10] developed a rupture risk management model for veloped a model that assesses the condition of oil and gas pipelines
crude oil pipelines using a methodology that incorporates structured based on several factors including corrosion using both Analytic Net-
expert judgment and analytic hierarchy process (AHP). Noor et al. [27] work Process (ANP) and Monte-Carlo simulation. The model considered
used semi-probabilistic and deterministic methodologies to predict factors' interdependency (using ANP), made decisions under uncertain-
the remaining strength of submarine pipelines subjected to internal ty (using simulation), and handled decisions involving large number of
corrosion. Bersani et al. [4] developed a risk assessment model using variables (using integrated simulation/ANP). It was successfully tested
historical data from the United States Department of Transportation on an existing offshore gas pipeline in Qatar by comparing the results
(DOT) to predict the failure caused by third party activity. Historical fail- obtained using the model with the actual pipeline condition.
ure data was also used to develop a tool to predict the class of each spill- The simulation model built by El-Abbasy et al. [14] is considered as a
age in oil pipelines using statistical analysis classification and regression first phase to evaluate or assess the condition of offshore oil and gas
tree [5]. Li et al. [22] presented a method to predict the corrosion and the pipelines. Two major limitations were found in the study conducted
remaining life of underground pipelines using a mechanically-based by El-Abbasy et al. [14]. First, the factors that were used to predict the
probabilistic model that considers the effect of randomness in pipeline pipeline condition were not sufficient due to the lack of collected data.
corrosion using Monte Carlo simulation technique. Singh and Markeset The factors related to the pipeline structural condition were also not
[33] presented a proposed methodology, based on fuzzy logic frame- considered. Second, the model was developed and tested using inspec-
work, for the establishment of a risk-based inspection program for pipe- tion data for a single 12-inch gas pipeline. The limited historical inspec-
lines according to the estimation of its corrosion rate. Peng et al. [28] tion data did not allow the examination of the effect of changing
developed a fuzzy neural network model, which is based on failure the pipe diameter or the type of the transported product on the devel-
tree and fuzzy computing, to predict the rate of failure for oil and gas oped model. Moreover, the limited inspection data did not allow the
pipelines. Dawotola (2009) [41] proposed a combined AHP and Fault development of sound deterioration curves for oil and gas pipelines.
Tree Analysis to support the design, the construction, and the inspection To overcome the above limitations, an extensive data collection was
and maintenance of oil and gas pipelines by proposing an optimal selec- performed in a study conducted by El-Abbasy et al. [15] where seven
tion strategy based on the probability and consequence of failure. Jinhai historical inspection data seta were collected for three different
et al. [19] proposed a leak fault-detection method based on the combi- pipelines with several sizes (i.e. diameters), materials, and types of the
nation of Rough Set (RS) and ANN, called hybrid fault-detection method carried product. Four factors were considered in addition to those
based on RS and ANN (HFDMRSNN). Carvalho et al. [7] used the ANN presented in the previous study [14]. The additional factors included
technique for pattern recognition of magnetic flux leakage (MFL) sig- the “anode wastage” and three factors related to the pipeline structural
nals in weld joints of pipelines obtained by intelligent pig to distinguish condition namely, “support condition”, “joint condition”, and “free
the presence of defects and their type. AHP was used by Dey [12] to de- spans”. The regression analysis technique was used to correlate be-
velop a model to help decision makers select a suitable type of inspec- tween all these factors using the gathered data. The developed models
tion or monitoring technique for pipelines. Hallen et al. [18] presented were validated yielding an average validity percentage above 96%. In
a probabilistic analysis framework to evaluate the condition of a corrod- addition, the study proposed a standard condition assessment scale
ing pipeline and the evolution of its probability of failure with time. or rating system for oil and gas pipelines. This rating system can be
Sinha and Pandey [34] developed a simulation-based probabilistic used as a guideline to decide and plan the maintenance of pipelines
fuzzy neural network model to estimate the failure probability of (i.e., lining, cathodic protection, replacement, etc.) and to prioritize
aging oil and gas pipelines due to corrosion. Ahammed [1] presented a rehabilitation/upgrading projects within the approved budget.
