Journal of Pipeline Systems Engineering and Practice

Ground-penetrating radar (GPR) is a nondestructive tool that has gained popularity after giving promising results in different areas—such as utility engineering, transportation engineering, civil engineering, and geology—with relatively low cost. Even as the number of applications for GPR increases, the interpretation of GPR data is still challenging, in part due to varying ground conditions. Researchers are continuously working on the development of new analysis methods to address these challenges. Computer vision algorithms, including neural networks and convolution neural networks, have advanced significantly over the past decade, and researchers have utilized these algorithms to extract information from GPR images and thus improve the interpretation of GPR data. This paper presents a review of literature that employs computer vision and machine learning algorithms, such as YOLO V3, Viola–Jones, and AlexNet, for automatic extraction of information from GPR images. The uptake in the use of automatic detection algorithms for GPR is increased by the ability to rapidly quantify and locate buried targets that previously could only be identified by professionals with a high level of expertise and training.

Residual stress and cracks after welding are widespread mechanical defects in gas and oil pipelines. Internal pressures cause crack propagation and reduce the fatigue life of pipelines. This study developed a new procedure, based on an extended isogeometric analysis (XIGA) to investigate the effect of welding residual stress and cyclic internal pressure on the crack propagation rate and fatigue life. A new approach based on a thermo elastic-plastic equation is introduced for residual stress analysis. The fundamental aspect of this approach is determining the redistribution of residual stress while the crack is growing, and computing the stress intensity factor (SIF) in the residual stress field. Grid points around the crack surface and crack front are identified by the level set method. Then, discontinuous enrichment functions are added to the XIGA approximation. Thus, remeshing is not required in this method. The residual stress results calculated by the presented numerical method are in good agreement with the hole-drilling strain-gage method results. The interaction integral method was used to extract SIF. The superposition method was employed to consider the effect of welding residual stress and cyclic internal pressure on the SIF. Also, the modified Walker equation was used to calculate the fatigue life caused by cyclic internal pressure and welding residual stress. To validate the results, the same analysis was performed using the finite element method. The results of the presented method are in good agreement with finite element method (FEM) results.

A novel mitigation technique is proposed in this paper to effectively improve the safety and integrity of buried pipelines subjected to ground deformation and to mitigate the detrimental effects of ground deformation on the pipe. This technique involves the installation of special geomaterial blocks (SGBs) adjacent to the pipe. The SGB consisting of multiple layers of hollow plastic boxes placed between layers of high-density expanded polystyrene (EPS) geofoam blocks forms a thick sandwich panel structure, which is oriented such that its orthotropic mechanical property allows the pipe to move laterally without developing significant reactions against the soil. A summary of past mitigation techniques and the method proposed in this study are first presented. Large-scale experimental testing used to assess the beneficial effects of the SGB on the pipe response when subjected to lateral and oblique displacements is then presented, followed by a simplified finite element model proposed to numerically simulate the pipe-SGB-soil interaction under lateral soil displacement. The results confirm that the proposed remediation method can significantly reduce the soil-pipe interaction force. Furthermore, the proposed beam-based numerical model that can be used in engineering design predicts well the lateral load-deformation response of the system.

In-pipe intelligent isolation plugging tools (IPTs) are crucial in pipeline maintenance. During the plugging process, the flow field around the IPT changes drastically, resulting in vibration and instability of the plugging process. Therefore, three foldable spoilers were designed at the tail of the IPT to reduce the vibration of the IPT. First, a disturbing flow experiment of IPT with spoilers was designed. A mathematical model of the pneumatic spoiler control system was established to regulate the spoiler angles. Second, based on the experimental data, a bidirectional long short-term memory (Bi-LSTM) neural network predictor between the plugging states, the spoiler angles, and the pressure gradient was established. Then, an adaptive dynamic programming controller was designed to select the optimal control action for each plugging state, thereby reducing the pressure gradient. Finally, Python and MATLAB/Simulink were used for simulation. The results showed that prediction errors were controlled within 9%, and the controller could reduce the pressure gradient during the plugging process by an average of 25.94%, which alleviated the vibration of the IPT and achieved a smooth plugging operation.

