Pipe Inspection Research Articles

Anomaly detection from images in pipes using GAN

In recent years, the number of pipes that have exceeded their service life has increased. For this reason, earthworm-type robots equipped with cameras have been developed to perform regularly inspections of sewer pipes. However, inspection methods have not yet been established. This paper proposes a method for anomaly detection from images in pipes using Generative Adversarial Network (GAN). A model that combines f-AnoGAN and Lightweight GAN is used to detect anomalies by taking the difference between input images and generated images. Since the GANs are only trained with non-defective images, they are able to convert an image containing defects into one without them. Subtraction images is used to estimate the location of anomalies. Experiments were conducted using actual images of cast iron pipes to confirm the effectiveness of the proposed method. It was also validated using sewer-ml, a public dataset.

Dynamic simulation research of adaptive support mechanism of pipeline inspection robot based on ADAMS

The drainage pipe contains plenty of toxic gases that are hazardous to the human body, and the narrow size of the drainage pipe makes manual inspection difficult, so it is necessary to use a robot to replace the manual inspection of the drainage pipe. For this purpose, this paper designs a pipe inspection robot that can smoothly realize the passage and inspection in the drainage pipe. With an adaptive support mechanism, the robot can move to the working position in the pipeline. The trajectory of the end of the support mechanism is planned, and the dynamics of the support mechanism are simulated by ADAMS to analyze the motor load to verify that it can cope with the complex environment of the drainage pipe.

Battery-powered FPGA-based embedded system for ultrasonic pipe inspection and gauging systems.

A water-immersible battery-powered field programmable gate array (FPGA)-based embedded system is a most suitable tool required to check the health of the pipe operating under harsh conditions. A novel, water-immersible, battery-powered, compact, stand-alone and FPGA-based embedded system has been designed and developed, which is suitable for ultrasonic pipe inspection and gauging systems useful for major applications in the petrochemical and nuclear industries. The developed FPGA-based embedded system is operated with lithium-ion batteries for more than five hours, and the IP67-grade system modules are capable of floating inside the pipe along with the flow of oil or water. Such applications require a system that is capable of acquiring large data under water-immersed conditions of battery-operated instrumentation. The onboard Double Data Rate (DDR) RAM of the FPGA module has been utilized for the storage of the 256 MBytes streams of A-scan data during evaluation for more than five hours. The experimentation of the battery-powered embedded system was carried out inside two samples of SS and MS pipes with the help of the in-house developed nylon inspection-head installed with two sets of spring-loaded eight Teflon balls and two 5MHz focused immersion transducers placed along the circumference at 180° apart. This paper provides brief details of the design, development, and evaluation phases of the battery-powered water-immersible embedded system suitable for ultrasonic pipe inspection and gauging, which can be expanded to 256 channels for demanding applications.

Torsional mode magnetostrictive patch transducer with TPSMs for liquid-filled pipes inspection

T (0,1) mode guided waves have no axial or radial vibration displacement. Therefore, the energy leakage is small in liquid-filled pipes, which is suitable for detecting the axial defects of the liquid-filled pipes. Fe–Co materials with high magnetostriction coefficient is fabricated. Its magnetic properties are tested. The size and distribution of static magnetic fields generated by different permanent magnets are verified by simulation. A new torsional mode guided wave magnetostrictive patch transducer with tile-shaped permanent magnets for defect detection of the liquid-filled pipes is proposed. The detection effect of the transducer on the liquid-filled pipes under different pressures is tested through experiments. The proposed transducer consists of four tile-shaped permanent magnets, eight triangular yokes, a coil, and two magnetostrictive patches. Four groups of tile permanent magnets are symmetrically distributed around the patch according to the polarity. Magnetic yokes are installed at both ends of each group of tile permanent magnets. The experiment verified that the magnetostrictive patch transducer realize the excitation and reception of guided wave signals in the magnetostrictive patches. The amplitude and signal-to-noise ratio of echo signals is improved. The position of pipe defects is determined according to the propagation time of guided wave. The influence of different pressures in the liquid-filled pipes on the amplitude of guided wave is verified.

Translational Calibration for Contact Type Three-Dimensional Position-Measuring Instruments