methodology to assess the remaining service life of a pressurized pipe- Although the study conducted by El-Abbasy et al. [15] provided
line containing active corrosion defects. Belsito et al. [3] developed a sound results, the use of the regression analysis technique as a machine
leakage detection system for liquefied gas pipelines using ANN for learning algorithm has still some limitations. Several other machine
leak sizing and location. learning algorithms can be used to predict pipeline condition including
Most of the previously-mentioned models were either subjective ANN, Support Vector Machine (SVM), Naïve Bayes (NB), Decision Trees
[10,12] or did not cover all the failure causes of oil and gas pipelines (DT), Random Forest (RF), and K-Nearest Neighbor (K-NN). Although
[1,4,18,22,23,26,27,30,33,34]. In other words, they lack the objectivity ANN is considered one of the oldest methods, it is still found to be a
in predicting the different failure types of pipelines. As a result, Senouci competitive algorithm among the new ones. For instance, Tahyudin
et al. [31] developed a regression and artificial neural network (ANN) et al. [36] compared the performance of SVM, DT, ANN, NB, and Logistic
models to predict possible failure types for oil and gas pipelines. The Regression (LR) to predict the graduation students on time. The results
model took into consideration the prediction of failure types beside cor- showed that ANN and SVM were the best predictors with an accuracy
rosion, such as mechanical, third party, natural hazard, and operational rate almost 100%. Caruana and Niculescu-Mizil [6] carried out a compar-
failures. The model was built based on a historical data collected from a ison between ten supervised learning algorithms being applied on
report that was prepared by CONCAWE [9]. Later, [32] developed eleven binary classification problems using eight performance metrics.
another model for the same purpose using fuzzy logic technique and It was found that the ANN was among the top five best algorithms.
compared the results with those obtained using the regression and Other studies showed the outperformance of the ANN technique.
ANN models developed by Senouci et al. [31]. The results comparison Mohana and Thangaraj [24] showed that ANN is better than SVM for
showed that the developed fuzzy-based model outperformed the modelling resource state prediction. Prabhakar [29] also showed the
regression and ANN models with respect to model validity. better performance of ANN over SVM in predicting software effort.
Despite the attempts made to predict the failure type of oil pipelines Mollazade et al. [25] compared four different learning algorithms,
considering causes other than corrosion, still none of the previously- namely, ANN, SVM, DT, and Bayesian Network (BN) for grading raisins
mentioned models can be used to assess the condition of pipelines. based on visual features. Results of validation stage showed ANN had
Actually, such models were intended to either predict the corrosion the highest classification accuracy, 96.33%. After ANN, SVM with poly-
rate, pipe leakage, or failure/defect type focusing mostly on corrosion nomial kernel function (95.67%), DT with J48 algorithm (94.67%) and
related factors. In addition to that, the important issues of “interdepen- BN with simulated annealing learning (94.33%) had higher accuracy,
dency” between different factors' relations and “uncertainty” of factors' respectively. On the contrary, Folorunsho [16] used medical dataset to
severity weights were not addressed simultaneously. Furthermore, predict the diabetes probability of any patient using ANN and DT. It
none of the previous studies developed models that can forecast the 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?
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
4. Research methodology
5. Data collection
The developed methodology, which is shown in Fig. 1, started by
performing a brief literature review to search for the different tech- 5.1. Factors affecting oil and gas pipeline condition assessment
niques and studies used by researchers for the condition assessment
of oil and gas pipelines. After that, a comprehensive data collection The factors related to corrosion or third party features are insuffi-
was performed to in two different stages. The first stage was concerned cient to build an accurate condition assessment model. Therefore, it
with the identification of the factors needed to increase the efficiency of is essential to identify other factors affecting pipeline condition. The
the condition prediction process. The second stage included gathering identification process was carried out in three main steps: (1) experts
historical data for different pipeline sizes and types in Qatar based on prepared the most important factors that need to be considered in a
previous inspections' records. The provided inspection dataset did not pipeline condition assessment, (2) another list was subsequently pre-
include all the factors identified in the first stage of the data collection pared from the literature, and (3) a comparison was made between
process. Furthermore, few parameters or factors in the inspections' 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.