In the construction of pipe jacking, the calculated jacking force is often greater than the actual measured value. In particular, the deviation between calculated and actual frictional resistance is large. Moreover, during the jacking process, the complex frictional behavior between the pipe and soil has not been fully understood. Therefore, this work aims to reveal the frictional properties and calculate the friction coefficient of the concrete pipe–soil interface. To that end, the frictional behavior and mechanical mechanism were investigated between seven types of soil and concrete pipe under different contact conditions (primarily considering three factors of shear rate, normal stress, and slurry lubrication) through direct shear tests. The test results show that the residual shear stress of the concrete-sand interface increased and then decreased with the increase in sand particle size. With the increase of normal stress, the shear displacement when the shear stress of the concrete-soil interface reaches the peak or stable value increases. Under the low normal stress, the shear rate has little effect on the shear stress of the concrete-soil interface. Under slurry-lubricated conditions, the shear stress of the concrete-sand interface can be reduced by 60%–80%, and the shear stresses of the concrete–silty clay interface and the concrete-clay interface can be reduced about 90%.

Long-distance oil pipelines consume extensive energy during the operation. Accurate prediction of pipeline’s energy consumption is the basis of intelligent management and energy-saving plan. This work demonstrates an effective data-driven model to predict a pipeline’s energy consumption. The model first extracts features through correlation analyses and then uses a hybrid support vector machine for prediction. In the hybrid model, the fruit fly optimizer, simulated annealing algorithm, and cross factor are fused to form an improved fruit fly optimizer used to optimize the traditional support vector machine. The proposed model is tested on a pipeline in China, and the results indicate that the model has a high prediction accuracy (prediction accuracy is measured by one minus mean absolute percentage error, and the accuracy exceeds 80%). Compared with the three benchmark models, the accuracy of the proposed model is increased by 4.18%–25.47%. This paper discusses the influence of the kernel function on the prediction. The results show that the support vector machines with radial basis kernel function and polynomial kernel function perform well in Dataset I, while support vector machines with radial basis kernel function, polynomial kernel function, and linear kernel function perform almost the same in Dataset II. Moreover, this paper also discusses the input of the model on a deeper level. More experiments show that removing highly repetitive input can ensure higher prediction accuracy in engineering and reduce the complexity of the model.

Operational monitoring of pipelines can prevent environmental and economic losses. However, pipeline data have the characteristics of high dimension and nonlinear coupling, which makes it difficult to determine the relationship between the data and process, resulting in a high rate of misjudgment of the operating condition. To address this issue, an operating condition recognition model based on kernel principal component analysis (KPCA)-convolutional neural network (CNN) is proposed. Deeppipe refers to the use of deep learning algorithms to solve pipeline-related problems. Considering the spatial and time-series characteristics of the pipeline, the inlet and outlet pressure matrixes of the initial station, intermediate station, and terminal station are constructed. Subsequently, the features of the pressure matrix in the time domain, frequency domain, and energy domain are extracted. KPCA is employed to obtain the reconstructed feature matrix, which is used as the input of the proposed CNN recognition model. Taking two multiproduct pipelines as examples, the effectiveness of the KPCA-CNN recognition model is verified while compared with traditional nonlinear classification models (e.g., artificial neural network, decision tree, random forest, and others). The results show that the proposed model has the highest accuracy, precision, recall, and F1 score, and all reach 100%, which has a certain guiding significance for the monitoring and management of onsite pipelines.

In the gas-gathering pipeline networks in gas fields, launching pigs in the downstream pipeline causes dramatic fluctuations in the gas transportation volume and pressure in upstream pipelines. It is important to shorten the launching period of pigs for the safe and smooth production of pipeline networks. In this study, a hydraulically activated power launching (HAPL) method was proposed based on the hydraulically activated power pigging (HAPP) method. Based on the proposed HAPL method, the launcher structure was designed. Then, a nonlinear dynamics model for launching pigs was established and relevant parameters were simulated. The simulation results showed that the launching period with the HAPL method was 76.5% shorter than that of the pneumatically activated power launching (PAPL) method under the same conditions.

Feasibility and suitability assessments have become increasingly important for trenchless projects, as some Federal and State permitting agencies have released guidance on the information required to complete their environmental review. The Federal Energy Regulatory Commission (FERC) released guidance in October 2019, and the Pennsylvania Department of Environmental Protection (PADEP) released a draft Trenchless Technology Technical Guidance Document for use by project applicants when considering trenchless crossing methods in the Commonwealth of Pennsylvania. For complex trenchless installations and those that involve multiple permitting agencies with different guidelines, adherence to these guidelines has become increasingly important in avoiding or minimizing potential permitting and project delays. This paper reviews the requirements established by FERC and PADEP as a case study that may be indicative of the regulatory trend emerging in various jurisdictions across the nation. Public data research, geohazards evaluation, geophysical evaluation, and geotechnical investigation are describe, while following both the FERC and PADEP trenchless technology guidelines. Finally, this paper demonstrates the consolidation of data gathering and engineering analysis to select the most practical and least impacting trenchless alternative.