In Japan, as the number of sewerage management facilities increases, continuous maintenance of drainage pipes and sewage pipes is considered important. However, it is grinding for operators to perform the expansive in-pipe inspection. Therefore, in recent years, inspections using stand-alone type piping inspection robots have been actively used. Inside of the pipe, there are disturbances such as unevenness, sludge, or dents at pipe joints which cause slips and tumbles of the robot. Therefore, the conventional ways of approaching those disturbances have been adjusting the size of the robot and tires according to the diameter of the pipe to prevent tipping over. We are exploring tip-over prevention measures by the software approach through advanced straight-ahead control. Currently, we are in the stage of verifying the self-position estimation necessary to realize straight-ahead control, and equipment for that purpose is required. However, to measure the position and posture of the robot inside the curved pipe, a special three-dimensional position-measuring device is required. Therefore, we have developed a three-dimensional position-measuring instrument for pipe inspection robots, but there is still an error in the absolute positioning accuracy. In this paper, to solve this error problem and make it precise, we propose a method to apply the calibration method used in the manipulator to the measuring instrument. Also, the kinematic model and its calibration parameters are explained, and a method of deleting unnecessary redundant parameters and parameter estimation by Newton's method is presented. Furthermore, in a comparative verification using a measuring instrument proposed in the paper, the positional accuracy after calibration is within a range of approximately ±1.0 mm, and the variation is also within a range of ±0.5 mm, which shows that the proposed method is effective.

Digital assistances in remote operations for ITER test blanket system replacement: An experimental validation

Removal/reinstallation of all Test Blanket System (TBS) equipment present in the Port Cell is required during the ITER Long Term Shutdown. TBS shall be designed so that occupational radiation exposure can be As Low As Reasonably Achievable (ALARA) over the life of the plant to follow the ITER Policy. The expected level of radiation in this area still allows performing maintenance tasks hands-on. However, the cumulated dose could be significant for operators. Classical Dose Reduction Measure (DRM) is to deploy Remote Handling systems. Consequently, use of robotized equipment, remotely operated means or collaborative robotics, have been investigated. Taking advantage of new digital technologies such as digital assistances, is expected to help operators during complex remote operations under limited vision conditions. Experiments were performed on a set of three TBS maintenance representative tasks: remote visual inspection of DN80 pipe, dye penetrant testing operation on pipe and dexterity test. A panel of remote handling equipment operators of different skill level was selected and involved onto these tasks. The results prove without ambiguity that for all operators the quality of the task execution is significantly improved when using digital assistances

Locating block caused by stuck PIGs in multi product pipeline using combination of radioisotope techniques

Blockages in pipelines inhibit the normal use of the pipeline due to constricted flow of fluid through the pipeline. Locating blockages in pipelines is a challenge and there is an increasing demand for sensitive inspection methods to locate blockages in pipelines, caused either due to presence of foreign undesired material during commissioning or maintenance of the pipeline or due to accumulation of product remanent during the prolonged use of the pipelines. A block was caused in a multiproduct pipeline due to a stuck pig (pipe inspection gauge). Radiotracer techniques viz. gamma scanning and radiography were employed to pinpoint the block location.

Design and Development of Robot for Industrial Pipe Cleaning and Inspection

Nowadays many industries used different diameter pipes for different applications like carrying chemicals, high-pressure steam, and gasses hence there may be chances of problems like corrosion, and leakages. The proposed system suggests the robot will be built to clean the residues that are built up inside the pipe. This is done through a brushing mechanism. Not only this robot will also be able to relay live video feedback from the ground to the controller that the user has. By this, the users can verify the cleaning that is done by the robot.

An Enhanced Long-Range Guided-Wave Pipe Inspection Method Based on Local Axial 2-D Signal Acquisition and Processing

An Enhanced Long-Range Guided-Wave Pipe Inspection Method Based on Local Axial 2-D Signal Acquisition and Processing

Determining the Effect of Velocity on Sensor Selection and Position in Non-Destructive Testing With Magnetic Flux Leakage Method: A Pipe Inspection Gauge Design Study With ANSYS Maxwell

Determining the Effect of Velocity on Sensor Selection and Position in Non-Destructive Testing With Magnetic Flux Leakage Method: A Pipe Inspection Gauge Design Study With ANSYS Maxwell

Pipe inspection robots: a review

Pipelines are one of the safe and most economical ways of transporting fluid matters in industries and households. These pipelines get deteriorated due to aging, internal and external corrosion, and so on. This may cause fluid leakages and may contaminate the environment. So, pipelines are inspected regularly to maintain proper functioning and cost-effectiveness. In-pipe inspection robots (IPIR) that move inside pipelines are widely used to carry out inspection operations. IPIR along with visual and other r non-destructive tests (NDT) are proven to be useful compared to manual inspection. Wheel-driven robots, track-driven robots, wall-press robots, pipe inspection gauge (PIG) robots, and many other bio-inspired designs are available. The design parameters and specializations of each type of robot will be presented in this article. Because each robot is created with different factors in mind, such as pipeline diameter, mobility, adaptability, working conditions, and so on, these robots are unique and have different constraints. These topics will be covered in depth in this article, and will ultimately aid in the selection of certain robots based on specific criteria. New design strategies in the pipe inspection industry that have yet to be explored will also be covered in depth.