factors affecting pipeline condition were then identified. These factors inspection method. On the other hand, the external inspections includ-
were divided into three main groups, namely, physical, external, and ed reports generated from Remotely Operated Vehicle (ROV) inspec-
operational. The physical factors comprise general pipeline characteris- tions and cathodic protection monitoring system. The inspection
tics such as age, wall thickness, diameter, and applied coating condition. reports were provided for two to three different inspection time inter-
The external factors deal with the surrounding environmental condition vals covering the full length of the offshore pipelines. As mentioned ear-
of the pipeline while the operational factors deal with the adapted lier, the provided inspection dataset did not include all the factors
operational strategies for the pipelines. The questionnaire that was identified in the first stage of the data collection process. Moreover,
developed for the factors' identification was sent to 55 experts in oil few factors in the inspections' dataset were not available in the factors
and gas pipelines integrity management. Out of the 55 questionnaires identified previously. As a result, the compatible factors as well as the
sent, 28 completed questionnaires were received out of which only 25 additional factors in the inspections dataset were selected to develop
were taken into consideration from the targeted sample, which repre- the condition prediction models. The factors selected to develop the
sents 45.5% of the total sample. The respondents were asset, inspection, condition prediction models are shown in Fig. 2.
and operation managers as well as onshore/offshore inspection engi-
neers with a technical experience of 6 to more than 20 years. It should 6. Model development
be noted that 22 of the respondents were inspection/operation man-
agers with a technical experience of more than 20 years. It should also The model building procedure is shown in Fig. 3. The historical in-
be noted that the surveys were mainly collected from the Middle-East spection datasets obtained from three pipelines in Qatar were used to
region, mostly from Qatar and Saudi Arabia. represent the factors affecting the pipeline condition. The 11 factors
shown in Fig. 2 were used to build the models. As mentioned before,
5.2. Historical inspection data 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-
Inspections data for three pipelines were collected from a large tional models were developed based only on the transported product
state-owned oil and gas industry corporation in Qatar. The three pipe- type making a total of five models as shown in Fig. 3.
lines were located offshore and were of different sizes and different After studying the inspection data of the three pipelines, it was
steel grades. The main characteristics of the three pipelines are shown found that some factors were not constant across the whole pipeline
in Table 1. Different inspection types were received whether they length. For example, the metal loss depth or the cathodic protection
were internal or external. The internal inspections included reports can be high in a certain sector of the pipeline and low in another. As a
and excel sheets obtained from the Magnetic Flux Leakage (MFL) result, the pipelines were divided into several 100-meter-long
Coating
Metal Loss Condition
Crossings
Diameter
Cathodic
Protection
Operating
Pressure
Joint
Condition Anode
Free Spans Wastage
Support
Condition
segments. For instance, the 24-inch gas pipeline with an inspected However, this time, the 12-inch and 24-inch gas pipelines were treated
length of 85 km was divided into 850 100-meter-long segments. As as oil pipelines by calculating their actual condition using the “oil
shown in Table 1, inspections were carried for the 24-inch gas pipeline model” developed by El-Abbasy et al. [14].