With the rapid development of utility tunnels, fire safety after construction is increasingly important, especially in the cable compartment. An intelligent fire detection method based on the particle swarm optimization algorithm was proposed for fire state estimation of the utility tunnel, including the fire source location, the maximum temperature value, and the temperature attenuation coefficient. Additionally, a corresponding sensor optimization strategy was also established. The dispersion coefficient of the fire source location was defined as the judgment criteria of sensor optimization. The validity of the proposed algorithm and the sensor optimization strategy were demonstrated in the application of a full-scale experimental example. The maximum errors of the identified fire source location and the maximum temperature value after sensor optimization were 34.7164 m and 8.5403°C, respectively. The total number of temperature sensors was reduced by more than 50%. The proposed intelligent fire detection algorithm can provide precise guidance for fire protection and extinguishing plan. Particularly, the sensor optimization strategy can economize the cost of temperature sensors.

The aim of this study was to test the feasibility of the distributed temperature sensing (DTS) method, which is based on Raman scattering, for detecting small leakages of tap water pipes. The temperature drop caused by water leakage was measured by DTS. A water pipe leakage sources method based on selective average threshold was proposed to capture temperature drop and locate tap water leakage points. The tests to detect leakages and to identify their locations in tap water pipes were conducted in lab-scale, medium-scale, and field-scale experiments. The medium-scale test demonstrated that DTS performed well with water pipes of different materials with multiple leakage points. The field trial results showed that DTS identified water leakage in the cast iron pipe with 0.5-m location error.

Buried high-density polyethylene (HDPE) pipes are widely used in solid waste landfills, heap-leach mining pads, large earth dams, and other infrastructures. Large earth pressures and elevated temperatures in these applications can lead to the failure of HDPE pipes, resulting in pipes plugged in the drainage system and increases in the leachate level. High leachate levels contribute to landslides in landfills. Based on the theory of elasticity, a plane strain pipe-soil interaction model was developed to investigate the deformation characteristics of HDPE pipes while considering the influence of temperature. Analytical solutions were obtained under perfectly smooth and fully bonded interfaces. The solutions and calculated results were verified using the Höeg formula and the results of laboratory tests. The results show that the Höeg formula is applicable to pipes with a standard dimension ratio (SDR = nominal diameter/wall thickness) greater than 40. In contrast, the analytical solutions obtained in this paper are relatively accurate for calculating the deformation characteristics of pipes when the SDR of the pipes is less than 40, as in the case of most landfills. A parametric analysis was conducted, and implications for landfills were analyzed. Furthermore, simplified equations were derived for landfill design, and preliminary suggestions were provided regarding the waste height control and temperature regulations in landfill operations. To ensure the safety and stability of HDPE pipes and to avoid environmental damage, the maximum waste temperature of the landfill should be regulated under a certain waste height, and the waste height should be controlled against a given maximum waste temperature. According to the simplified equations, the security of the drainage system can be evaluated with monitored waste height and temperature, and pipes plugged in the drainage system could be avoided.

Sediment deposition impacts the hydraulic capacity of a channel in urban drainage and sewer systems. To reduce the impact of this continuous deposition of sediment particles, sewer systems are typically designed with a self-cleansing mechanism to keep the bottom of the channel clean from sedimentation. Therefore, accurate prediction of the particle Froude number (${\text{F}}_r$) is important in designing sewer systems. This study used five data sets available in the literature, comprising wide ranges of the volumetric sediment concentration ($C_v$), dimensionless grain size of particles ($D_{gr}$), sediment median size ($d$), hydraulic radius ($R$), pipe friction factor ($\lambda$) for the condition of nondeposition with deposited bed. Five different input variable combinations were considered for the prediction of ${\text{F}}_r$. Four boosting machine-learning models, i.e., AdaboostRegressor, GradientBoostingRegressor, CatboostRegressor, and LightGBMRegressor, were developed, and the results obtained were compared with the existing empirical equations as well as state-of-the-art approaches proposed in the literature. To evaluate the proposed models, several performance metrics were used, such as index of agreement ($I_d$), mean absolute error (MAE), root-mean-square error (RMSE), $R^2$, and adjusted $R^2$. AdaboostRegressor ($I_d=0.981$, $\mathrm{MAE}=0.483$, $\mathrm{RMSE}=0.591$, $R^2=0.940$, and adjusted $R^2=0.937$) provided better results, followed by GradientBoostingRegressor, CatboostRegressor, and LightGBMRegressor. The boosting techniques used in this study performed better than multigene genetic programming, gene expression programming, multilayer perceptron (MLP), and the empirical equations proposed in the literature, indicating superior performance.