Autonomous Navigation of In-Pipe Inspection Robot Using Contact Sensor Modules

Pipes, which are the main means of transporting resources, deteriorate over time, thereby leading to defects or accidents. Therefore, periodic inspection of pipes is required, and a pipe robot that moves and inspects the inside of a pipe is one of the solutions. Herein, we propose an inspection robot system capable of autonomous driving inside buried pipes. This robot is called a Multifunctional Robotic Caterpillar for in-pipe INSPECTion (MRCINSPECT) and has been developed for pipes with a 0.5-m diameter. The robot utilizes a caterpillar mechanism and a wall-press mechanism to ensure that it can drive on slopes and generate a high traction force. In addition, we developed a miter bend recognition method using contact sensor modules. Therefore, MRCINSPECT can autonomously navigate in accordance with the estimated pipe information, and simultaneously, an operator can check the robot’s location and pipe information in real time. We verified the performance of the robot system through indoor experiments and its field applicability through outdoor tests.

Nondestructive testing and 3D imaging of PE pipes using terahertz frequency-modulated continuous wave.

Polyethylene (PE) pipes are widely used as the main carrier for the transportation of natural gas, so nondestructive testing techniques for PE pipes are essential for the safety of natural gas transportation. In order to compensate for the shortcomings of conventional inspection methods, a terahertz (THz) three-dimensional imaging system for nondestructive inspection of PE pipes is designed. The system is based on frequency-modulated continuous-wave (FMCW) technology, with a THz source bandwidth of 0.225-0.330THz and an output power of over 5mW, which can achieve submillimeter spatial resolution in three dimensions. The system is used to scan PE pipes in three dimensions in a laboratory environment, and the results show that the system could achieve nondestructive testing and three-dimensional imaging of different defects in PE pipes. In addition, combined with the deep-learning-based THz transformer network, the intelligent identification of different defects is realized, and the accuracy rate can reach up to 88%. The above results provide technical guidance for the application of THz FMCW systems in the actual detection of PE pipes, and provide supplements and improvements for traditional detection methods.

Research Status and Development Trend of Oil and Gas Pipeline Robot

The oil and gas pipeline will have defects such as wear, cracks, corrosion, aging and mechanical damage in the working process, which need to be detected and repaired in time. At present, there are various types of robots in the field of pipeline inspection, including wheeled robots, tracked robots, PIG robots, screw driven robots, walking robots, and inchworm robots. In this paper, the specifications, design and performance of different types of in pipe inspection robots are reviewed. Finally, a summary and prospect are made to provide a theoretical basis for the design and research of robots in this field.

Autonomous control for miniaturized mobile robots in unknown pipe networks.

Despite recent advances in robotic technology, sewer pipe inspection is still limited to conventional approaches that use cable-tethered robots. Such commercially available tethered robots lack autonomy, and their operation must be manually controlled via their tethered cables. Consequently, they can only travel to a certain distance in pipe, cannot access small-diameter pipes, and their deployment incurs high costs for highly skilled operators. In this paper, we introduce a miniaturised mobile robot for pipe inspection. We present an autonomous control strategy for this robot that is effective, stable, and requires only low-computational resources. The robots used here can access pipes as small as 75 mm in diameter. Due to their small size, low carrying capacity, and limited battery supply, our robots can only carry simple sensors, a small processor, and miniature wheel-legs for locomotion. Yet, our control method is able to compensate for these limitations. We demonstrate fully autonomous robot mobility in a sewer pipe network, without any visual aid or power-hungry image processing. The control algorithm allows the robot to correctly recognise each local network configuration, and to make appropriate decisions accordingly. The control strategy was tested using the physical micro robot in a laboratory pipe network. In both simulation and experiment, the robot autonomously and exhaustively explored an unknown pipe network without missing any pipe section while avoiding obstacles. This is a significant advance towards fully autonomous inspection robot systems for sewer pipe networks.

Design and Prototype of Vertical PVC Pipe Climbing Device for Gas Leakage Detection

This paper describes the Design and Prototype of vertical PVC pipe climbing device for gas leakage Detection. However, manually it is very difficult to reach up and inspect the vertical pipes for leakage or damage, because the pipe height is too long and sometime it installed in very high places and also the environmental condition is not safe. To overcome this type of problem and carry out the inspection more easily, we developed a PVC Vertical Pipe Climbing device to climb up and down vertically to detect the gas leakage, and when the leakage is detecting, the device is automatically stop on detected place. In this project we used the butane gas from cigarette lighter and check the leakage up to the level of 4 feet on vertical PVC pipe with the help of toggle switch. Here MQ-2 sensor is used with the device to help us for inspection of pipe.