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 6.1. ANN model building
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 The ANN model is developed and analyzed using the Neuroshell
1540, 900, 4990, and 4990, respectively. 2V4.0® package [37], which is a commercially available neural network
The data for the “gas pipeline” model was generated by combining analysis and modeling software. The ANN application framework of the
the data of the 12-inch and 24-inch gas pipelines with the 20-inch oil condition prediction problem is shown in Fig. 3. The inspection data for
pipeline. The 20-inch oil pipeline was treated as a gas pipeline by calcu- selected factors are used to train the ANN in order to obtain ANN-based
lating its actual condition using the “gas model” developed by El-Abbasy condition prediction models. The inspection data points were divided
et al. [14]. This will allow the prediction models to accommodate a randomly into three sets: (1) 60% for training; (2) 20% for testing; and
wider range of different pipelines' diameter and age. The same proce- (3) 20% for validation. The training set is used to train the network
dure was followed again to obtain the data for the “oil pipeline” whereas the testing set is used to test the network during the develop-
model. In other words, the 20-inch oil pipeline data was combined ment/training and also to continuously correct it by adjusting the
together with the 12-inch and 24-inch gas pipeline data into one set. weights of network links. The validation data set, which is not presented
START
(1) 12-Inch Gas Pipes (2) 20-Inch Oil Pipes (3) 24-Inch Gas Pipes (4) Gas Pipes (5) Oil Pipes
Investigated variables
Train Model
Test Model
NO
Testing Successful?
YES
Model Validation
YES
END
Table 3
Condition assessment scale [15].
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
Link 2
SLAB 2
Link 1
Link 4
SLAB 1 Link 3 SLAB 4 SLAB 5
Link 5
SLAB 3
Link 6
rate times the error. For example, if the learning rate is 0.5, the weight network to the next layer in back propagation networks, the values
change is one half the error. Large learning rates often lead to oscillation are modified by a weight value in the link that represents connection
of weight changes and learning never completes, or to a convergence to strengths between the neurons.
a non-optimum solution. One way to allow faster learning without os- Finally, the training criteria include fixing the maximum and mini-
cillation is to make the weight change as a function of the previous mum absolute error and the number of training cycles without improve-
weight change to provide a smoothing effect. The momentum factor ments. When the given training criteria are met, the model training is
determines the proportion of the last weight change that is added into stopped. If the training criteria are not met, it is suggested to either
the new weight change. As neurons pass values from one layer of the change the activation functions or retrain using different architecture.
Table 4
Models' design parameters and training criteria.
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
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
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
mended in literature [2,40]. Eqs. (1) and (2) show the average validi-
Relative variables' contribution factors and ranking.
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
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.
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
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
8
7
6
5
4
3
2
1
0
0 100 200 300 400 500 600 700 800 900 1000
Event Number
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
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
8.5
PIPE CONDITION
7.5
6.5
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
and independent variables as well as the correlation between the impact on the pipeline condition. For this purpose, the values of the
factors affecting the pipeline condition. studied factor were varied whereas the values of the other factors
Fig. 5 shows the “actual versus predicted output plot” results for the were kept constant at their average values. The data was presented to
five developed models. It is observed that the predicted values by the the developed models to predict new outputs. The pipeline conditions
developed models are within the acceptable limits and scattered around were obtained using the prediction models. Since there were no varia-
the actual values of response variable. In other words, the majority of tions in any factor other than the one studied, the variations observed
the results obtained are matching with few instances of disagreement. in the predicted pipeline conditions were under the exclusive influence
Therefore, the validation test results are satisfactory. 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-
8. Deterioration curve building dition were determined.
It is also important to express graphically the impact of each fac-
A sensitivity analysis is executed in order to test the developed tor on the pipeline condition. As a result, deterioration curves were
models' sensitivity to changes in their inputs. For each model, the developed for each model as shown in Figs. 6 to 10. These deteriora-
input variables were varied one at a time to determine their respective tion curves give a clearer understanding of the interrelationships of
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
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
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
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
pipeline future condition and the studied factors. As shown in the pipeline condition by protecting it against corrosion. Finally, well main-
mentioned figures, each deterioration curve set was separated into tained supports and joints condition achieves a better structural perfor-
two groups of factors, namely, directly proportional and inversely mance of the pipeline.