Water distribution systems (WDSs) are crucial urban infrastructures playing major roles in maintaining the social and economic functions of modern cities. Understanding the operation condition contributes to daily maintenance, asset management, and future planning for decision makers. This study statistically analyzes the operation condition of WDSs in a large city in China by using pipe basic and failure databases collected from local sectors. For the basic database, the distribution rules of pipe attributes, including region, material, depth, diameter, and joint type, are studied. For the failure database, the failure regions, occurrence times, types, and causes are analyzed. The relationships between failure percentages and pipe attributes are discussed, and the corresponding failure rates are calculated. The WDS is complex in the diversity of pipe materials, diameters, and joint types. Corrosion, aging, and temperature-related extreme weather are summarized as three main failure causes through the statistical analysis of the pipe failure database. Pipes with low depth, extended service period, small diameter, and hot melt joint have large failure percentages and rates. These findings demonstrate the current operation condition of WDS and contribute to failure prediction and asset management for decision makers.

This paper discusses the main causes of the severe deterioration of prestressed concrete cylinder pipes (PCCPs) used for potable water distribution in northeastern Morocco. A diagnostic study and in situ and laboratory tests were performed to gain some insight into the causes of the deterioration of PCCPs. Overall, it was found that the failure of PCCPs in the region is primarily the result of improper pipe joint installations, which allow water to leak from the pipes, allowing chlorides in the mortar coating to reach the prestressing wires inside the pipes and causing their corrosion. The mortar used to spray the prestressing wires was found to have been contaminated with chlorides during mixing by way of the mixing water, sand, and/or aggregates. The presence of sulfate ions in the mortar coating and the cyclical wetting and drying conditions of the region further accelerated corrosion rates. It was also found that poor bedding of pipes in the region’s marl soil resulted in differential settlement, causing high stress at joints, leading to cracking of the mortar coatings and corrosion of the prestressing wires and cylinders. The soil surrounding the pipes was, however, not found to be aggressive and there was no groundwater (at the buried depth of the PCCPs of approximately 2 m). The overall durability exposure class for the region was identified both as “cyclic wet and dry” and “moderately aggressive chemical environment” according to the Moroccan and European concrete standards.

Robust design optimization (RDO) of an existing underground reinforced concrete pipe subjected to seismic load is presented. The pipe considered is from a straight section of a water transmission pipeline system located in Kolkata City, India. Ovaling deformation due to earthquake is considered in the RDO. The seismic effect has been estimated by a “simplified” model based on beams on elastic foundation subjected to sinusoidal seismic waves, and validated with a more detailed nonlinear time-history analysis of the finite element model of pipe. Generally, underground structures are designed considering all parameters to be deterministic. However, along with the random seismic load, there are other parameters that are random and chaotic. To consider those, the RDO has been executed in the following two separate modules: (1) under probabilistic uncertainty; and (2) with uncertain-but-bounded (UBB) type parameters (as many system parameters cannot be ascertained accurately with their prevailing statistics). The deterministic design optimization problem is cast as a cost minimization problem subjected to moment, shear, axial thrust, and crack control constraints. The uncertainty is incorporated by Monte Carlo simulation (MCS). The probabilistic RDO case is formulated by the weighted sum method and the penalty function approach, whereas the UBB-based RDO is posed through hyperellipsoidal convex programming. The results of RDO with probabilistic parameters, UBB parameters, and the ASCE and British code-based deterministic approaches are compared. The results show that the RDO yields design solutions that require marginally higher costs than the conventional ASCE or British code-based design, even when considering the seismic effect. With the RDO approach, optimal design solutions become insensitive to uncertainty effects. It has been observed that, by accepting a marginal increment in costs, a designer can achieve a reliable, sustainable, and economical solution through the present RDO approach.