Predicting the microbiologically induced concrete corrosion in sewer based on XGBoost algorithm

Microbiologically induced concrete corrosion (MICC) is a major reason for sewer pipe replacement and rehabilitation. Predicting the depth of concrete corrosion can help make better decisions on the inspection and rehabilitation of pipes. Due to the limited data available, the models using deep learning methods for predicting MICC are prone to overfitting. This study develops an XGBoost-based MICC model with the benefits of hyperparametric auto-optimization. For this purpose, the factors affecting MICC were sorted out to be used as a guide for selecting attributes when building the database. 379 datasets relevant to the corrosion loss of the origin Portland cement-based materials in sewers were collected from literature to establish a database. It is then randomly partitioned into 8:2 training and test datasets. The hyperparameters were adjusted by performing Bayesian optimization for 200 iterations. On the training and test sets, the R2 scores of the trained model are 0.87 and 0.85, respectively. In addition, an ongoing field trail in a sewer well is introduced to test the generalization ability of the model. By deploying the model on the field inspection data, the predicted corrosion loss after 169 days is 1.6 mm, which ranges between 1.5 and 3.5 mm measured. The developed MICC model is anticipated to perform well when fed future inspection data that is richer and more abundant.

Development of digital tools to enable remote ultrasonic inspection of fusion reactor in-vessel components

The feasibility of a new approach for pipe inspection has been explored using digital twins to enhance guided wave inspection. Guided wave inspection is well established in the oil & gas industry to remotely screen long lengths of predominately straight pipeline for corrosion. However, the inspection of complex pipe geometries remains a challenge. Nuclear fusion facilities are one such potential application. Fusion reactors have a network of many kilometres of service pipes with complex features, including multiple pipe bends. Some of these pipes could be used for actively cooling components such as the first wall and divertor. Guided ultrasonic wave inspection has the significant advantage of offering 100% coverage of the pipe wall over tens of metres of pipe from a remote test location. This is a highly attractive feature, particularly in the nuclear industry where it is important that human presence in high-risk areas is prohibited due to high radiation doses and temperatures. In this work, finite element wave propagation models have been investigated as digital twins of fusion reactor components. The models have been used to calculate bespoke excitation signals that will allow for full volumetric inspections of these complex pipes to be carried out from a remote location. For the first time, a digital twin technique has been developed that is predicted to successfully correct the distortion in guided wave signals caused by multiple pipe bends. The technique is predicted to yield an order of magnitude improvement in detection capability over conventional guided wave inspection. The digital twin technique presented here therefore shows significant promise for the future inspection of nuclear fusion power plant pipes.

Recent Patents on Petroleum Pipe Inspection Gauge in China

Background: As the demand for petroleum products grows, pipes to carry these products are also required extensively. Consequently, petroleum pipe blockage has become a frequent and severe problem in China. In order to ensure trouble-free operation, it is necessary to clean and inspect the petroleum pipe regularly. However, currently available petroleum pipe inspection gauges can block the petroleum pipe easily, and their cleaning efficiency is not as high as desired. Therefore, mechanisms to prevent pipe blockage and ensure high-efficiency cleaning are being given much importance in studies on petroleum pipe inspection gauges. Objective: The aim of the study is to review recent patents related to petroleum pipe inspection gauges in China and forecast possible designs that can mitigate present-day problems associated with petroleum pipe inspection gauges. Methods: This paper has studied and compared various representative patents relevant to the petroleum pipe inspection gauge. Results: A large number of patents filed in China related to petroleum pipe inspection gauges have been studied and the anti-blocking mechanism as well as the cleaning efficiency of the petroleum pipe inspection gauges described in those patents have been analyzed and compared. Forecasts were made regarding the possible development trajectories in the design of petroleum pipe inspection gauges. Conclusion: The problems of easy blockage and poor cleaning efficiency are yet unsolved for petroleum pipe inspection gauges. It is expected that future work will focus on the development of pigging, new materials, power sources, and intelligent control to resolve these issues.

Integration of multiple wall thinning parameters into the probability of detection analysis for long-range pipe inspection using microwaves

A three-dimensional probability of detection (POD) model integrating the depth, circumferential angle, and location of pipe wall thinning (PWT) was proposed for the probabilistic analysis of long-range pipe inspection using microwaves. Microwaves in TM01 mode were used to detect PWT with different sizes and locations (up to 13.5 m). The microwave signals reflected from the PWT were measured and processed, and their amplitudes were extracted and treated as the signal response. The results showed that the signal response was rarely influenced by the axial length of the PWT, while its natural logarithm was proportional to the natural logarithm of the PWT depth and circumferential angle. In addition, the signal response decreased exponentially with the PWT location. Subsequently, a multivariate regression model was established, and the related coefficients were estimated using the maximum likelihood method. The POD calculated from the regression model suggests that a small PWT at a far distance (e.g., 36.0 m) can be reliably detected using microwaves. Compared with a two-dimensional POD model that considers only the PWT cross-section area as the size parameter, the proposed POD model clearly shows that the POD is more dependent on the circumferential angle than on the depth of the PWT.