proportional. On the other hand, the second group shows only the factors that
The first group shows only the factors that have a positive impact on have a negative impact on the pipeline condition. The factors in this
the pipeline condition. The factors in this group are the diameter, the group are the age, the metal loss, the anode wastage, the operating
coating condition, the cathodic protection, the support condition, and pressure, the crossings, and the free spans. The impact of age on pipeline
the joint condition. Smaller pipeline diameters have usually higher condition is negative in nature. An increase of the metal loss depth as a
probability of failure than those with larger ones [39]. This is possibly percentage of its pipeline wall thickness due to corrosion or mechanical
because smaller standard dimension ratios (SDR) affect the structural damage degrades pipeline condition. As galvanic anodes waste, their
performance of pipelines and make them more vulnerable to external sizes decrease; resulting in a decrease in their well-known sacrificial
impact and third party damage. In addition, smaller diameter pipelines, action to protect the pipeline from corroding. Maximum allowable
which have thinner wall thicknesses, allow faster corrosion rate. Good operating pressure (MAOP) decreases the pipeline condition when it
and well maintained coating and cathodic protection enhances the 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
PIPE CONDITION
8.5
7.5
6.5
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
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
pipeline. Finally, as the number of other crossing and free spans shown in each deterioration curve. For example, let us assume that the
increase, the pipelines become less stable. effect of the “coating condition” factor on the pipeline condition is
As shown in Figs. 6 to 10, the vertical axis represents the predicted studied for the “20-Inch Oil pipelines”. Let us also assume that the target
pipeline conditions while the horizontal axis the impact factor. Since all coating condition percentages are 20 and 60%. Therefore, simply by using
the factors do not have the same units, the horizontal axis of the Fig. 7, the user will select the 0.2 and 0.6 normalized values on the hori-
deterioration curves are plotted using a normalized scale from 0 to 1 as zontal axis and read the corresponding predicted pipeline condition for
explained in Table 2. However, for better visualization to the reader, each case using the underneath table for the coating condition factor.
the real values of the factors (age, diameter, crossings, cathodic protec- Alternatively, the user can just hit the “coating condition” curve for each
tion, and free spans) are listed below their corresponding normalized case and accordingly read the predicted pipeline condition from the
values as shown in Figs. 6 to 10. The real values of the remaining factors vertical axis. Based on that, the predicted pipeline conditions for coating
(metal loss, coating condition, operating pressure, anode wastage, sup- condition of 20 and 60% will be 6.93 and 7.72, respectively. As a reminder,
port condition, and joint condition) are not listed since they are the these results are based on the average values of factors other than the
same as the normalized values. In addition, the corresponding predicted “coating condition”. The same procedure can be followed to check or
pipeline condition values to each factor's different values are tabulated as 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
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
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
Besides examining the impact of changing each factor on the pipe- deterioration profiles shown in Fig. 11 does not take into account any
line condition, additional deterioration curves were developed—for oil kind of rehabilitation action that may take place during the pipeline op-
and gas pipelines—to show the effect of changing all the factors togeth- eration. Also, due to the lack of inspections data received, the accuracy
er. These curves were developed by changing simultaneously all the of the deterioration profiles can be enhanced throughout receiving
factors normalized values starting from their best possible to their more additional inspections data.
worst effects on the pipeline condition as shown in Fig. 11. For more According to the developed deterioration curves, it can be observed
clarification, the curves were built by first increasing the age factor by that the “cathodic protection” and “coating condition” factors have the
one year starting from zero. Simultaneously, the metal loss, coating con- highest positive impacts on the pipeline condition while the “diameter”
dition, cathodic protection, crossings, anode wastage, free spans, joint factor has the lowest positive impact. On the other hand, the “metal loss”
and support condition factors were changed proportionally according and “crossings” factors have the highest and lowest negative impacts on
to their rate of increase or decrease based on the received historical the pipeline condition, respectively. This indicates that the corrosion re-
inspection data. However, both the factors of diameter and operating lated factors (cathodic protection, metal loss, and coating condition) are
pressure were kept constant. The effect of such periodical change in the most important contributors to the pipeline condition prediction.
the factors' values was determined by calculating the pipeline condition However, other factors including age, support condition, joint condition,
each year using the developed model. It should be noted that the 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
[4] C. Bersani, L. Citro, R.V. Gagliardi, R. Sacile, A.M. Tomasoni, Accident occurence
7 evaluation in the pipeline transport dangerous goods, Chem. Eng. Trans. 19
6 (2010) 249–254.
[5] M. Bertolini, N. Bevilacqua, Methodology and theory oil pipeline cause analysis a
5
classification tree approach, J. Qual. Maint. Eng. 12 (2) (2006) 186–198.
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.
[7] A.A. Carvalho, J.M.A. Rebello, L.V.S. Sagrilo, C.S. Camerini, I.V.J. Miranda, MFL signals
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 70 [8] J. Cheng, A.N. Tegge, P. Baldi, Machine learning methods for protein structure
AGE (Years) prediction, IEEE Rev. Biomed. Eng. 1 (2008) 41–49.
[9] P.M. Davis, J. Dubois, F. Gambardella, F. Uhlig, Performance of European Cross-
GAS PIPES OIL PIPES 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
Fig. 11. Deterioration profiles. 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
prediction as they together represent around 40% of their contribution (AHP-FTA), Proceedings of the 7th International Probabilistic Workshop, Delft,
Netherlands, 2009.
strength. Also, operating pressure has a significantly higher effect on [12] P.K. Dey, A risk based model for inspection and maintenance of cross country
“gas” pipeline condition than on “oil” pipelines. 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.
9. Conclusions [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
A study on the condition prediction of oil and gas pipelines was con- 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-
ducted. Twenty quantitative and qualitative factors having a major im- tion models for oil and gas pipelines using regression analysis, ASCE J. Constr. Eng.
pact on the condition of oil and gas pipeline were identified of which 11 Manag. 140 (6) (2014).
were used in this study. The ANN technique was used to develop five [16] O. Folorunsho, Comparative study of different data mining techniques performance
in knowledge discovery from medical database, Int. J. Adv. Res. Comput. Sci. Softw.
condition prediction models with respect to pipeline size and type of
Eng. 3 (3) (2013) 11–15.
transported product. The developed models are based on historical [17] R. Goodland, Oil and Gas Pipelines Social and Environmental Impact Assessment:
inspection data collected from three different offshore pipelines in 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
Qatar. The collected data were prepared, organized, and subsequently
Pipelines in Mexico, Proceedings of the 3rd Pan American Conference for Nonde-
used to train, test, and validate the models. The coefficient of determina- structive Testing (PANNDT), Rio de Janeiro, Brazil, 2003.
tion (R2) results for the developed models were between 99.04 and [19] L. Jinhai, Z. Huaguang, F. Jian, Y. Heng, A new fault detection and diagnosis method
99.59%. In addition, all other necessary statistical diagnosis have been 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.
checked showing sound results for the developed models. The models [20] M. Kalanaki, J. Soltani, Performance assessment among hybrid algorithms in tuning
have been validated and the results showed their robustness with an SVR parameters to predict pipe failure rates, Adv. Comput. Int. J. 2 (5) (2013) 40–46.
average validity percentage between 97.40 and 98.40%. The developed [21] J.L. Kennedy, Oil and Gas Pipeline Fundamentals, 2nd edition PennWell Publishing
Company, Oklahoma, 1993.
ANN models were compared with previously developed regression [22] S.X. Li, S.R. Yu, H.L. Zeng, J.H. Li, R. Liang, Predicting corrosion remaining life of
models that serve the same purpose of this study. It was found that the underground pipelines with a mechanically-based probabilistic model, J. Pet. Sci.
performance of both techniques were close to each other, however, the Eng. 65 (3–4) (2009) 162–166.
[23] K. Liao, Q. Yao, X. Wu, W. Jia, A numerical corrosion rate prediction method for direct
ANN technique provided better results. Finally, a sensitivity analysis assessment of wet gas gathering pipelines internal corrosion, Energies 5 (10) (2012)
was carried out in order to build deterioration curves for the models de- 3892–3907.
veloped. The deterioration curves show the degree of the individual effect [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,
of each factor on the pipeline condition. Cathodic protection and coating
J. Comput. Sci. 9 (10) (2013) 1283–1294.
condition were found to have the highest positive effect on the pipeline [25] K. Mollazade, M. Omid, A. Arefi, Comparing data mining classifiers for grading
condition while metal loss have the highest negative effect. On the raisins based on visual features, Comput. Electron. Agric. 84 (2012) (2012)
124–131.
other hand, diameter and crossings were found to have the lowest posi-
[26] N.M. Noor, N.A.N. Ozman, N. Yahaya, Deterministic prediction of corroding pipeline
tive and negative effects on the pipeline condition, respectively. The remaining strength in marine environment using DNV RP—F101 (Part A), J. Sustain.
models are expected to help pipeline operators to assess and predict Sci. Manag. 6 (1) (2011) 69–78.
the condition of existing oil and gas pipelines and hence prioritize their [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
inspections and rehabilitation planning. (2010) 246–263.
[28] X.Y. Peng, P. Zhang, L.Q. Chen, Long-Distance Oil/Gas Pipeline Failure Rate Prediction
Acknowledgments 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.
The authors gratefully acknowledge the support provided by [29] M.D. Prabhakar, Prediction of software effort using artificial neural network and
Qatar National Research Fund (QNRF) for this research project under support vector machine, Int. J. Adv. Res. Comput. Sci. Softw. Eng. 3 (3) (2013)
40–46.
award No. QNRF-NPRP 09-901-2-343. The authors would also like to [30] C.Y. Ren, W. Qiao, X. Tian, Natural gas pipeline corrosion rate prediction model
acknowledge the operational pipeline engineers of Qatar Petroleum based on bp neural network, Adv. Intell. Soft Comput. 147 (2012) 449–455.
for their invaluable suggestions and recommendations. [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.
References [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).
[1] M. Ahammed, Probabilistic estimation of remaining life of a pipeline in the presence [33] M. Singh, T. Markeset, A methodology for risk-based inspection planning of oil and
of active corrosion defects, Int. J. Press. Vessel. Pip. 75 (4) (1998) 321–329. 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 65
[34] S.K. Sinha, M.D. Pandey, Probabilistic neural network for reliability assessment [38] H. White, Learning in artificial neural networks: a statistical perspective, Neural
of oil and gas pipelines, Comput. Aided Civ. Infrastruct. Eng. 17 (5) (2002) Comput. 1 (4) (1989) 425–464.
320–329. [39] P. Wilson, D. Wheeler, R. Wilson, R. Coleman, N. Wolfe, An Assessment of Low
[35] M. Tabesh, J. Soltani, R. Farmani, D. Savic, Assessing pipe failure rate and mechanical Pressure Crude Oil Pipelines and Crude Oil Gathering Lines in California, California
reliability of water distribution networks using data-driven modeling, J. Hydroinf. 11 State Fire Marshal (CSFM), Sacramento, April 1997.
(1) (2009) 1–17. [40] T. Zayed, D. Halpin, Deterministic models for assessing prod. and cost of bored piles,
[36] I. Tahyudin, E. Utami, A. Amborowati, Comparing Classification Algorithm of Data Constr. Manag. Econ. 23 (5) (2005) 531–543.
Mining to Predict the Graduation Students on Time, Information Systems Interna- [41] A.W. Dawotola, P.H.A.J.M. VanGelder, J.K. Vrijling, “Risk Assessment of Petroleum
tional Conference (ISICO), Bali, Indonesia, 2013. Pipelines using a combined Analytical Hierarchy Process: Fault Tree Analysis
[37] Ward Systems Group Inc., Neuroshell 2V4.0, Computer Software http://www. (AHP-FTA)”, Proceedings of the 7th International Probabilistic Workshop, Delft,
wardsystems.com/neuroshell2.asp 1996 surfed at 5 July 2013. The Netherlands, 2009.